{"object":"catalog","schema_version":1,"provider":"multiple","source_hash":"6bf05ec353f3a2c2afed772e6db618c5734c60c99ebb12461ad3dd174e185040","catalog_version":"6bf05ec353f3a2c2afed772e6db618c5734c60c99ebb12461ad3dd174e185040","last_success_at":"2026-10-27T06:28:39.625Z","stale":true,"status":"critical","providers":[{"provider":"abliteration","last_success_at":"2026-10-27T21:50:30.343Z","stale":false,"status":"healthy"},{"provider":"amazon-bedrock","last_success_at":"2026-10-27T21:50:30.513Z","stale":false,"status":"healthy"},{"provider":"aws-bedrock","last_success_at":"2026-10-27T06:28:39.625Z","stale":true,"status":"critical"},{"provider":"baseten","last_success_at":"2026-10-27T21:50:31.142Z","stale":false,"status":"healthy"},{"provider":"cheaperinference","last_success_at":"2026-10-27T21:50:31.142Z","stale":false,"status":"healthy"},{"provider":"cloudflare","last_success_at":"2026-10-27T21:50:30.621Z","stale":false,"status":"healthy"},{"provider":"deepinfra","last_success_at":"2026-10-27T21:51:11.427Z","stale":false,"status":"healthy"},{"provider":"fireworks","last_success_at":"2026-10-27T21:53:36.449Z","stale":false,"status":"healthy"},{"provider":"groq","last_success_at":"2026-10-27T21:50:30.659Z","stale":false,"status":"healthy"},{"provider":"kilo","last_success_at":"2026-10-27T21:50:33.115Z","stale":false,"status":"healthy"},{"provider":"near-ai","last_success_at":"2026-10-27T21:49:04.882Z","stale":false,"status":"healthy"},{"provider":"phala-ai","last_success_at":"2026-10-27T21:49:38.730Z","stale":false,"status":"healthy"},{"provider":"relace","last_success_at":"2026-10-27T21:50:30.958Z","stale":false,"status":"healthy"},{"provider":"sail","last_success_at":"2026-10-27T21:50:31.301Z","stale":false,"status":"healthy"},{"provider":"surplusintelligence","last_success_at":"2026-10-27T21:50:31.792Z","stale":false,"status":"healthy"},{"provider":"tinfoil","last_success_at":"2026-10-27T21:51:10.016Z","stale":false,"status":"healthy"},{"provider":"venice","last_success_at":"2026-10-27T21:50:00.510Z","stale":false,"status":"healthy"},{"provider":"wafer","last_success_at":"2026-10-27T21:50:31.623Z","stale":false,"status":"healthy"},{"provider":"zai","last_success_at":"2026-10-27T21:50:32.116Z","stale":false,"status":"healthy"}],"models":[{"id":"google/gemma-4-26b-a4b-uncensored","routeId":"e2ee-gemma-4-26b-a4b-uncensored-p","features":["streaming","web-search"],"provider":"venice","modalities":["text"],"moderation":"uncensored","releasedAt":"2026-05-24","displayName":"Gemma 4 26B A4B Uncensored","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"e2ee","privacyNotes":["The client encrypts prompts before relay and only the verified enclave it encrypted to can decrypt them.","On some routes that enclave is a verified gateway rather than the machine running the model, and it forwards the prompt onward after decrypting it.","E2EE requires attestation verification, encrypted messages, E2EE headers, and response decryption."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":64000,"privacySummary":"End-to-end encrypted inference","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"google/gemma-4-26b-a4b-uncensored-e2ee","shortDescription":"Gemma 4 26B A4B Uncensored is a community fine-tune of Google DeepMind's Gemma 4 26B A4B, modified to reduce refusals. The base model is a Mixture-of-Experts model with 25.2B total and 3.8B active…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/coder3101/gemma-4-26B-A4B-it-heretic","label":"Model source"}],"inputPriceUsdPerMillion":0.19,"outputPriceUsdPerMillion":0.88,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"phala-ai","providerName":"Phala AI","providerRouteId":"phala-ai/gemma-4-26b-a4b-uncensored","routeId":"phala/gemma-4-26b-a4b-uncensored","privacyLevel":"tee","privacySummary":"Verified gateway and pinned confidential model session","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.7,"cacheReadPriceUsdPerMillion":0.049999999999999996,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","contextTokens":262144,"maxOutputTokens":262144,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"}]}],"description":"Gemma 4 26B A4B Uncensored is a community fine-tune of Google DeepMind's Gemma 4 26B A4B, modified to reduce refusals. The base model is a Mixture-of-Experts model with 25.2B total and 3.8B active parameters; this variant takes text input and produces text output."},{"id":"qwen/qwen-2.5-7b","routeId":"e2ee-qwen-2-5-7b-p","features":["streaming","web-search"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2026-03-18","displayName":"Qwen 2.5 7B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"e2ee","privacyNotes":["The client encrypts prompts before relay and only the verified enclave it encrypted to can decrypt them.","On some routes that enclave is a verified gateway rather than the machine running the model, and it forwards the prompt onward after decrypting it.","E2EE requires attestation verification, encrypted messages, E2EE headers, and response decryption."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32000,"privacySummary":"End-to-end encrypted inference","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"qwen/qwen-2.5-7b-e2ee","shortDescription":"Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct","label":"Model source"}],"inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":0.13,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"phala-ai","providerName":"Phala AI","providerRouteId":"phala-ai/qwen-2.5-7b-instruct","routeId":"qwen/qwen-2.5-7b-instruct","privacyLevel":"tee","privacySummary":"Verified gateway and pinned confidential model session","inputPriceUsdPerMillion":0.09999999999999999,"outputPriceUsdPerMillion":0.19999999999999998,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","contextTokens":32768,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct","label":"Creator model card"}]}],"description":"Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification."},{"id":"deepseek/deepseek-v4.1-flash","routeId":"deepseek-v4-1-flash","features":["streaming","tool-calling","vision","reasoning","code-optimized","confidential-compute"],"provider":"tinfoil","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","statusNote":"Experimental: Tinfoil is still productionizing this model; capacity and performance may change.","displayName":"DeepSeek V4.1 Flash","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/deepseek-v4.1-flash","shortDescription":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text,…","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash","label":"Creator model card"}],"inputPriceUsdPerMillion":0.65,"outputPriceUsdPerMillion":1.45,"cacheReadPriceUsdPerMillion":0.13,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"deepseek/deepseek-v4.1-flash","routeId":"deepseek-v4-1-flash","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.0075,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/deepseek-ai-deepseek-v4-1-flash","routeId":"deepseek-ai/DeepSeek-V4.1-Flash","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.006,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/deepseek-ai-deepseek-v4-1-flash","routeId":"deepseek-ai/DeepSeek-V4.1-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.007,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-1-flash","routeId":"deepseek-ai/DeepSeek-V4.1-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.008,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/deepseek-ai-deepseek-v4-1-flash","routeId":"deepseek-ai/DeepSeek-V4.1-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":0.006,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/deepseek-v4-1-flash","routeId":"DeepSeek-V4.1-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.19,"outputPriceUsdPerMillion":0.65,"cacheReadPriceUsdPerMillion":0.006,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/deepseek-v4.1-flash","routeId":"deepseek/deepseek-v4.1-flash","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to a third-party host through a routing service; not hardware-protected, and zero retention is not guaranteed end to end","inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.006,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":393216,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-1-flash","routeId":"deepseek-v4.1-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1045,"outputPriceUsdPerMillion":0.418,"cacheReadPriceUsdPerMillion":0.00209,"cacheWritePriceUsdPerMillion":0.1045,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-1-flash","routeId":"deepseek-v4.1-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.098,"outputPriceUsdPerMillion":0.294,"cacheReadPriceUsdPerMillion":0.00294,"cacheWritePriceUsdPerMillion":0.098,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":false,"sourceReferences":[]}],"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance."},{"id":"google/gemma-4-31b-instruct","routeId":"gemma4-31b","features":["streaming","tool-calling","vision","reasoning","confidential-compute"],"provider":"tinfoil","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["minimal","low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Gemma 4 31B","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/gemma-4-31b","shortDescription":"Gemma 4 31B is the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family, with about 30.7B parameters. It takes text and image input and produces text output, with a…","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"}],"inputPriceUsdPerMillion":0.4,"outputPriceUsdPerMillion":1,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"google/google-gemma-4-31b-instruct","routeId":"google-gemma-4-31b-it","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.12,"outputPriceUsdPerMillion":0.36,"cacheReadPriceUsdPerMillion":0.09,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":256000,"maxOutputTokens":8192,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/google/gemma-4-31B-it","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/gemma-4-31b-it","routeId":"google/gemma-4-31B-it","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/google-gemma-4-31b-it","routeId":"google/gemma-4-31B-it","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.4,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":254720,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemma-4-31b-it","routeId":"gemma-4-31b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.11727,"outputPriceUsdPerMillion":0.335058,"cacheReadPriceUsdPerMillion":0.083765,"cacheWritePriceUsdPerMillion":0.11727,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemma-4-31b-it","routeId":"gemma-4-31b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.084,"outputPriceUsdPerMillion":0.252,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.084,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemma 4 31B is the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family, with about 30.7B parameters. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking, native function calling and pretraining on over 140 languages."},{"id":"meta/llama-3.3-70b","routeId":"llama3-3-70b","features":["streaming","tool-calling","confidential-compute"],"provider":"tinfoil","modalities":["text"],"moderation":"unknown","displayName":"Llama 3.3 70B","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/llama-3.3-70b","shortDescription":"Llama 3.3 70B is Meta's multilingual instruction-tuned text model, released in December 2024. It takes text input and produces text and code with a 128K-token context window, officially supports…","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"}],"inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":2.75,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"meta-llama/llama-3.3-70b","routeId":"llama-3.3-70b","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.7,"outputPriceUsdPerMillion":2.8,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":128000,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/llama-3-3-70b","routeId":"llama-3.3-70b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.073234,"outputPriceUsdPerMillion":0.23435,"cacheReadPriceUsdPerMillion":0.073234,"cacheWritePriceUsdPerMillion":0.073234,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":12288,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/llama-3-3-70b-instruct","routeId":"llama-3.3-70b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.224,"cacheReadPriceUsdPerMillion":0.0105,"cacheWritePriceUsdPerMillion":0.07,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Llama 3.3 70B is Meta's multilingual instruction-tuned text model, released in December 2024. It takes text input and produces text and code with a 128K-token context window, officially supports eight languages, and is built for assistant-style chat."},{"id":"mistralai/voxtral-small-24b-2507","routeId":"voxtral-small-24b","features":["streaming","confidential-compute"],"provider":"tinfoil","modalities":["text"],"moderation":"unknown","displayName":"Voxtral Small 24B","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32768,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/voxtral-small-24b-2507","shortDescription":"Voxtral Small 24B is a text model.","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"},{"url":"https://huggingface.co/mistralai/Voxtral-Small-24B-2507","label":"Creator model card"}],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-26","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/mistral-voxtral-small-24b-2507","routeId":"mistral.voxtral-small-24b-2507","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":32000,"maxOutputTokens":32000,"availability":"available","callable":true,"sourceReferences":[]}]},{"id":"moonshotai/kimi-k3","routeId":"kimi-k3","features":["streaming","tool-calling","vision","reasoning","confidential-compute"],"provider":"tinfoil","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"max","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Kimi K3","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/kimi-k3","shortDescription":"Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text,…","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"}],"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":0.8,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"phala-ai","providerName":"Phala AI","providerRouteId":"phala-ai/kimi-k3","routeId":"moonshotai/kimi-k3","privacyLevel":"tee","privacySummary":"Verified gateway and pinned confidential model session","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","contextTokens":1048576,"maxOutputTokens":1048576,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/moonshotai/Kimi-K3","label":"Creator model card"}]},{"provider":"venice","providerName":"Venice","providerRouteId":"moonshotai/kimi-k3","routeId":"kimi-k3","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":3.75,"outputPriceUsdPerMillion":18.75,"cacheReadPriceUsdPerMillion":0.375,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/moonshotai/Kimi-K3","label":"Model source"}]},{"provider":"fireworks","providerName":"Fireworks AI","providerRouteId":"fireworks/kimi-k3","routeId":"accounts/fireworks/models/kimi-k3","privacyLevel":"private","privacySummary":"Fireworks zero-data-retention routing","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Fireworks Standard serverless pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.fireworks.ai/serverless/pricing","label":"Fireworks serverless pricing"},{"url":"https://docs.fireworks.ai/guides/security_compliance/data_handling","label":"Fireworks zero data retention"},{"url":"https://docs.fireworks.ai/serverless/overview","label":"Fireworks serverless models"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/moonshotai-kimi-k3","routeId":"moonshotai/Kimi-K3","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":2.85,"outputPriceUsdPerMillion":14.25,"cacheReadPriceUsdPerMillion":0.285,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Explicit cache-write multipliers (5m 1.25x, 1h 2x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/moonshotai-kimi-k3","routeId":"moonshotai/Kimi-K3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/moonshotai-kimi-k3","routeId":"moonshotai/kimi-k3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":2.4,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/moonshotai-kimi-k3","routeId":"moonshotai/Kimi-K3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":12.5,"cacheReadPriceUsdPerMillion":0.25,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/kimi-k3","routeId":"Kimi-K3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/kimi-k3","routeId":"kimi-k3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.95,"outputPriceUsdPerMillion":9.75,"cacheReadPriceUsdPerMillion":0.195,"cacheWritePriceUsdPerMillion":1.95,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/kimi-k3","routeId":"kimi-k3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1113,"outputPriceUsdPerMillion":13.125,"cacheReadPriceUsdPerMillion":0.1043,"cacheWritePriceUsdPerMillion":0.1113,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"moonshotai/kimi-k3-e2ee","routeId":"e2ee-kimi-k3-p","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":3.75,"outputPriceUsdPerMillion":18.75,"cacheReadPriceUsdPerMillion":0.375,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/moonshotai/Kimi-K3","label":"Model source"}]}],"description":"Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning."},{"id":"nomic-ai/nomic-embed-text","routeId":"nomic-embed-text","features":["embeddings","confidential-compute"],"provider":"tinfoil","modalities":["embeddings"],"moderation":"unknown","displayName":"Nomic Embed Text","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":8192,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":null,"primaryModality":"embeddings","providerRouteId":"tinfoil/nomic-embed-text","shortDescription":"Nomic Embed Text is an open-source English text embedding model from Nomic AI with a context of up to 8,192 tokens and fully released training data. It produces 768-dimensional embeddings that can be…","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"}],"inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-22","callable":true,"operationalAvailability":"available","description":"Nomic Embed Text is an open-source English text embedding model from Nomic AI with a context of up to 8,192 tokens and fully released training data. It produces 768-dimensional embeddings that can be shortened, and expects task prefixes such as search_query and search_document for retrieval, clustering and classification."},{"id":"openai/gpt-oss-120b","routeId":"gpt-oss-120b","features":["streaming","tool-calling","reasoning","confidential-compute"],"provider":"tinfoil","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GPT OSS 120B","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/gpt-oss-120b","shortDescription":"gpt-oss-120b is OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters, released under the Apache 2.0 license. It takes text input and produces text output…","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"openai/openai-gpt-oss-120b","routeId":"openai-gpt-oss-120b","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/openai/gpt-oss-120b","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/openai-gpt-oss-120b","routeId":"openai/gpt-oss-120b","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.037,"outputPriceUsdPerMillion":0.17,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":131072,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/openai-gpt-oss-120b","routeId":"openai.gpt-oss-120b","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/openai-gpt-oss-120b","routeId":"openai/gpt-oss-120b","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128072,"maxOutputTokens":128072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/openai-gpt-oss-120b","routeId":"openai/gpt-oss-120b","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":130417,"maxOutputTokens":130417,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-oss-120b","routeId":"gpt-oss-120b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.04,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":0.04,"cacheWritePriceUsdPerMillion":0.04,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/openai-gpt-oss-120b","routeId":"openai-gpt-oss-120b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.049,"outputPriceUsdPerMillion":0.21,"cacheReadPriceUsdPerMillion":0.00735,"cacheWritePriceUsdPerMillion":0.049,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"openai/gpt-oss-120b-e2ee","routeId":"e2ee-gpt-oss-120b-p","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":0.13,"outputPriceUsdPerMillion":0.65,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/openai/gpt-oss-120b","label":"Model source"}]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"openai.gpt-oss-120b","routeId":"openai.gpt-oss-120b","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}],"description":"gpt-oss-120b is OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters, released under the Apache 2.0 license. It takes text input and produces text output with a 128K-token context window, configurable low, medium and high reasoning, full chain-of-thought access and native tool use including function calling and structured outputs."},{"id":"z-ai/glm-5.3","routeId":"glm-5-3","features":["streaming","tool-calling","reasoning","code-optimized","confidential-compute"],"provider":"tinfoil","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"max","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GLM 5.3","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/glm-5.3","shortDescription":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"},{"url":"https://huggingface.co/zai-org/GLM-5.3","label":"Creator model card"}],"inputPriceUsdPerMillion":1.8,"outputPriceUsdPerMillion":5.75,"cacheReadPriceUsdPerMillion":0.45,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/zai-org-glm-5-3","routeId":"zai-org/GLM-5.3","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.9,"outputPriceUsdPerMillion":4,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/zai-org-glm-5-3","routeId":"zai-org/GLM-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/z-ai-glm-5-3","routeId":"z-ai/glm-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":2.4,"cacheReadPriceUsdPerMillion":0.075,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/zai-org-glm-5-3","routeId":"zai-org/GLM-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.98,"outputPriceUsdPerMillion":3.08,"cacheReadPriceUsdPerMillion":0.18,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/glm-5-3","routeId":"GLM-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.26,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3","routeId":"z-ai-glm-5-3","privacyLevel":"anonymous","privacySummary":"Anonymous route","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":5.5,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5.3","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5-3","routeId":"glm-5.3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.77,"outputPriceUsdPerMillion":2.42,"cacheReadPriceUsdPerMillion":0.143,"cacheWritePriceUsdPerMillion":0.77,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5-3","routeId":"glm-5.3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.04893,"outputPriceUsdPerMillion":0.98,"cacheReadPriceUsdPerMillion":0.04823,"cacheWritePriceUsdPerMillion":0.04893,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3-e2ee","routeId":"e2ee-glm-5-3-p","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":5.5,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/zai-org/GLM-5.3","label":"Model source"}]}],"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency."},{"id":"deepseek/deepseek-v3.2","routeId":"deepseek/deepseek-v3.2","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"phala-ai","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"DeepSeek V3.2","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":163840,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":64000,"primaryModality":"text","providerRouteId":"phala-ai/deepseek-v3.2","shortDescription":"DeepSeek-V3.2 uses DeepSeek Sparse Attention for efficient long contexts, with strong reasoning and tool use.","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2","label":"Creator model card"}],"inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":1,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"deepseek/deepseek-v3.2","routeId":"deepseek-v3.2","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.33,"outputPriceUsdPerMillion":0.48,"cacheReadPriceUsdPerMillion":0.16,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":160000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/deepseek-v3.2","routeId":"deepseek-ai/DeepSeek-V3.2","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.26,"outputPriceUsdPerMillion":0.38,"cacheReadPriceUsdPerMillion":0.13,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":163840,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/deepseek-v3-2","routeId":"deepseek.v3.2","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.62,"outputPriceUsdPerMillion":1.85,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":164000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v3-2","routeId":"deepseek-v3.2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.403,"outputPriceUsdPerMillion":1.2025,"cacheReadPriceUsdPerMillion":0.403,"cacheWritePriceUsdPerMillion":0.403,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":160000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v3-2","routeId":"deepseek-v3.2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.196,"outputPriceUsdPerMillion":0.294,"cacheReadPriceUsdPerMillion":0.0196,"cacheWritePriceUsdPerMillion":0.196,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":160000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"deepseek.v3.2","routeId":"deepseek.v3.2","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":0.62,"outputPriceUsdPerMillion":1.85,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":164000,"maxOutputTokens":8000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}]},{"id":"deepseek/deepseek-v4-flash-0731","routeId":"deepseek/deepseek-v4-flash-0731","features":["streaming","prompt-caching"],"provider":"phala-ai","modalities":["text"],"moderation":"unknown","displayName":"DeepSeek V4 Flash 0731","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":393216,"primaryModality":"text","providerRouteId":"phala-ai/deepseek-v4-flash-0731","shortDescription":"DeepSeek V4 Flash 0731 is the July 31, 2026 official release of DeepSeek V4 Flash, a Mixture-of-Experts model with 284B total and 13B active parameters and a 1M-token context window. It keeps the…","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","label":"Creator model card"}],"inputPriceUsdPerMillion":0.44,"outputPriceUsdPerMillion":1.32,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"deepseek/deepseek-v4-flash-0731","routeId":"deepseek-v4-flash-0731","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.13,"outputPriceUsdPerMillion":0.26,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/deepseek-ai-deepseek-v4-flash-0731","routeId":"deepseek-ai/DeepSeek-V4-Flash-0731","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.18,"cacheReadPriceUsdPerMillion":0.015,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":384000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/deepseek-ai-deepseek-v4-flash-0731","routeId":"deepseek-ai/DeepSeek-V4-Flash-0731","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.13,"outputPriceUsdPerMillion":0.26,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-flash-0731","routeId":"deepseek-ai/DeepSeek-V4-Flash-0731","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/deepseek-ai-deepseek-v4-flash-0731","routeId":"deepseek-ai/DeepSeek-V4-Flash-0731","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":0.18,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-flash-0731","routeId":"deepseek-v4-flash-0731","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.132,"outputPriceUsdPerMillion":0.396,"cacheReadPriceUsdPerMillion":0.0042,"cacheWritePriceUsdPerMillion":0.132,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-flash-0731","routeId":"deepseek-v4-flash-0731","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0833,"outputPriceUsdPerMillion":0.1666,"cacheReadPriceUsdPerMillion":0.01666,"cacheWritePriceUsdPerMillion":0.0833,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65536,"availability":"available","callable":false,"sourceReferences":[]}],"description":"DeepSeek V4 Flash 0731 is the July 31, 2026 official release of DeepSeek V4 Flash, a Mixture-of-Experts model with 284B total and 13B active parameters and a 1M-token context window. It keeps the preview's architecture and size but is re-post-trained for much stronger agentic performance, with low, high and max reasoning effort."},{"id":"moonshotai/kimi-k2.6","routeId":"moonshotai/kimi-k2.6","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"phala-ai","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Kimi K2.6","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":262144,"primaryModality":"text","providerRouteId":"phala-ai/kimi-k2.6","shortDescription":"Moonshot AI's open-weight multimodal agentic model has 1T total and 32B active parameters, built for long-horizon coding and tool use.","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/moonshotai/Kimi-K2.6","label":"Creator model card"}],"inputPriceUsdPerMillion":1.0899999999999999,"outputPriceUsdPerMillion":4.6,"cacheReadPriceUsdPerMillion":0.37,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"moonshotai/kimi-k2.6","routeId":"kimi-k2-6","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":0.16,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/moonshotai/Kimi-K2.6","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/kimi-k2.6","routeId":"moonshotai/Kimi-K2.6","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":0.15,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/moonshotai-kimi-k2-6","routeId":"moonshotai/Kimi-K2.6","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":4,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":260834,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/kimi-k2-6","routeId":"kimi-k2.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.6175,"outputPriceUsdPerMillion":2.6,"cacheReadPriceUsdPerMillion":0.104,"cacheWritePriceUsdPerMillion":0.6175,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/kimi-k2-6","routeId":"kimi-k2.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.455,"outputPriceUsdPerMillion":2.387,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.455,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"moonshotai/kimi-k2.6-e2ee","routeId":"e2ee-kimi-k2-6","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":0.87,"outputPriceUsdPerMillion":4.12,"cacheReadPriceUsdPerMillion":0.44,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":262144,"maxOutputTokens":8192,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/moonshotai/Kimi-K2.6","label":"Model source"}]}]},{"id":"qwen/qwen-3.5-397b","routeId":"qwen/qwen3.5-397b-a17b","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"phala-ai","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"Qwen 3.5 397B A17B","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":262144,"primaryModality":"text","providerRouteId":"phala-ai/qwen3.5-397b-a17b","shortDescription":"Qwen3.5-397B-A17B is a multimodal Mixture-of-Experts model from Alibaba's Qwen team, with 397B total parameters and 17B active per token. It takes text, image and video input and produces text, with…","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","label":"Creator model card"}],"inputPriceUsdPerMillion":0.55,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":0.22499999999999998,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-5-397b-a17b","routeId":"Qwen/Qwen3.5-397B-A17B","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.45,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":0.22,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":81920,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"venice","providerName":"Venice","providerRouteId":"qwen/qwen-3.5-397b","routeId":"qwen3-5-397b-a17b","privacyLevel":"anonymous","privacySummary":"Venice Anonymous routing","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":4.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","label":"Model source"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-5-397b-a17b","routeId":"qwen3.5-397b-a17b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":2.52,"cacheReadPriceUsdPerMillion":0.07875,"cacheWritePriceUsdPerMillion":0.35,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen3.5-397B-A17B is a multimodal Mixture-of-Experts model from Alibaba's Qwen team, with 397B total parameters and 17B active per token. It takes text, image and video input and produces text, with a 262K-token native context window (extendable to about 1M), a default thinking mode, tool calling and support for 201 languages and dialects."},{"id":"qwen/qwen-3.6-27b","routeId":"qwen/qwen3.6-27b","features":["streaming","vision","prompt-caching"],"provider":"phala-ai","modalities":["text","image"],"moderation":"unknown","displayName":"Qwen 3.6 27B","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":262140,"primaryModality":"text","providerRouteId":"phala-ai/qwen3.6-27b","shortDescription":"Qwen's dense 27B vision-language model supports reasoning, coding and tool-driven tasks.","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/Qwen/Qwen3.6-27B","label":"Creator model card"}],"inputPriceUsdPerMillion":0.32,"outputPriceUsdPerMillion":3.25,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"qwen/qwen-3.6-27b","routeId":"qwen3-6-27b","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.325,"outputPriceUsdPerMillion":3.25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3.6-27B-FP8","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-6-27b","routeId":"Qwen/Qwen3.6-27B","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.32,"outputPriceUsdPerMillion":3.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":81920,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-6-27b","routeId":"qwen3.6-27b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.39,"outputPriceUsdPerMillion":2.34,"cacheReadPriceUsdPerMillion":0.39,"cacheWritePriceUsdPerMillion":0.39,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-6-27b","routeId":"qwen3.6-27b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.224,"outputPriceUsdPerMillion":2.24,"cacheReadPriceUsdPerMillion":0.0336,"cacheWritePriceUsdPerMillion":0.224,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}]},{"id":"qwen/qwen-3.8-27b","routeId":"qwen/qwen3.8-27b","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"phala-ai","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Qwen 3.8 27B","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":262144,"primaryModality":"text","providerRouteId":"phala-ai/qwen3.8-27b","shortDescription":"Qwen 3.8 27B is an open-weight dense model from Alibaba's Qwen team with 27B parameters and a vision encoder, using hybrid Gated DeltaNet and gated attention layers. It takes text, image and video…","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/Qwen/Qwen3.8-27B","label":"Creator model card"}],"inputPriceUsdPerMillion":0.19999999999999998,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":0.049999999999999996,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"qwen/qwen-3.8-27b","routeId":"qwen-3-8-27b","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.45,"outputPriceUsdPerMillion":3.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":262144,"maxOutputTokens":65536,"availability":"preview","callable":true,"statusNote":"Beta","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3.8-27B-FP8","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-8-27b","routeId":"Qwen/Qwen3.8-27B","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-8-27b","routeId":"qwen3.8-27b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.325,"outputPriceUsdPerMillion":1.95,"cacheReadPriceUsdPerMillion":0.0325,"cacheWritePriceUsdPerMillion":0.40625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen-3-8-27b","routeId":"qwen-3-8-27b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.063,"cacheWritePriceUsdPerMillion":0.14,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"qwen/qwen-3.8-27b-e2ee","routeId":"e2ee-qwen3-8-27b","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":0.47,"outputPriceUsdPerMillion":3.53,"cacheReadPriceUsdPerMillion":0.047,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":262144,"maxOutputTokens":8192,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/Qwen/Qwen3.8-27B","label":"Model source"}]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/qwen3-8-27b","routeId":"Qwen3.8-27B","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":2.3,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":false,"sourceReferences":[]}],"description":"Qwen 3.8 27B is an open-weight dense model from Alibaba's Qwen team with 27B parameters and a vision encoder, using hybrid Gated DeltaNet and gated attention layers. It takes text, image and video input with a native 262K-token context window and is built for coding, professional and research work, and long-horizon agentic tasks, with adjustable thinking effort."},{"id":"qwen/qwen-3.8-27b-uncensored","routeId":"phala/qwen3.8-27b-uncensored","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"phala-ai","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"Qwen 3.8 27B Uncensored","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":262144,"primaryModality":"text","providerRouteId":"phala-ai/qwen3.8-27b-uncensored","shortDescription":"HauhauCS's Aggressive adaptation of Qwen3.8-27B retains text and visual capabilities while modifying refusal behavior.","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF","label":"Creator model card"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":0.049999999999999996,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available"},{"id":"z-ai/glm-5.1","routeId":"z-ai/glm-5.1","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"phala-ai","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GLM 5.1","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":202752,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"phala-ai/glm-5.1","shortDescription":"GLM-5.1 is Z.ai's open-weight Mixture-of-Experts model for agentic engineering, with 744B total and 40B active parameters. It takes text input and output with a 200K-token context window and up to…","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/zai-org/GLM-5.1","label":"Creator model card"}],"inputPriceUsdPerMillion":1.21,"outputPriceUsdPerMillion":4.199999999999999,"cacheReadPriceUsdPerMillion":0.6,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.1","routeId":"zai-org-glm-5-1","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":1.54,"outputPriceUsdPerMillion":4.84,"cacheReadPriceUsdPerMillion":0.286,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":200000,"maxOutputTokens":80000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5.1","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5-1","routeId":"glm-5.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.77,"outputPriceUsdPerMillion":2.42,"cacheReadPriceUsdPerMillion":0.143,"cacheWritePriceUsdPerMillion":0.77,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5-1","routeId":"glm-5.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.6762,"outputPriceUsdPerMillion":2.1252,"cacheReadPriceUsdPerMillion":0.12558,"cacheWritePriceUsdPerMillion":0.6762,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":24000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-5.1 is Z.ai's open-weight Mixture-of-Experts model for agentic engineering, with 744B total and 40B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is tuned for coding agents and long-running tool use."},{"id":"z-ai/glm-5.2","routeId":"z-ai/glm-5.2","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"phala-ai","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GLM 5.2","pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","availability":"available","privacyLevel":"tee","privacyNotes":["AnonRouter verifies the gateway CPU attestation, fresh nonce, TLS key, measured deployment and published forwarding code before using this route.","The verified gateway enforces the model CPU and production profile. AnonRouter independently verifies the selected session identity and GPU attestation, then pins that session for dispatch.","Prompts are decrypted inside the verified gateway and model boundaries. This route does not provide client-opaque end-to-end encryption.","On this route the model machine can be operated by a separate compute provider. The verified gateway forwards only to that provider's attested model session, and AnonRouter checks that session's GPU attestation before sending your request.","AnonRouter obscures the caller's identity from the provider. Provider retention beyond serving the request is not guaranteed by AnonRouter."],"providerName":"Phala AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Verified gateway and pinned confidential model session","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"phala-ai/glm-5.2","shortDescription":"GLM-5.2 is Z.ai's open-weight Mixture-of-Experts model for long-horizon tasks and software engineering. It takes text input and output with a 1M-token context window and up to 128K output tokens, and…","sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/zai-org/GLM-5.2","label":"Creator model card"}],"inputPriceUsdPerMillion":1.26,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":0.22,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.2","routeId":"zai-org-glm-5-2","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.26,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5.2","label":"Model source"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/glm-5.2","routeId":"zai-org/GLM-5.2","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":2.4,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter. Explicit cache-write multipliers (5m 1.25x, 1h 2x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":163840,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/zai-org-glm-5-2","routeId":"zai-org/GLM-5.2","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/z-ai-glm-5-2","routeId":"z-ai/glm-5.2","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.4,"outputPriceUsdPerMillion":4,"cacheReadPriceUsdPerMillion":0.08,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5-2","routeId":"glm-5.2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.77,"outputPriceUsdPerMillion":2.42,"cacheReadPriceUsdPerMillion":0.143,"cacheWritePriceUsdPerMillion":0.77,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5-2","routeId":"glm-5.2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.02387,"outputPriceUsdPerMillion":3.08,"cacheReadPriceUsdPerMillion":0.0231,"cacheWritePriceUsdPerMillion":0.02387,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.2-e2ee","routeId":"e2ee-glm-5-2-p","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":5.75,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":524288,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/zai-org/GLM-5.2","label":"Model source"}]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/glm-5-2","routeId":"GLM-5.2","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.19,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.18,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":false,"sourceReferences":[]}],"description":"GLM-5.2 is Z.ai's open-weight Mixture-of-Experts model for long-horizon tasks and software engineering. It takes text input and output with a 1M-token context window and up to 128K output tokens, and offers multiple thinking effort levels to balance performance and latency."},{"id":"alibaba/z-image-turbo","routeId":"z-image-turbo","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-12-03","displayName":"Z-Image Turbo","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"alibaba/z-image-turbo","outputPriceLabel":"$0.01/image","shortDescription":"Z-Image Turbo is the distilled, speed-focused variant of Z-Image, a 6B-parameter open-weight image model from Alibaba's Tongyi-MAI team built on a single-stream diffusion transformer. It generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Tongyi-MAI/Z-Image-Turbo","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Z-Image Turbo is the distilled, speed-focused variant of Z-Image, a 6B-parameter open-weight image model from Alibaba's Tongyi-MAI team built on a single-stream diffusion transformer. It generates images from a text prompt in 8 sampling steps, with photorealistic output and English and Chinese text rendering."},{"id":"baai/bge-en-icl","routeId":"text-embedding-bge-en-icl","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"BGE-EN-ICL","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":8192,"privacySummary":"Venice Private routing","primaryModality":"embeddings","providerRouteId":"baai/bge-en-icl","shortDescription":"BGE-EN-ICL is an English text embedding model from BAAI (Beijing Academy of Artificial Intelligence), built on a 7B-parameter Mistral architecture. It supports in-context learning: adding a task…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/BAAI/bge-en-icl","label":"Model source"}],"inputPriceUsdPerMillion":0.0125,"outputPriceUsdPerMillion":0.0125,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"BGE-EN-ICL is an English text embedding model from BAAI (Beijing Academy of Artificial Intelligence), built on a 7B-parameter Mistral architecture. It supports in-context learning: adding a task instruction and a few example query and answer pairs to a query helps it adapt to new retrieval tasks, and it also works zero-shot."},{"id":"baai/bge-m3","routeId":"text-embedding-bge-m3","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2025-03-14","displayName":"BGE-M3","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":8192,"privacySummary":"Venice Private routing","primaryModality":"embeddings","providerRouteId":"baai/bge-m3","shortDescription":"BGE-M3 is a multilingual text embedding model from BAAI (Beijing Academy of Artificial Intelligence), built from XLM-RoBERTa-large. It supports more than 100 languages and inputs up to 8,192 tokens,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/BAAI/bge-m3","label":"Model source"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"BGE-M3 is a multilingual text embedding model from BAAI (Beijing Academy of Artificial Intelligence), built from XLM-RoBERTa-large. It supports more than 100 languages and inputs up to 8,192 tokens, and one model provides dense, sparse (lexical) and multi-vector retrieval, producing 1,024-dimensional dense embeddings."},{"id":"black-forest-labs/chroma1-hd","routeId":"chroma","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-01-30","displayName":"Chroma1-HD","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/chroma","outputPriceLabel":"$0.01/image","shortDescription":"Chroma1-HD is an 8.9B-parameter open-weight text-to-image model by lodestones (Lodestone Rock), derived from Black Forest Labs' FLUX.1 [schnell] and released under Apache 2.0. It is intended as a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/lodestones/Chroma1-HD","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Chroma1-HD is an 8.9B-parameter open-weight text-to-image model by lodestones (Lodestone Rock), derived from Black Forest Labs' FLUX.1 [schnell] and released under Apache 2.0. It is intended as a neutral base for fine-tuning and generates images from a text prompt, including adult content."},{"id":"canopylabs/orpheus-tts","voices":["dan","jess","leah","leo","mia","tara","zac","zoe"],"routeId":"tts-orpheus","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Orpheus TTS","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$62.50/1M chars","primaryModality":"audio","providerRouteId":"venice/orpheus-tts","outputPriceLabel":"–","shortDescription":"Orpheus TTS is an open-source text-to-speech model from Canopy Labs, built on Llama 3.2 3B as a speech language model. It produces human-like speech with natural intonation, supports emotion control…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/canopylabs/orpheus-3b-0.1-ft","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Orpheus TTS is an open-source text-to-speech model from Canopy Labs, built on Llama 3.2 3B as a speech language model. It produces human-like speech with natural intonation, supports emotion control through simple tags and zero-shot voice cloning, and streams audio for real-time use."},{"id":"deepseek/deepseek-v4-flash-0731-fast","routeId":"deepseek-v4-flash-0731-fast","features":["streaming","tool-calling","reasoning","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-08-09","displayName":"DeepSeek V4 Flash 0731 Fast","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"deepseek/deepseek-v4-flash-0731-fast","shortDescription":"DeepSeek V4 Flash 0731 Fast is a faster serving variant of DeepSeek V4 Flash 0731, DeepSeek's July 2026 release of its 284B-parameter Mixture-of-Experts model with 13B active parameters. The model…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","label":"Model source"}],"inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":0.7,"cacheReadPriceUsdPerMillion":0.0875,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-flash-0731-fast","routeId":"deepseek-v4-flash-0731-fast","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.2975,"outputPriceUsdPerMillion":0.595,"cacheReadPriceUsdPerMillion":0.074375,"cacheWritePriceUsdPerMillion":0.2975,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-flash-0731-fast","routeId":"deepseek-v4-flash-0731-fast","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.245,"outputPriceUsdPerMillion":0.49,"cacheReadPriceUsdPerMillion":0.06125,"cacheWritePriceUsdPerMillion":0.245,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek V4 Flash 0731 Fast is a faster serving variant of DeepSeek V4 Flash 0731, DeepSeek's July 2026 release of its 284B-parameter Mixture-of-Experts model with 13B active parameters. The model has a 1M-token context window and is re-post-trained for stronger agentic performance, with low, high and max reasoning effort."},{"id":"deepseek/deepseek-v4-pro-0813","routeId":"deepseek-v4-pro-0813","features":["streaming","tool-calling","reasoning","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-08-14","displayName":"DeepSeek V4 Pro 0813","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"deepseek/deepseek-v4-pro-0813","shortDescription":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","label":"Model source"}],"inputPriceUsdPerMillion":1.65,"outputPriceUsdPerMillion":4.95,"cacheReadPriceUsdPerMillion":0.165,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":2.6,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1.32,"outputPriceUsdPerMillion":3.96,"cacheReadPriceUsdPerMillion":0.132,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.92,"outputPriceUsdPerMillion":2.77,"cacheReadPriceUsdPerMillion":0.04,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-pro-0813","routeId":"deepseek-v4-pro-0813","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.553184,"outputPriceUsdPerMillion":1.659553,"cacheReadPriceUsdPerMillion":0.018439,"cacheWritePriceUsdPerMillion":0.553184,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-pro-0813","routeId":"deepseek-v4-pro-0813","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.462,"outputPriceUsdPerMillion":1.386,"cacheReadPriceUsdPerMillion":0.0154,"cacheWritePriceUsdPerMillion":0.462,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing."},{"id":"deepseek/deepseek-v4.1-flash-1017","routeId":"deepseek-v4-1-flash-1017","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-17","displayName":"DeepSeek v4.1 Flash (1017)","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"deepseek/deepseek-v4.1-flash-1017","shortDescription":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017","label":"Model source"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.0075,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/deepseek-ai-deepseek-v4-1-flash-1017","routeId":"deepseek-ai/DeepSeek-V4.1-Flash-1017","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.006,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-1-flash-1017","routeId":"deepseek-ai/DeepSeek-V4.1-Flash-1017","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.008,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/deepseek-v4-1-flash-1017","routeId":"DeepSeek-V4.1-Flash-1017","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.13,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.003,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-1-flash-1017","routeId":"deepseek-v4.1-flash-1017","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.075,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":0.0015,"cacheWritePriceUsdPerMillion":0.075,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-1-flash-1017","routeId":"deepseek-v4.1-flash-1017","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.42,"cacheReadPriceUsdPerMillion":0.0021,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance."},{"id":"deepseek/deepseek-v4.1-flash-uncensored","routeId":"deepseek-v4-1-flash-uncensored","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"uncensored","releasedAt":"2026-10-23","displayName":"DeepSeek V4.1 Flash Uncensored","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"deepseek/deepseek-v4.1-flash-uncensored","shortDescription":"DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output)…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8","label":"Model source"}],"inputPriceUsdPerMillion":0.33,"outputPriceUsdPerMillion":1.32,"cacheReadPriceUsdPerMillion":0.00825,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"abliteration","providerName":"abliteration.ai","providerRouteId":"abliteration/abliterated-model-large-flash","routeId":"abliterated-model-large-flash","privacyLevel":"private","privacySummary":"Private route. abliteration.ai processes prompts and outputs in memory and, by default, does not store them or use them for training. It can read content while serving the request.","inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"venice/abliterated-large-flash","routeId":"abliteration-abliterated-model-large-flash","privacyLevel":"anonymous","privacySummary":"Venice Anonymous routing","inputPriceUsdPerMillion":1.25,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":0.125,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.abliteration.ai/models","label":"Model source"}]}],"description":"DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails."},{"id":"google/gemma-3-27b-it","routeId":"google-gemma-3-27b-it","features":["streaming","tool-calling","vision","json-schema","web-search"],"provider":"venice","modalities":["text","image"],"moderation":"unknown","releasedAt":"2025-11-04","displayName":"Gemma 3 27B Instruct","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"google/google-gemma-3-27b-instruct","shortDescription":"Gemma 3 27B Instruct is the 27-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/google/gemma-3-27b-it","label":"Model source"}],"inputPriceUsdPerMillion":0.12,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/google-gemma-3-27b-it","routeId":"google/gemma-3-27b-it","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.08,"outputPriceUsdPerMillion":0.16,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":131072,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/google-gemma-3-27b-it","routeId":"google.gemma-3-27b-it","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.23,"outputPriceUsdPerMillion":0.38,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemma-3-27b-it","routeId":"gemma-3-27b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.056,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":0.0126,"cacheWritePriceUsdPerMillion":0.056,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":40000,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemma-3-27b-it","routeId":"gemma-3-27b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.052,"outputPriceUsdPerMillion":0.2925,"cacheReadPriceUsdPerMillion":0.026,"cacheWritePriceUsdPerMillion":0.052,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":40000,"maxOutputTokens":16384,"availability":"available","callable":false,"sourceReferences":[]}],"description":"Gemma 3 27B Instruct is the 27-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding."},{"id":"google/gemma-4-26b-a4b-it","routeId":"google-gemma-4-26b-a4b-it","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-04-02","displayName":"Gemma 4 26B A4B Instruct","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"google/google-gemma-4-26b-a4b-instruct","shortDescription":"Gemma 4 26B A4B Instruct is the Mixture-of-Experts model in Google DeepMind's open-weight Gemma 4 family, with 25.2B total and 3.8B active parameters per token. It takes text and image input and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/google/gemma-4-26B-A4B-it","label":"Model source"}],"inputPriceUsdPerMillion":0.13,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/google-gemma-4-26b-a4b-it","routeId":"google/gemma-4-26B-A4B-it","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.34,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemma-4-26b-a4b-it","routeId":"gemma-4-26b-a4b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0975,"outputPriceUsdPerMillion":0.39,"cacheReadPriceUsdPerMillion":0.00975,"cacheWritePriceUsdPerMillion":0.0975,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemma-4-26b-a4b-it","routeId":"gemma-4-26b-a4b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.05355,"outputPriceUsdPerMillion":0.1785,"cacheReadPriceUsdPerMillion":0.02975,"cacheWritePriceUsdPerMillion":0.05355,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemma 4 26B A4B Instruct is the Mixture-of-Experts model in Google DeepMind's open-weight Gemma 4 family, with 25.2B total and 3.8B active parameters per token. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling."},{"id":"google/gemma-4-uncensored","routeId":"gemma-4-uncensored","features":["streaming","tool-calling","vision","json-schema","web-search"],"provider":"venice","modalities":["text","image"],"moderation":"uncensored","releasedAt":"2026-04-13","displayName":"Gemma 4 Uncensored","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"google/gemma-4-uncensored","shortDescription":"Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Jiunsong/supergemma4-26b-uncensored-gguf-v2","label":"Model source"}],"inputPriceUsdPerMillion":0.1625,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemma-4-uncensored","routeId":"gemma-4-uncensored","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.11375,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.01708,"cacheWritePriceUsdPerMillion":0.11375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation."},{"id":"hexgrad/kokoro-82m","voices":["af_alloy","af_aoede","af_bella","af_heart","af_jadzia","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa","bf_alice","bf_emma","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","ef_dora","em_alex","em_santa","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo","pf_dora","pm_alex","pm_santa","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang"],"routeId":"tts-kokoro","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2025-03-19","displayName":"Kokoro 82M","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$3.50/1M chars","primaryModality":"audio","providerRouteId":"venice/kokoro-text-to-speech","outputPriceLabel":"–","shortDescription":"Kokoro is an open-weight text-to-speech model from hexgrad with 82 million parameters, built on the StyleTTS 2 and ISTFTNet architectures. Released under Apache 2.0, it offers 54 voices across 8…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/hexgrad/Kokoro-82M","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Kokoro is an open-weight text-to-speech model from hexgrad with 82 million parameters, built on the StyleTTS 2 and ISTFTNet architectures. Released under Apache 2.0, it offers 54 voices across 8 languages and is designed to give natural speech while staying fast and inexpensive to run."},{"id":"meta/llama-3.2-3b","routeId":"llama-3.2-3b","features":["streaming","tool-calling","web-search"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2024-10-03","displayName":"Llama 3.2 3B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"meta-llama/llama-3.2-3b","shortDescription":"Llama 3.2 3B is a small multilingual text model from Meta, instruction tuned for assistant-style chat and agentic tasks such as knowledge retrieval, summarization and prompt rewriting. It takes text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/meta-llama/Llama-3.2-3B","label":"Model source"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/llama-3-2-3b-instruct","routeId":"llama-3.2-3b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.035,"outputPriceUsdPerMillion":0.231,"cacheReadPriceUsdPerMillion":0.00525,"cacheWritePriceUsdPerMillion":0.035,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Llama 3.2 3B is a small multilingual text model from Meta, instruction tuned for assistant-style chat and agentic tasks such as knowledge retrieval, summarization and prompt rewriting. It takes text input and produces text and code with a 128K-token context window, and officially supports eight languages."},{"id":"meta/muse-spark-open","routeId":"muse-spark-open","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"xhigh","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-15","displayName":"Muse Spark Open","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Venice Private routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"venice/muse-spark-open","shortDescription":"Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B","label":"Model source"}],"inputPriceUsdPerMillion":1.5625,"outputPriceUsdPerMillion":5.3125,"cacheReadPriceUsdPerMillion":0.1875,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/muse-spark-open","routeId":"muse-spark-open","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.8125,"outputPriceUsdPerMillion":2.7625,"cacheReadPriceUsdPerMillion":0.0975,"cacheWritePriceUsdPerMillion":0.8125,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/muse-spark-open","routeId":"muse-spark-open","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":2.975,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.875,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window."},{"id":"microsoft/multilingual-e5-large-instruct","routeId":"text-embedding-multilingual-e5-large-instruct","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Multilingual E5 Large Instruct","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":512,"privacySummary":"Venice Private routing","primaryModality":"embeddings","providerRouteId":"microsoft/multilingual-e5-large-instruct","shortDescription":"Multilingual E5 Large Instruct is a text embedding model from Microsoft researchers, initialized from XLM-RoBERTa-large with 24 layers and 1,024-dimensional embeddings. It covers about 100 languages…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/intfloat/multilingual-e5-large-instruct","label":"Model source"}],"inputPriceUsdPerMillion":0.0125,"outputPriceUsdPerMillion":0.0125,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Multilingual E5 Large Instruct is a text embedding model from Microsoft researchers, initialized from XLM-RoBERTa-large with 24 layers and 1,024-dimensional embeddings. It covers about 100 languages and takes inputs up to 512 tokens, with each query paired with a one-sentence task instruction to guide retrieval and similarity tasks."},{"id":"minimax/minimax-m2.5","routeId":"minimax-m25","features":["streaming","tool-calling","reasoning","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-02-12","displayName":"MiniMax M2.5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Private routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"minimax/minimax-m2.5","shortDescription":"MiniMax-M2.5 is MiniMax's open-weight large language model for coding, agentic tool use and search, and office work. It takes text input and produces text output, and is built for complex multi-step…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","label":"Model source"}],"inputPriceUsdPerMillion":0.27,"outputPriceUsdPerMillion":0.95,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/minimax-minimax-m2-5","routeId":"minimax.minimax-m2.5","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":196000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/minimax-m2-5","routeId":"minimax-m2.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.195,"outputPriceUsdPerMillion":0.78,"cacheReadPriceUsdPerMillion":0.0195,"cacheWritePriceUsdPerMillion":0.24375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m2-5","routeId":"minimax-m2.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.189,"outputPriceUsdPerMillion":0.665,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.189,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiniMax-M2.5 is MiniMax's open-weight large language model for coding, agentic tool use and search, and office work. It takes text input and produces text output, and is built for complex multi-step agentic tasks and deliverable outputs such as Word, PowerPoint and Excel documents."},{"id":"minimax/minimax-m2.7","routeId":"minimax-m27","features":["streaming","tool-calling","reasoning","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-03-18","displayName":"MiniMax M2.7","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Private routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"minimax/minimax-m2.7","shortDescription":"MiniMax-M2.7 is MiniMax's open-weight model of about 229B parameters, built for agentic and professional work. It handles software engineering (debugging, refactoring, code security), complex agent…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7","label":"Model source"}],"inputPriceUsdPerMillion":0.375,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":0.06875,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/minimax-m2-7","routeId":"minimax-m2.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.195,"outputPriceUsdPerMillion":0.78,"cacheReadPriceUsdPerMillion":0.039,"cacheWritePriceUsdPerMillion":0.24375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m2-7","routeId":"minimax-m2.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.042,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiniMax-M2.7 is MiniMax's open-weight model of about 229B parameters, built for agentic and professional work. It handles software engineering (debugging, refactoring, code security), complex agent harnesses with tool search, and editing of Word, Excel and PowerPoint files."},{"id":"minimax/minimax-m3","routeId":"minimax-m3-preview","features":["streaming","tool-calling","reasoning","vision","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-06-12","displayName":"MiniMax M3 Preview","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":524288,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"minimax/minimax-m3-preview","shortDescription":"MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/MiniMaxAI/MiniMax-M3","label":"Model source"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.06,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/minimaxai-minimax-m3","routeId":"MiniMaxAI/MiniMax-M3","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.28,"outputPriceUsdPerMillion":1.1,"cacheReadPriceUsdPerMillion":0.056,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":524288,"maxOutputTokens":512000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/minimax-m3","routeId":"minimax-m3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.225,"outputPriceUsdPerMillion":0.9,"cacheReadPriceUsdPerMillion":0.09,"cacheWritePriceUsdPerMillion":0.45,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m3","routeId":"minimax-m3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.042,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m3-preview","routeId":"minimax-m3-preview","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.042,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":524288,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of up to 1M tokens, and can also operate a desktop computer."},{"id":"mistralai/mistral-small-3.2-24b-instruct-2506","routeId":"mistral-small-3-2-24b-instruct","features":["streaming","tool-calling","vision","json-schema","web-search"],"provider":"venice","modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-01-15","displayName":"Mistral Small 3.2 24B Instruct","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"mistralai/mistral-small-3.2-24b-instruct","shortDescription":"Mistral Small 3.2 is a 24B open-weight model from Mistral AI that accepts text and image input, released in June 2025 as a minor update to Mistral Small 3.1. It improves instruction following,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","label":"Model source"}],"inputPriceUsdPerMillion":0.09375,"outputPriceUsdPerMillion":0.25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/mistralai-mistral-small-3-2-24b-instruct-2506","routeId":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.075,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/mistral-small-3-2-24b-instruct","routeId":"mistral-small-3.2-24b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0525,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":0.00784,"cacheWritePriceUsdPerMillion":0.0525,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Mistral Small 3.2 is a 24B open-weight model from Mistral AI that accepts text and image input, released in June 2025 as a minor update to Mistral Small 3.1. It improves instruction following, produces fewer repetitive or infinite generations, and has a more robust function-calling template."},{"id":"mistralai/mistral-uncensored-1.2","routeId":"venice-uncensored-1-2","features":["streaming","tool-calling","vision","json-schema","web-search"],"provider":"venice","modalities":["text","image"],"moderation":"uncensored","releasedAt":"2026-04-01","displayName":"Mistral Uncensored 1.2","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"venice/venice-uncensored-1.2","shortDescription":"Mistral Uncensored 1.2 is an uncensored 24B fine-tune of Mistral Small 24B, built on Dolphin Mistral 24B, made for open-ended dialogue, roleplay and creative writing with minimal content…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","label":"Model source"}],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.9,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/venice-uncensored-1-2","routeId":"venice-uncensored-1.2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.63,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.14,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Mistral Uncensored 1.2 is an uncensored 24B fine-tune of Mistral Small 24B, built on Dolphin Mistral 24B, made for open-ended dialogue, roleplay and creative writing with minimal content restrictions. It accepts text and image input, supports function calling and structured output, and has a 128K-token context window."},{"id":"mistralai/mistral-uncensored-roleplay","routeId":"venice-uncensored-role-play","features":["streaming","tool-calling","vision","json-schema","web-search"],"provider":"venice","modalities":["text","image"],"moderation":"uncensored","releasedAt":"2026-02-20","displayName":"Mistral Uncensored Roleplay","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"venice/venice-role-play-uncensored","shortDescription":"Mistral Uncensored Roleplay is an uncensored 24B fine-tune of Mistral Small 24B for character-driven roleplay, immersive storytelling and open-ended creative writing with minimal content…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/dphnAI/24B-3.2-RP-K2-final","label":"Model source"}],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/venice-uncensored-role-play","routeId":"venice-uncensored-role-play","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.4,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.35,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Mistral Uncensored Roleplay is an uncensored 24B fine-tune of Mistral Small 24B for character-driven roleplay, immersive storytelling and open-ended creative writing with minimal content restrictions. It accepts text and image input, supports function calling and has a 128K-token context window."},{"id":"moonshotai/kimi-k2.5","routeId":"kimi-k2-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-01-27","displayName":"Kimi K2.5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"moonshotai/kimi-k2.5","shortDescription":"Kimi K2.5 is Moonshot AI's open-weight, natively multimodal Mixture-of-Experts model with 1T total and 32B active parameters and a 256K-token context window. It accepts text and image input, offers…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/moonshotai/Kimi-K2.5","label":"Model source"}],"inputPriceUsdPerMillion":0.56,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":0.22,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/moonshotai-kimi-k2-5","routeId":"moonshotai.kimi-k2.5","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.6,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/kimi-k2-5","routeId":"kimi-k2.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.39,"outputPriceUsdPerMillion":1.95,"cacheReadPriceUsdPerMillion":0.065,"cacheWritePriceUsdPerMillion":0.39,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/kimi-k2-5","routeId":"kimi-k2.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.35,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Kimi K2.5 is Moonshot AI's open-weight, natively multimodal Mixture-of-Experts model with 1T total and 32B active parameters and a 256K-token context window. It accepts text and image input, offers thinking and instant modes, and is built for coding, visual coding, agent swarm workflows and office tasks."},{"id":"moonshotai/kimi-k2.7-code","routeId":"kimi-k2-7-code","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-06-13","displayName":"Kimi K2.7 Code","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"moonshotai/kimi-k2.7-code","shortDescription":"Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/moonshotai/Kimi-K2.7-Code","label":"Model source"}],"inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":0.16,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/kimi-k2-7-code","routeId":"kimi-k2.7-code","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.6175,"outputPriceUsdPerMillion":2.6,"cacheReadPriceUsdPerMillion":0.104,"cacheWritePriceUsdPerMillion":0.6175,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/kimi-k2-7-code","routeId":"kimi-k2.7-code","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.392,"outputPriceUsdPerMillion":2.17,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.392,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context."},{"id":"moonshotai/kimi-k3-fast","routeId":"kimi-k3-fast-api","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"max","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-08-03","displayName":"Kimi K3 Fast","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"moonshotai/kimi-k3-fast","shortDescription":"Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/moonshotai/Kimi-K3","label":"Model source"}],"inputPriceUsdPerMillion":4.5,"outputPriceUsdPerMillion":22.5,"cacheReadPriceUsdPerMillion":0.45,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/kimi-k3-fast","routeId":"kimi-k3-fast","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.78547,"outputPriceUsdPerMillion":18.92735,"cacheReadPriceUsdPerMillion":0.378547,"cacheWritePriceUsdPerMillion":3.78547,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/kimi-k3-fast-api","routeId":"kimi-k3-fast-api","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.15,"outputPriceUsdPerMillion":15.75,"cacheReadPriceUsdPerMillion":0.315,"cacheWritePriceUsdPerMillion":3.15,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback."},{"id":"nousresearch/hermes-3-llama-3.1-405b","routeId":"hermes-3-llama-3.1-405b","features":["streaming","web-search"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2025-09-25","statusNote":"Venice removes this route on 2026-11-02; replacement: deepseek-v4-1-flash.","displayName":"Hermes 3 Llama 3.1 405B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"deprecated","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"meta-llama/hermes-3-llama-3.1-405b","shortDescription":"Hermes 3 405B is Nous Research's full-parameter fine-tune of Meta's Llama 3.1 405B, focused on aligning the model to the user with strong steering and control. It improves agentic behavior, roleplay,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B","label":"Model source"}],"inputPriceUsdPerMillion":1.1,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/hermes-3-llama-3-1-405b","routeId":"hermes-3-llama-3.1-405b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.7,"outputPriceUsdPerMillion":0.7,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.7,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Hermes 3 405B is Nous Research's full-parameter fine-tune of Meta's Llama 3.1 405B, focused on aligning the model to the user with strong steering and control. It improves agentic behavior, roleplay, reasoning, multi-turn conversation and long-context coherence, and supports function calling and JSON structured outputs."},{"id":"nvidia/nemotron-embed-vl-1b-v2","routeId":"text-embedding-nemotron-embed-vl-1b-v2","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Llama Nemotron Embed VL 1B v2","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32768,"privacySummary":"Venice Private routing","primaryModality":"embeddings","providerRouteId":"nvidia/nemotron-embed-vl-1b-v2","shortDescription":"Llama Nemotron Embed VL 1B v2 is NVIDIA's multimodal embedding model for question-answering retrieval over documents. It pairs a Llama 3.2 1B language model with a SigLIP2 image encoder (about 1.7B…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/nvidia/llama-nemotron-embed-vl-1b-v2","label":"Model source"}],"inputPriceUsdPerMillion":0.0125,"outputPriceUsdPerMillion":0.0125,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Llama Nemotron Embed VL 1B v2 is NVIDIA's multimodal embedding model for question-answering retrieval over documents. It pairs a Llama 3.2 1B language model with a SigLIP2 image encoder (about 1.7B parameters total) and embeds text queries and document pages given as images, text or both, including tables, charts and infographics, as 2,048-dimensional vectors."},{"id":"nvidia/nvidia-nemotron-3-nano-30b","routeId":"nvidia-nemotron-3-nano-30b-a3b","features":["streaming","tool-calling","json-schema","web-search"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2026-01-27","displayName":"NVIDIA Nemotron 3 Nano 30B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"nvidia/nvidia-nemotron-3-nano-30b","shortDescription":"NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/nvidia/Nemotron-3-Nano-30B-A3B","label":"Model source"}],"inputPriceUsdPerMillion":0.075,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/nvidia-nemotron-nano-3-30b","routeId":"nvidia.nemotron-nano-3-30b","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.24,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/nvidia-nemotron-3-nano-30b-a3b","routeId":"nvidia-nemotron-3-nano-30b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0525,"outputPriceUsdPerMillion":0.21,"cacheReadPriceUsdPerMillion":0.00784,"cacheWritePriceUsdPerMillion":0.0525,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks."},{"id":"nvidia/nvidia-nemotron-3-ultra","routeId":"nvidia-nemotron-3-ultra-550b-a55b","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-06-04","displayName":"NVIDIA Nemotron 3 Ultra","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"nvidia/nvidia-nemotron-3-ultra","shortDescription":"NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","label":"Model source"}],"inputPriceUsdPerMillion":0.625,"outputPriceUsdPerMillion":3.125,"cacheReadPriceUsdPerMillion":0.1875,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/nvidia-nemotron-3-ultra-550b-a55b","routeId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2.2,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter. Explicit cache-write multipliers (5m 1.25x, 1h 2x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/nvidia-nvidia-nemotron-3-ultra-550b-a55b","routeId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.6,"outputPriceUsdPerMillion":2.4,"cacheReadPriceUsdPerMillion":0.12,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":202800,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/nvidia-nemotron-3-ultra-550b-a55b","routeId":"nvidia-nemotron-3-ultra-550b-a55b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.4375,"outputPriceUsdPerMillion":2.1875,"cacheReadPriceUsdPerMillion":0.13125,"cacheWritePriceUsdPerMillion":0.4375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context."},{"id":"nvidia/nvidia-nemotron-3.5-super-vl","routeId":"nvidia-nemotron-3-5-super-vl-120b-a12b","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-10-16","displayName":"NVIDIA Nemotron 3.5 Super VL 120B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Venice Private routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"nvidia/nvidia-nemotron-3.5-super-vl-120b","shortDescription":"NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","label":"Model source"}],"inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":1.25,"cacheReadPriceUsdPerMillion":0.125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/nvidia-nvidia-nemotron-3-5-super-vl","routeId":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/nemotron-3-5-super-vl","routeId":"nemotron-3.5-super-vl","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, combining reasoning, instruction following, and tool use for long-running agentic workflows."},{"id":"qwen/qwen-3-235b-a22b-instruct-2507","routeId":"qwen3-235b-a22b-instruct-2507","features":["streaming","tool-calling","json-schema","web-search"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2025-04-29","displayName":"Qwen 3 235B A22B Instruct 2507","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"qwen/qwen-3-235b-a22b-instruct-2507","shortDescription":"Qwen 3 235B A22B Instruct 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant runs in non-thinking mode only, answering…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8","label":"Model source"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.75,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-235b-a22b-instruct-2507","routeId":"Qwen/Qwen3-235B-A22B-Instruct-2507","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":0.55,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-235b-a22b-2507","routeId":"qwen3-235b-a22b-2507","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.063,"outputPriceUsdPerMillion":0.385,"cacheReadPriceUsdPerMillion":0.00945,"cacheWritePriceUsdPerMillion":0.063,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3 235B A22B Instruct 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant runs in non-thinking mode only, answering directly without reasoning blocks, and has a native 262K-token context window."},{"id":"qwen/qwen-3-235b-a22b-thinking-2507","routeId":"qwen3-235b-a22b-thinking-2507","features":["streaming","tool-calling","reasoning","json-schema","web-search"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2025-04-29","displayName":"Qwen 3 235B A22B Thinking 2507","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"qwen/qwen-3-235b-a22b-thinking-2507","shortDescription":"Qwen 3 235B A22B Thinking 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant always thinks before answering, for complex…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8","label":"Model source"}],"inputPriceUsdPerMillion":0.45,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-235b-a22b-thinking-2507","routeId":"qwen3-235b-a22b-thinking-2507","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.315,"outputPriceUsdPerMillion":2.45,"cacheReadPriceUsdPerMillion":0.04725,"cacheWritePriceUsdPerMillion":0.315,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3 235B A22B Thinking 2507 is the July 2025 update of Alibaba's Qwen3 Mixture-of-Experts model, with 235B total and 22B active parameters. This variant always thinks before answering, for complex reasoning tasks, and has a native 262K-token context window."},{"id":"qwen/qwen-3-coder-480b-turbo","routeId":"qwen3-coder-480b-a35b-instruct-turbo","features":["streaming","tool-calling","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2026-01-27","displayName":"Qwen 3 Coder 480B Turbo","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3-coder-480b-turbo","shortDescription":"Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","label":"Model source"}],"inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":0.04,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-coder-480b-a35b-instruct-turbo","routeId":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-coder-turbo","routeId":"qwen3-coder-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.245,"outputPriceUsdPerMillion":1.05,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":0.245,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a native 262K-token context window and is built for agentic coding, tool calling and repository-scale work."},{"id":"qwen/qwen-3-next-80b","routeId":"qwen3-next-80b","features":["streaming","tool-calling","json-schema","web-search"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2025-04-29","displayName":"Qwen 3 Next 80B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"qwen/qwen-3-next-80b","shortDescription":"Qwen 3 Next 80B is a Mixture-of-Experts model from Alibaba's Qwen team with 80B total and 3B active parameters, using hybrid Gated DeltaNet and gated attention layers with multi-token prediction for…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct","label":"Model source"}],"inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.9,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-next-80b-a3b-instruct","routeId":"Qwen/Qwen3-Next-80B-A3B-Instruct","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":1.1,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-next-80b-a3b-instruct","routeId":"qwen3-next-80b-a3b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0975,"outputPriceUsdPerMillion":0.78,"cacheReadPriceUsdPerMillion":0.0975,"cacheWritePriceUsdPerMillion":0.0975,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-next-80b-a3b-instruct","routeId":"qwen3-next-80b-a3b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.063,"outputPriceUsdPerMillion":0.77,"cacheReadPriceUsdPerMillion":0.00945,"cacheWritePriceUsdPerMillion":0.063,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3 Next 80B is a Mixture-of-Experts model from Alibaba's Qwen team with 80B total and 3B active parameters, using hybrid Gated DeltaNet and gated attention layers with multi-token prediction for efficient long-context work. It takes text input and output with a native 262K-token context window."},{"id":"qwen/qwen-3-tts-0.6b","voices":["Aiden","Dylan","Eric","Ono_Anna","Ryan","Serena","Sohee","Uncle_Fu","Vivian"],"routeId":"tts-qwen3-0-6b","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-03-10","displayName":"Qwen3-TTS 0.6B","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$87.50/1M chars","primaryModality":"audio","providerRouteId":"qwen/qwen-3-tts-0.6b","outputPriceLabel":"–","shortDescription":"Qwen3-TTS 0.6B is the smaller text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-TTS","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3-TTS 0.6B is the smaller text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including Chinese, English, Japanese and Spanish, supports streaming output, and balances quality with efficiency, with variants for preset voices and 3-second voice cloning."},{"id":"qwen/qwen-3-tts-1.7b","voices":["Aiden","Dylan","Eric","Ono_Anna","Ryan","Serena","Sohee","Uncle_Fu","Vivian"],"routeId":"tts-qwen3-1-7b","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-03-10","displayName":"Qwen3-TTS 1.7B","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$112.50/1M chars","primaryModality":"audio","providerRouteId":"qwen/qwen-3-tts-1.7b","outputPriceLabel":"–","shortDescription":"Qwen3-TTS 1.7B is the larger text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-TTS","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3-TTS 1.7B is the larger text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including Chinese, English, Japanese and Spanish, supports streaming output and instruction-based style control, with variants for preset voices, voice design from a text description and 3-second voice cloning."},{"id":"qwen/qwen-3.6-35b-a3b","routeId":"qwen3-6-35b-a3b","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-20","statusNote":"Beta","displayName":"Qwen 3.6 35B A3B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"preview","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3.6-35b-a3b","shortDescription":"Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8","label":"Model source"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":1,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen3.6-35b-a3b","routeId":"Qwen/Qwen3.6-35B-A3B","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.95,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-6-35b-a3b","routeId":"qwen3.6-35b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.24375,"outputPriceUsdPerMillion":1.4625,"cacheReadPriceUsdPerMillion":0.24375,"cacheWritePriceUsdPerMillion":0.24375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-6-35b-a3b","routeId":"qwen3-6-35b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.7,"cacheReadPriceUsdPerMillion":0.0105,"cacheWritePriceUsdPerMillion":0.07,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window."},{"id":"qwen/qwen-3.8-2.4t","routeId":"qwen-3-8-2-4t-a95b","features":["streaming","tool-calling","reasoning","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-08-12","displayName":"Qwen 3.8 2.4T","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3.8-2.4t","shortDescription":"Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B","label":"Model source"}],"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.3125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-8-2-4t-a95b","routeId":"qwen3.8-2.4t-a95b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":3.9,"cacheReadPriceUsdPerMillion":0.1625,"cacheWritePriceUsdPerMillion":1.625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-8-2-4t-a95b","routeId":"qwen3.8-2.4t-a95b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.2,"cacheReadPriceUsdPerMillion":0.175,"cacheWritePriceUsdPerMillion":1.4,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window."},{"id":"qwen/qwen3-embedding-0.6b","routeId":"text-embedding-qwen3-0-6b","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Qwen3 Embedding 0.6B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32768,"privacySummary":"Venice Private routing","primaryModality":"embeddings","providerRouteId":"qwen/qwen3-embedding-0.6b","shortDescription":"Qwen3 Embedding 0.6B is the smallest text embedding model in Alibaba's Qwen team's Qwen3 Embedding series, with 28 layers and a 32K-token context. It supports more than 100 natural and programming…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-Embedding-0.6B","label":"Model source"}],"inputPriceUsdPerMillion":0.0125,"outputPriceUsdPerMillion":0.0125,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3 Embedding 0.6B is the smallest text embedding model in Alibaba's Qwen team's Qwen3 Embedding series, with 28 layers and a 32K-token context. It supports more than 100 natural and programming languages, takes optional task instructions, and produces embeddings of up to 1,024 dimensions that can be set to a smaller size."},{"id":"qwen/qwen3-embedding-8b","routeId":"text-embedding-qwen3-8b","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Qwen3 Embedding 8B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32768,"privacySummary":"Venice Private routing","primaryModality":"embeddings","providerRouteId":"qwen/qwen3-embedding-8b","shortDescription":"Qwen3 Embedding 8B is the largest text embedding model in Alibaba's Qwen team's Qwen3 Embedding series, with 36 layers and a 32K-token context. It supports more than 100 natural and programming…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-Embedding-8B","label":"Model source"}],"inputPriceUsdPerMillion":0.0125,"outputPriceUsdPerMillion":0.0125,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3 Embedding 8B is the largest text embedding model in Alibaba's Qwen team's Qwen3 Embedding series, with 36 layers and a 32K-token context. It supports more than 100 natural and programming languages, takes optional task instructions, and produces embeddings of up to 4,096 dimensions that can be set anywhere from 32 to 4,096."},{"id":"qwen/qwen3-vl-235b","routeId":"qwen3-vl-235b-a22b","features":["streaming","tool-calling","vision","json-schema","web-search","prompt-caching"],"provider":"venice","modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-01-16","displayName":"Qwen3 VL 235B","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"qwen/qwen3-vl-235b","shortDescription":"Qwen3-VL 235B A22B Instruct is Alibaba's Qwen vision-language Mixture-of-Experts model with about 236B total and 22B active parameters. It takes image, video and text input and produces text, with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct","label":"Model source"}],"inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":1.9,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-vl-235b-a22b-instruct","routeId":"Qwen/Qwen3-VL-235B-A22B-Instruct","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.88,"cacheReadPriceUsdPerMillion":0.11,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/qwen-qwen3-vl-235b-a22b-instruct","routeId":"qwen.qwen3-vl-235b-a22b-instruct","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.53,"outputPriceUsdPerMillion":2.66,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-vl-235b-a22b-instruct","routeId":"qwen3-vl-235b-a22b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.26,"outputPriceUsdPerMillion":1.04,"cacheReadPriceUsdPerMillion":0.26,"cacheWritePriceUsdPerMillion":0.26,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-vl-235b-a22b-instruct","routeId":"qwen3-vl-235b-a22b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.147,"outputPriceUsdPerMillion":1.33,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":0.147,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"qwen.qwen3-vl-235b-a22b-instruct","routeId":"qwen.qwen3-vl-235b-a22b-instruct","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":0.53,"outputPriceUsdPerMillion":2.66,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":8000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}],"description":"Qwen3-VL 235B A22B Instruct is Alibaba's Qwen vision-language Mixture-of-Experts model with about 236B total and 22B active parameters. It takes image, video and text input and produces text, with a native 256K-token context, OCR in 32 languages, GUI agent abilities and long-video understanding."},{"id":"resemble-ai/chatterbox-hd","voices":["Aurora","Blade","Britney","Carl","Cliff","Richard","Rico","Siobhan","Vicky"],"routeId":"tts-chatterbox-hd","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Chatterbox HD","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$50.00/1M chars","primaryModality":"audio","providerRouteId":"venice/chatterbox-hd-resemble-ai","outputPriceLabel":"–","shortDescription":"Chatterbox HD is a text-to-speech model from Resemble AI's Chatterbox family. The open-source Chatterbox models are built on a 0.5B Llama backbone and support zero-shot voice cloning from a short…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/ResembleAI/chatterbox","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Chatterbox HD is a text-to-speech model from Resemble AI's Chatterbox family. The open-source Chatterbox models are built on a 0.5B Llama backbone and support zero-shot voice cloning from a short reference clip and control over emotional intensity, with a PerTh watermark in generated audio."},{"id":"stabilityai/anime-wai","routeId":"wai-Illustrious","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-01-11","displayName":"WAI-Illustrious-SDXL","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/anime-wai","outputPriceLabel":"$0.01/image","shortDescription":"WAI-Illustrious-SDXL is a community anime checkpoint by the Civitai creator WAI0731, fine-tuned from OnomaAI's Illustrious XL, an SDXL-based model. It generates anime and illustration-style images…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://civitai.com/models/827184?modelVersionId=1761560","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"WAI-Illustrious-SDXL is a community anime checkpoint by the Civitai creator WAI0731, fine-tuned from OnomaAI's Illustrious XL, an SDXL-based model. It generates anime and illustration-style images from a text prompt, including adult content."},{"id":"stabilityai/lustify-sdxl","routeId":"lustify-sdxl","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-02-04","displayName":"Lustify SDXL","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"stabilityai/lustify-sdxl","outputPriceLabel":"$0.01/image","shortDescription":"Lustify SDXL is a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://civitai.com/models/573152/lustify-sdxl-nsfw-checkpoint","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Lustify SDXL is a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt."},{"id":"stabilityai/lustify-v7","routeId":"lustify-v7","features":[],"provider":"venice","modalities":["image"],"moderation":"uncensored","releasedAt":"2025-01-11","displayName":"Lustify v7","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/lustify-v7","outputPriceLabel":"$0.01/image","shortDescription":"Lustify v7 (GGWP) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://civitai.com/models/573152/lustify-sdxl-nsfw-checkpoint","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Lustify v7 (GGWP) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt."},{"id":"stabilityai/lustify-v8","routeId":"lustify-v8","features":[],"provider":"venice","modalities":["image"],"moderation":"uncensored","releasedAt":"2026-03-30","displayName":"Lustify v8","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/lustify-v8","outputPriceLabel":"$0.01/image","shortDescription":"Lustify v8 (APEX) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://civitai.com/models/573152/lustify-sdxl-nsfw-checkpoint","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Lustify v8 (APEX) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt."},{"id":"stabilityai/venice-sd35","routeId":"venice-sd35","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-03-27","displayName":"Stable Diffusion 3.5 Large","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"stabilityai/venice-sd35","outputPriceLabel":"$0.01/image","shortDescription":"Stable Diffusion 3.5 Large is Stability AI's 8B-parameter Multimodal Diffusion Transformer (MMDiT) text-to-image model, with improved image quality, typography and complex prompt understanding. It…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Stable Diffusion 3.5 Large is Stability AI's 8B-parameter Multimodal Diffusion Transformer (MMDiT) text-to-image model, with improved image quality, typography and complex prompt understanding. It generates images from a text prompt."},{"id":"tencent/hunyuan-image-3.0","routeId":"hunyuan-image-v3","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-03-01","displayName":"Hunyuan Image 3.0","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"tencent/hunyuan-image-3.0","outputPriceLabel":"$0.09/image","shortDescription":"HunyuanImage 3.0 is Tencent's open-weight native multimodal image model, unifying understanding and generation in one autoregressive framework. It uses a Mixture-of-Experts design with 80B total and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/tencent/HunyuanImage-3.0-Instruct","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"HunyuanImage 3.0 is Tencent's open-weight native multimodal image model, unifying understanding and generation in one autoregressive framework. It uses a Mixture-of-Experts design with 80B total and 13B active parameters, generates images from a text prompt and can use reasoning to expand sparse prompts."},{"id":"venice/hy4-preview","routeId":"hy4-preview","features":["streaming","tool-calling","reasoning","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-08-28","displayName":"Hy4 Preview","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Venice Private routing","maxOutputTokens":64000,"primaryModality":"text","providerRouteId":"venice/hy4-preview","shortDescription":"Hy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window. It is post-trained for software…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/tencent/Hy4-preview","label":"Model source"}],"inputPriceUsdPerMillion":1.0425,"outputPriceUsdPerMillion":3.12625,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Hy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window. It is post-trained for software engineering, office and data analysis, game development, and scientific research, with strong long-horizon reasoning, tool use, and agentic performance."},{"id":"x-ai/grok-4.20","routeId":"grok-4-20","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-03-12","displayName":"Grok 4.20","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":2000000,"privacySummary":"Venice Private routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"x-ai/grok-4.20","shortDescription":"Grok 4.20 is xAI's reasoning model built for speed and agentic tool calling, with low hallucination rates and strict prompt adherence. It takes text and image input and produces text output, with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.x.ai/developers/models","label":"Model source"}],"inputPriceUsdPerMillion":1.42,"outputPriceUsdPerMillion":2.83,"cacheReadPriceUsdPerMillion":0.23,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":2.83,"outputPriceUsdPerMillion":5.67,"cacheReadPriceUsdPerMillion":0.45,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Grok 4.20 is xAI's reasoning model built for speed and agentic tool calling, with low hallucination rates and strict prompt adherence. It takes text and image input and produces text output, with a 1M-token context window, function calling and structured outputs."},{"id":"x-ai/grok-4.20-multi-agent","routeId":"grok-4-20-multi-agent","features":["streaming","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-03-12","displayName":"Grok 4.20 Multi-Agent","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":2000000,"privacySummary":"Venice Private routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"x-ai/grok-4.20-multi-agent","shortDescription":"Grok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://x.ai/api","label":"Model source"}],"inputPriceUsdPerMillion":1.42,"outputPriceUsdPerMillion":2.83,"cacheReadPriceUsdPerMillion":0.23,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":2.83,"outputPriceUsdPerMillion":5.67,"cacheReadPriceUsdPerMillion":0.45,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/grok-4-20-multi-agent","routeId":"grok-4.20-multi-agent","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.8125,"outputPriceUsdPerMillion":1.625,"cacheReadPriceUsdPerMillion":0.26,"cacheWritePriceUsdPerMillion":1.625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":2000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Grok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks."},{"id":"x-ai/grok-4.3","routeId":"grok-4-3","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-04-18","displayName":"Grok 4.3","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":32000,"primaryModality":"text","providerRouteId":"x-ai/grok-4.3","shortDescription":"Grok 4.3 is xAI's fast, reliable model with strong tool calling and instruction following, suited to agentic workflows. It takes text and image input and produces text output, with a 1M-token context…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.x.ai/developers/models","label":"Model source"}],"inputPriceUsdPerMillion":1.42,"outputPriceUsdPerMillion":2.83,"cacheReadPriceUsdPerMillion":0.23,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":2.83,"outputPriceUsdPerMillion":5.67,"cacheReadPriceUsdPerMillion":0.45,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/grok-4-3","routeId":"grok-4.3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.8125,"outputPriceUsdPerMillion":1.625,"cacheReadPriceUsdPerMillion":0.26,"cacheWritePriceUsdPerMillion":1.625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/grok-4-3","routeId":"grok-4.3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":0.875,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"xai.grok-4.3","routeId":"xai.grok-4.3","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":1.25,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}],"description":"Grok 4.3 is xAI's fast, reliable model with strong tool calling and instruction following, suited to agentic workflows. It takes text and image input and produces text output, with a 1M-token context window, function calling, structured outputs and reasoning effort from none to xhigh."},{"id":"x-ai/grok-4.5","routeId":"grok-4-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-07","displayName":"Grok 4.5","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":500000,"privacySummary":"Venice Private routing","maxOutputTokens":32000,"primaryModality":"text","providerRouteId":"x-ai/grok-4.5","shortDescription":"Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.x.ai/developers/models","label":"Model source"}],"inputPriceUsdPerMillion":2.27,"outputPriceUsdPerMillion":6.8,"cacheReadPriceUsdPerMillion":0.34,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":4.53,"outputPriceUsdPerMillion":13.6,"cacheReadPriceUsdPerMillion":0.68,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/grok-4-5","routeId":"grok-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":3.9,"cacheReadPriceUsdPerMillion":0.39,"cacheWritePriceUsdPerMillion":2.6,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":500000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/grok-4-5","routeId":"grok-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.2,"cacheReadPriceUsdPerMillion":0.21,"cacheWritePriceUsdPerMillion":1.4,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":500000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window."},{"id":"x-ai/grok-4.6","routeId":"grok-4-6","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-08-10","displayName":"Grok 4.6","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":500000,"privacySummary":"Venice Private routing","maxOutputTokens":200000,"primaryModality":"text","providerRouteId":"x-ai/grok-4.6","shortDescription":"Grok 4.6 is xAI's model for coding, agentic tasks and knowledge work, designed for long, multi-step work such as research, codebase tasks and turning an idea into a working application. It takes text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.x.ai/developers/models","label":"Model source"}],"inputPriceUsdPerMillion":2.27,"outputPriceUsdPerMillion":6.8,"cacheReadPriceUsdPerMillion":0.57,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":4.53,"outputPriceUsdPerMillion":13.6,"cacheReadPriceUsdPerMillion":1.13,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/grok-4.6","routeId":"x-ai/grok-4.6","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to xAI through a third-party routing service; not hardware-protected, and zero retention is not guaranteed end to end","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":6,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 199,999 input tokens, so AnonRouter caps this route's context there.","contextTokens":199999,"maxOutputTokens":199999,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/grok-4-6","routeId":"grok-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.7,"outputPriceUsdPerMillion":5.1,"cacheReadPriceUsdPerMillion":0.85,"cacheWritePriceUsdPerMillion":3.4,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":500000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/grok-4-6","routeId":"grok-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.2,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":1.4,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":500000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Grok 4.6 is xAI's model for coding, agentic tasks and knowledge work, designed for long, multi-step work such as research, codebase tasks and turning an idea into a working application. It takes text and image input and produces text output, with a 500K-token context window, function calling, structured outputs and low to xhigh reasoning effort."},{"id":"x-ai/grok-4.7","routeId":"grok-4-7","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-16","displayName":"Grok 4.7","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":500000,"privacySummary":"Venice Private routing","maxOutputTokens":200000,"primaryModality":"text","providerRouteId":"x-ai/grok-4.7","shortDescription":"Grok 4.7 is xAI's model for software engineering and professional knowledge work, especially long-running tasks. Compared with Grok 4.6 it uses a larger base model trained longer on harder tasks and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.x.ai/developers/models","label":"Model source"}],"inputPriceUsdPerMillion":2.27,"outputPriceUsdPerMillion":6.8,"cacheReadPriceUsdPerMillion":0.57,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":4.53,"outputPriceUsdPerMillion":13.6,"cacheReadPriceUsdPerMillion":1.13,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/grok-4.7","routeId":"x-ai/grok-4.7","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to xAI through a third-party routing service; not hardware-protected, and zero retention is not guaranteed end to end","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":6,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 199,999 input tokens, so AnonRouter caps this route's context there.","contextTokens":199999,"maxOutputTokens":199999,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/grok-4-7","routeId":"grok-4.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.313309,"outputPriceUsdPerMillion":3.939926,"cacheReadPriceUsdPerMillion":0.656654,"cacheWritePriceUsdPerMillion":2.626617,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":500000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/grok-4-7","routeId":"grok-4.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.2,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":1.4,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":500000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Grok 4.7 is xAI's model for software engineering and professional knowledge work, especially long-running tasks. Compared with Grok 4.6 it uses a larger base model trained longer on harder tasks and checks its own output more carefully, and it takes text and image input with a 500K-token context window and low to xhigh reasoning effort."},{"id":"x-ai/grok-build-0.1","routeId":"grok-build-0-1","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-05-21","displayName":"Grok Build 0.1","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"x-ai/grok-build-0.1","shortDescription":"xAI's fast coding model trained specifically for agentic coding, currently in early access.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.x.ai/developers/models/grok-build-0.1","label":"Model source"}],"inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":4,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/grok-build-0-1","routeId":"grok-build-0.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.85,"outputPriceUsdPerMillion":1.7,"cacheReadPriceUsdPerMillion":0.34,"cacheWritePriceUsdPerMillion":1.7,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/grok-build-0-1","routeId":"grok-build-0-1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.7,"outputPriceUsdPerMillion":1.4,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":0.7,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"xAI's fast coding model trained specifically for agentic coding, currently in early access."},{"id":"xiaomi/mimo-v2.6-flash","routeId":"xiaomi-mimo-v2-6-flash","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-09-28","displayName":"MiMo-V2.6-Flash","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"xiaomi/mimo-v2.6-flash","shortDescription":"MiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL","label":"Model source"}],"inputPriceUsdPerMillion":0.175,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.00375,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/xiaomimimo-mimo-v2-6-flash","routeId":"XiaomiMiMo/MiMo-V2.6-Flash","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.28,"cacheReadPriceUsdPerMillion":0.0028,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/mimo-v2-6-flash","routeId":"mimo-v2.6-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.091,"outputPriceUsdPerMillion":0.182,"cacheReadPriceUsdPerMillion":0.00182,"cacheWritePriceUsdPerMillion":0.091,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/mimo-v2-6-flash","routeId":"mimo-v2.6-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.098,"outputPriceUsdPerMillion":0.196,"cacheReadPriceUsdPerMillion":0.00196,"cacheWritePriceUsdPerMillion":0.098,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/xiaomi-mimo-v2-6-flash","routeId":"xiaomi/mimo-v2.6-flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":false,"sourceReferences":[]}],"description":"MiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window. Trained with mixed reinforcement learning across coding, general agents, visual, and cybersecurity tasks, it is built for long-horizon coding, tool use, and computer use."},{"id":"z-ai/glm-4.6","routeId":"zai-org-glm-4.6","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2024-04-01","displayName":"GLM 4.6","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"z-ai/glm-4.6","shortDescription":"GLM-4.6 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-4.6","label":"Model source"}],"inputPriceUsdPerMillion":0.43,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.08,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/zai-org-glm-4-6","routeId":"zai-org/GLM-4.6","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":202752,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-4-6","routeId":"glm-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.33,"outputPriceUsdPerMillion":1.21,"cacheReadPriceUsdPerMillion":0.0605,"cacheWritePriceUsdPerMillion":0.33,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-4-6","routeId":"glm-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.301,"outputPriceUsdPerMillion":1.225,"cacheReadPriceUsdPerMillion":0.056,"cacheWritePriceUsdPerMillion":0.301,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-4.6 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is built for agentic coding, front-end development, reasoning, writing and role-play."},{"id":"z-ai/glm-4.7","routeId":"zai-org-glm-4.7","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2025-12-24","displayName":"GLM 4.7","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Private routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"z-ai/glm-4.7","shortDescription":"GLM-4.7 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-4.7","label":"Model source"}],"inputPriceUsdPerMillion":0.55,"outputPriceUsdPerMillion":2.65,"cacheReadPriceUsdPerMillion":0.11,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/zai-org-glm-4-7","routeId":"zai-org/GLM-4.7","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.4,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.08,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":202752,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/zai-glm-4-7","routeId":"zai.glm-4.7","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.6,"outputPriceUsdPerMillion":2.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":203000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-4-7","routeId":"glm-4.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.33,"outputPriceUsdPerMillion":1.21,"cacheReadPriceUsdPerMillion":0.0605,"cacheWritePriceUsdPerMillion":0.33,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-4-7","routeId":"glm-4.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.378,"outputPriceUsdPerMillion":1.386,"cacheReadPriceUsdPerMillion":0.0693,"cacheWritePriceUsdPerMillion":0.378,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-4.7 is Z.ai's open-weight Mixture-of-Experts model with 355B total and 32B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is built for agentic coding, UI generation, tool use, reasoning and writing."},{"id":"z-ai/glm-4.7-flash-heretic","routeId":"olafangensan-glm-4.7-flash-heretic","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"uncensored","releasedAt":"2026-02-04","displayName":"GLM 4.7 Flash Heretic","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Venice Private routing","maxOutputTokens":24000,"primaryModality":"text","providerRouteId":"z-ai/glm-4.7-flash-heretic","shortDescription":"GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Olafangensan/GLM-4.7-Flash-heretic","label":"Model source"}],"inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":0.035,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-4-7-flash-heretic","routeId":"glm-4.7-flash-heretic","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.049,"outputPriceUsdPerMillion":0.28,"cacheReadPriceUsdPerMillion":0.0245,"cacheWritePriceUsdPerMillion":0.049,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed."},{"id":"z-ai/glm-5","routeId":"zai-org-glm-5","features":["streaming","tool-calling","reasoning","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-02-11","displayName":"GLM 5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Private routing","maxOutputTokens":32000,"primaryModality":"text","providerRouteId":"z-ai/glm-5","shortDescription":"GLM-5 is Z.ai's open-weight Mixture-of-Experts model with 744B total and 40B active parameters, built for complex systems engineering and long-horizon agentic tasks. It takes text input and output…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5","label":"Model source"}],"inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":3.2,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/zai-glm-5","routeId":"zai.glm-5","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":3.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5","routeId":"glm-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.55,"outputPriceUsdPerMillion":1.76,"cacheReadPriceUsdPerMillion":0.11,"cacheWritePriceUsdPerMillion":0.55,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5","routeId":"glm-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.7,"outputPriceUsdPerMillion":2.24,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":0.7,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-5 is Z.ai's open-weight Mixture-of-Experts model with 744B total and 40B active parameters, built for complex systems engineering and long-horizon agentic tasks. It takes text input and output with a 200K-token context window and up to 128K output tokens."},{"id":"deepseek/deepseek-r1-0528","routeId":"deepseek-ai/DeepSeek-R1-0528","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"DeepSeek R1 0528","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":163840,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"deepinfra/deepseek-ai-deepseek-r1-0528","shortDescription":"The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2.15,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-r1-0528","routeId":"deepseek-r1-0528","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.425,"outputPriceUsdPerMillion":1.8275,"cacheReadPriceUsdPerMillion":0.425,"cacheWritePriceUsdPerMillion":0.425,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":131072,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528."},{"id":"deepseek/deepseek-v3","routeId":"deepseek-ai/DeepSeek-V3","features":["streaming","tool-calling"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"DeepSeek V3","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":163840,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/deepseek-ai-deepseek-v3","shortDescription":"DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.32,"outputPriceUsdPerMillion":0.89,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v3","routeId":"deepseek-v3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.2295,"outputPriceUsdPerMillion":0.935,"cacheReadPriceUsdPerMillion":0.0595,"cacheWritePriceUsdPerMillion":0.2295,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":64000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2."},{"id":"deepseek/deepseek-v3.1","routeId":"deepseek-ai/DeepSeek-V3.1","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"DeepSeek V3.1","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":163840,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"deepinfra/deepseek-ai-deepseek-v3-1","shortDescription":"DeepSeek V3.1 is DeepSeek's hybrid Mixture-of-Experts model with 671B total and 37B active parameters, supporting both thinking and non-thinking modes in a single model. It has a 128K-token context…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":0.95,"cacheReadPriceUsdPerMillion":0.13,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/deepseek-v3-1","routeId":"deepseek.v3.1","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.58,"outputPriceUsdPerMillion":1.68,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v3-1","routeId":"deepseek-v3.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1625,"outputPriceUsdPerMillion":0.6175,"cacheReadPriceUsdPerMillion":0.0845,"cacheWritePriceUsdPerMillion":0.1625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v3-1","routeId":"deepseek-v3.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.175,"outputPriceUsdPerMillion":0.665,"cacheReadPriceUsdPerMillion":0.091,"cacheWritePriceUsdPerMillion":0.175,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek V3.1 is DeepSeek's hybrid Mixture-of-Experts model with 671B total and 37B active parameters, supporting both thinking and non-thinking modes in a single model. It has a 128K-token context window and improves tool calling and agent tasks over DeepSeek V3."},{"id":"deepseek/deepseek-v4-flash","routeId":"deepseek-ai/DeepSeek-V4-Flash","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"DeepSeek V4 Flash (Preview)","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter. Explicit cache-write multipliers (5m 1.25x, 1h 2x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"deepinfra/deepseek-v4-flash","shortDescription":"DeepSeek V4 Flash (Preview) is the April 2026 preview release of DeepSeek's efficiency-focused Mixture-of-Experts model, with 284B total and 13B active parameters and a 1M-token context window. It…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":0.18,"cacheReadPriceUsdPerMillion":0.018,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-flash-0423","routeId":"deepseek-ai/DeepSeek-V4-Flash-0423","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.0277,"outputPriceUsdPerMillion":1.28,"cacheReadPriceUsdPerMillion":0.0277,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/deepseek-v4-flash-0423","routeId":"DeepSeek-V4-Flash-0423","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.28,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"deepseek/deepseek-v4-flash-0423","routeId":"deepseek-v4-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route","inputPriceUsdPerMillion":0.138,"outputPriceUsdPerMillion":0.275,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-flash","routeId":"deepseek-v4-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":0.36,"cacheReadPriceUsdPerMillion":0.0018,"cacheWritePriceUsdPerMillion":0.09,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"deepseek/deepseek-v4-flash-e2ee","routeId":"e2ee-deepseek-v4-flash","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":0.182,"outputPriceUsdPerMillion":0.373,"cacheReadPriceUsdPerMillion":0.038,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":8192,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","label":"Model source"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-flash","routeId":"deepseek-v4-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.03311,"outputPriceUsdPerMillion":0.06622,"cacheReadPriceUsdPerMillion":0.00665,"cacheWritePriceUsdPerMillion":0.03311,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":false,"sourceReferences":[]}],"description":"DeepSeek V4 Flash (Preview) is the April 2026 preview release of DeepSeek's efficiency-focused Mixture-of-Experts model, with 284B total and 13B active parameters and a 1M-token context window. It offers a non-thinking mode and two thinking levels (high and max) for fast reasoning and coding workloads."},{"id":"deepseek/deepseek-v4-flash-vision-exp","routeId":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"DeepSeek V4 Flash Vision Exp","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":262144,"primaryModality":"text","providerRouteId":"deepinfra/deepseek-ai-deepseek-v4-flash-vision-exp","shortDescription":"DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and supports image input with visual grounding, tool calling, structured/JSON output, and configurable reasoning effort (low/high/max, or disabled).","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.44,"outputPriceUsdPerMillion":1.32,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-flash-vision-exp","routeId":"deepseek-v4-flash-vision-exp","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.195,"outputPriceUsdPerMillion":0.78,"cacheReadPriceUsdPerMillion":0.0039,"cacheWritePriceUsdPerMillion":0.195,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and supports image input with visual grounding, tool calling, structured/JSON output, and configurable reasoning effort (low/high/max, or disabled)."},{"id":"deepseek/deepseek-v4-pro","routeId":"deepseek-ai/DeepSeek-V4-Pro","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"DeepSeek V4 Pro","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/deepseek-v4-pro","shortDescription":"DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":2.6,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-pro","routeId":"deepseek-ai/DeepSeek-V4-Pro","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.45,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":0.09,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"deepseek/deepseek-v4-pro","routeId":"deepseek-v4-pro","privacyLevel":"anonymous","privacySummary":"Anonymous route","inputPriceUsdPerMillion":1.65,"outputPriceUsdPerMillion":3.301,"cacheReadPriceUsdPerMillion":0.33,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-pro","routeId":"deepseek-v4-pro","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.561,"outputPriceUsdPerMillion":1.683,"cacheReadPriceUsdPerMillion":0.0187,"cacheWritePriceUsdPerMillion":0.561,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-pro","routeId":"deepseek-v4-pro","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.61278,"outputPriceUsdPerMillion":1.22556,"cacheReadPriceUsdPerMillion":0.05103,"cacheWritePriceUsdPerMillion":0.61278,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":false,"sourceReferences":[]}],"description":"DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks."},{"id":"google/gemma-3-12b-it","routeId":"google/gemma-3-12b-it","features":["streaming","tool-calling","vision"],"provider":"deepinfra","modalities":["text","image"],"moderation":"unknown","displayName":"Gemma 3 12B Instruct","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/google-gemma-3-12b-it","shortDescription":"Gemma 3 12B Instruct is the 12-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output,…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":0.15,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/google-gemma-3-12b-it","routeId":"google.gemma-3-12b-it","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":0.29,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemma-3-12b-it","routeId":"gemma-3-12b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0325,"outputPriceUsdPerMillion":0.0975,"cacheReadPriceUsdPerMillion":0.0325,"cacheWritePriceUsdPerMillion":0.0325,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8192,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemma-3-12b-it","routeId":"gemma-3-12b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.035,"outputPriceUsdPerMillion":0.105,"cacheReadPriceUsdPerMillion":0.00525,"cacheWritePriceUsdPerMillion":0.035,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemma 3 12B Instruct is the 12-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding."},{"id":"google/gemma-3-4b-it","routeId":"google/gemma-3-4b-it","features":["streaming","tool-calling","vision"],"provider":"deepinfra","modalities":["text","image"],"moderation":"unknown","displayName":"Gemma 3 4B Instruct","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/google-gemma-3-4b-it","shortDescription":"Gemma 3 4B Instruct is the 4-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output,…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":0.1,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/google-gemma-3-4b-it","routeId":"google.gemma-3-4b-it","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.04,"outputPriceUsdPerMillion":0.08,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemma-3-4b-it","routeId":"gemma-3-4b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0325,"outputPriceUsdPerMillion":0.065,"cacheReadPriceUsdPerMillion":0.0325,"cacheWritePriceUsdPerMillion":0.0325,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemma-3-4b-it","routeId":"gemma-3-4b-it","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.035,"outputPriceUsdPerMillion":0.07,"cacheReadPriceUsdPerMillion":0.00525,"cacheWritePriceUsdPerMillion":0.035,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"google.gemma-3-4b-it","routeId":"google.gemma-3-4b-it","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":0.04,"outputPriceUsdPerMillion":0.08,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}],"description":"Gemma 3 4B Instruct is the 4-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding."},{"id":"google/gemma-4-31b-it-turbo","routeId":"google/gemma-4-31B-it-turbo","features":["streaming","tool-calling","vision","video-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","displayName":"Gemma 4 31B Instruct Turbo","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/google-gemma-4-31b-it-turbo","shortDescription":"Gemma 4 31B Instruct Turbo is a faster serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.09,"outputPriceUsdPerMillion":0.34,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Gemma 4 31B Instruct Turbo is a faster serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling."},{"id":"ibm-granite/granite-4.2-8b","routeId":"ibm-granite/granite-4.2-8b","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"Granite 4.2 8B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/ibm-granite-granite-4-2-8b","shortDescription":"Granite 4.2 8B is IBM's 8B-parameter dense reasoning model in the open-weight Granite 4.2 family, for reasoning, code generation, tool calling and agentic workflows. It takes text input and produces…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.25,"cacheReadPriceUsdPerMillion":0.015,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Granite 4.2 8B is IBM's 8B-parameter dense reasoning model in the open-weight Granite 4.2 family, for reasoning, code generation, tool calling and agentic workflows. It takes text input and produces text output with a 128K-token native context, and offers full thinking, non-thinking and low-effort thinking modes per request."},{"id":"inclusionai/ling-3.0-flash","routeId":"inclusionAI/Ling-3.0-flash","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"Ling 3.0 Flash","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"deepinfra/inclusionai-ling-3-0-flash","shortDescription":"Ling 3.0 Flash is inclusionAI's hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 124B total and 5.1B active parameters built for efficient agentic workflows such as coding and deep…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.18,"cacheReadPriceUsdPerMillion":0.012,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/ling-3-0-flash","routeId":"ling-3.0-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.039,"outputPriceUsdPerMillion":0.117,"cacheReadPriceUsdPerMillion":0.0078,"cacheWritePriceUsdPerMillion":0.039,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32000,"availability":"available","callable":false,"sourceReferences":[]}],"description":"Ling 3.0 Flash is inclusionAI's hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 124B total and 5.1B active parameters built for efficient agentic workflows such as coding and deep research. It takes text input and output with a 256K-token context window, and its thinking mode can be turned off per request."},{"id":"inclusionai/ling-3.0-flash-vl","routeId":"inclusionAI/Ling-3.0-flash-VL","features":["streaming","tool-calling","vision","video-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","displayName":"Ling 3.0 Flash VL","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"deepinfra/inclusionai-ling-3-0-flash-vl","shortDescription":"Ling 3.0 Flash VL is inclusionAI's multimodal version of Ling 3.0 Flash, a Mixture-of-Experts model with 124B total and 5.5B active parameters. It takes text, image and video input and produces text…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.18,"cacheReadPriceUsdPerMillion":0.012,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/ling-3-0-flash-vl","routeId":"ling-3.0-flash-vl","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.051,"outputPriceUsdPerMillion":0.153,"cacheReadPriceUsdPerMillion":0.051,"cacheWritePriceUsdPerMillion":0.051,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Ling 3.0 Flash VL is inclusionAI's multimodal version of Ling 3.0 Flash, a Mixture-of-Experts model with 124B total and 5.5B active parameters. It takes text, image and video input and produces text with a context of up to 256K tokens, and is built for document and chart understanding, GUI agents and long-video question answering."},{"id":"inclusionai/ling-3.1-flash","routeId":"inclusionAI/Ling-3.1-flash","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","displayName":"Ling 3.1 Flash","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/inclusionai-ling-3-1-flash","shortDescription":"Ling 3.1 Flash is inclusionAI's native hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 560B total and 25B active parameters that builds on Ling 3.0 Flash. It takes text input and…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":0.9,"cacheReadPriceUsdPerMillion":0.06,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/ling-3-1-flash","routeId":"ling-3.1-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.04875,"outputPriceUsdPerMillion":0.14625,"cacheReadPriceUsdPerMillion":0.04875,"cacheWritePriceUsdPerMillion":0.04875,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/ling-3-1-flash","routeId":"ling-3.1-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0525,"outputPriceUsdPerMillion":0.1575,"cacheReadPriceUsdPerMillion":0.0105,"cacheWritePriceUsdPerMillion":0.0525,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Ling 3.1 Flash is inclusionAI's native hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 560B total and 25B active parameters that builds on Ling 3.0 Flash. It takes text input and output with a 1M-token context window, is designed for complex real-world tasks, and lets thinking be turned on or off."},{"id":"meta/llama-3.1-8b-instruct-turbo","routeId":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","features":["streaming","tool-calling"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"Meta Llama 3.1 8B Instruct Turbo","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/meta-llama-meta-llama-3-1-8b-instruct-turbo","shortDescription":"Meta Llama 3.1 8B Instruct Turbo is a faster serving variant of Llama 3.1 8B Instruct, Meta's small multilingual instruction-tuned text model. The model has a 128K-token context window, officially…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.02,"outputPriceUsdPerMillion":0.04,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Meta Llama 3.1 8B Instruct Turbo is a faster serving variant of Llama 3.1 8B Instruct, Meta's small multilingual instruction-tuned text model. The model has a 128K-token context window, officially supports eight languages and supports tool use."},{"id":"meta/llama-3.3-70b-instruct-turbo","routeId":"meta-llama/Llama-3.3-70B-Instruct-Turbo","features":["streaming","tool-calling"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"Llama 3.3 70B Instruct Turbo","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/meta-llama-llama-3-3-70b-instruct-turbo","shortDescription":"Llama 3.3 70B Instruct is Meta's 70B-parameter multilingual instruction-tuned model, tuned for assistant-style dialogue in English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. It…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.32,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Llama 3.3 70B Instruct is Meta's 70B-parameter multilingual instruction-tuned model, tuned for assistant-style dialogue in English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. It takes text input and produces text and code with a 128K-token context window. This Turbo variant is a faster serving variant of Llama 3.3 70B Instruct."},{"id":"meta/llama-4-scout-17b-16e-instruct","routeId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","features":["streaming","tool-calling","vision"],"provider":"deepinfra","modalities":["text","image"],"moderation":"unknown","displayName":"Llama 4 Scout 17B 16E Instruct","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":327680,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/meta-llama-llama-4-scout-17b-16e-instruct","shortDescription":"Llama 4 Scout is Meta's natively multimodal Mixture-of-Experts model with 17B active parameters, 16 experts and 109B total parameters. It takes text and image input and produces text and code with a…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Llama 4 Scout is Meta's natively multimodal Mixture-of-Experts model with 17B active parameters, 16 experts and 109B total parameters. It takes text and image input and produces text and code with a context window of up to 10M tokens, and is built for assistant chat and visual reasoning such as captioning and image question answering."},{"id":"meta/llama-guard-4-12b","routeId":"meta-llama/Llama-Guard-4-12B","features":["streaming","vision"],"provider":"deepinfra","modalities":["text","image"],"moderation":"unknown","displayName":"Llama Guard 4 12B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":163840,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/meta-llama-llama-guard-4-12b","shortDescription":"Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (resp…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.18,"outputPriceUsdPerMillion":0.18,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It itself acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated."},{"id":"meta/muse-glimmer-30b","routeId":"meta-models/Muse-Glimmer-30B","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Muse Glimmer 30B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/meta-models-muse-glimmer-30b","shortDescription":"Muse Glimmer 30B is an open-weight multimodal model from Meta Superintelligence Lab, distilled from Muse Spark. It is a dense 30B transformer that takes text and image input and produces text with a…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.04,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/muse-glimmer-30b","routeId":"muse-glimmer-30b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.2275,"outputPriceUsdPerMillion":0.975,"cacheReadPriceUsdPerMillion":0.026,"cacheWritePriceUsdPerMillion":0.2275,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":131072,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/muse-glimmer-30b","routeId":"muse-glimmer-30b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":131072,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Muse Glimmer 30B is an open-weight multimodal model from Meta Superintelligence Lab, distilled from Muse Spark. It is a dense 30B transformer that takes text and image input and produces text with a context window of at least 131K tokens, built for local and coding agents, tool calling and multimodal reasoning on a single consumer GPU or Mac."},{"id":"microsoft/phi-4","routeId":"microsoft/phi-4","features":["streaming"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"Phi-4","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":16384,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/microsoft-phi-4","shortDescription":"Phi-4 is Microsoft's 14B-parameter dense decoder-only language model, trained on a blend of synthetic data, filtered public web content and academic books and Q&A data with a focus on reasoning. It…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Phi-4 is Microsoft's 14B-parameter dense decoder-only language model, trained on a blend of synthetic data, filtered public web content and academic books and Q&A data with a focus on reasoning. It takes text input and produces text output with a 16K-token context window and is intended primarily for English."},{"id":"mistralai/mistral-nemo-instruct-2407","routeId":"mistralai/Mistral-Nemo-Instruct-2407","features":["streaming"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","displayName":"Mistral Nemo Instruct 2407","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/mistralai-mistral-nemo-instruct-2407","shortDescription":"12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.029,"outputPriceUsdPerMillion":0.03,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size."},{"id":"mistralai/mistral-small-24b-instruct-2501","routeId":"mistralai/Mistral-Small-24B-Instruct-2501","features":["streaming"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"Mistral Small 24B Instruct 2501","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32768,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/mistralai-mistral-small-24b-instruct-2501","shortDescription":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operatin…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":0.08,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware."},{"id":"nvidia/nemotron-content-safety-3.5","routeId":"nvidia/Nemotron-Content-Safety-3.5","features":["streaming","vision"],"provider":"deepinfra","modalities":["text","image"],"moderation":"unknown","displayName":"Nemotron Content Safety 3.5","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/nvidia-nemotron-content-safety-3-5","shortDescription":"Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-train models for safer behavior.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-train models for safer behavior."},{"id":"nvidia/nvidia-nemotron-3-super-120b-a12b","routeId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","features":["streaming","tool-calling","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"NVIDIA Nemotron 3 Super 120B A12B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/nvidia-nemotron-3-super-120b-a12b","shortDescription":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.085,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/nvidia-nemotron-super-3-120b","routeId":"nvidia.nemotron-super-3-120b","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.65,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/nvidia-nemotron-3-super-120b","routeId":"nvidia-nemotron-3-super-120b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":1.68,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following."},{"id":"nvidia/nvidia-nemotron-3.5-lightning","routeId":"nvidia/NVIDIA-Nemotron-3.5-Lightning","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","displayName":"NVIDIA Nemotron 3.5 Lightning","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/nvidia-nvidia-nemotron-3-5-lightning","shortDescription":"NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.16,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/nvidia-nemotron-3-5-lightning-30b-a3b","routeId":"nvidia-nemotron-3-5-lightning-30b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.049,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":0.049,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[]}],"description":"NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context."},{"id":"openai/gpt-oss-20b","routeId":"openai/gpt-oss-20b","features":["streaming","tool-calling","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","displayName":"OpenAI GPT OSS 20B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/gpt-oss-20b","shortDescription":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling,…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.03,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/openai-gpt-oss-20b","routeId":"openai.gpt-oss-20b","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-oss-20b","routeId":"gpt-oss-20b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0455,"outputPriceUsdPerMillion":0.195,"cacheReadPriceUsdPerMillion":0.0455,"cacheWritePriceUsdPerMillion":0.0455,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/openai-gpt-oss-20b","routeId":"openai-gpt-oss-20b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0126,"outputPriceUsdPerMillion":0.063,"cacheReadPriceUsdPerMillion":0.0063,"cacheWritePriceUsdPerMillion":0.0126,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"openai.gpt-oss-20b","routeId":"openai.gpt-oss-20b","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}],"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs."},{"id":"qwen/qwen-3.5-35b-a3b","routeId":"Qwen/Qwen3.5-35B-A3B","features":["streaming","tool-calling","vision","video-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","displayName":"Qwen3.5 35B A3B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":81920,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen3-5-35b-a3b","shortDescription":"Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":1,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-5-35b-a3b","routeId":"qwen3.5-35b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1625,"outputPriceUsdPerMillion":1.3,"cacheReadPriceUsdPerMillion":0.1625,"cacheWritePriceUsdPerMillion":0.1625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-5-35b-a3b","routeId":"qwen3-5-35b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.7,"cacheReadPriceUsdPerMillion":0.035,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"qwen/qwen-3.5-35b-a3b","routeId":"qwen3-5-35b-a3b","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":1,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":256000,"maxOutputTokens":16384,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","label":"Model source"}]}],"description":"Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost."},{"id":"qwen/qwen-3.5-9b","routeId":"Qwen/Qwen3.5-9B","features":["streaming","tool-calling","vision","video-input","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","displayName":"Qwen3.5 9B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen3-5-9b","shortDescription":"Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.15,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks."},{"id":"qwen/qwen2.5-72b-instruct","routeId":"Qwen/Qwen2.5-72B-Instruct","features":["streaming","tool-calling"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"Qwen2.5 72B Instruct","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32768,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen2-5-72b-instruct","shortDescription":"Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.36,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages."},{"id":"qwen/qwen3-14b","routeId":"Qwen/Qwen3-14B","features":["streaming","tool-calling","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"Qwen3 14B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":40960,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen3-14b","shortDescription":"Qwen3 14B is a dense 14.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.12,"outputPriceUsdPerMillion":0.24,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-14b","routeId":"qwen3-14b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.068,"outputPriceUsdPerMillion":0.17,"cacheReadPriceUsdPerMillion":0.068,"cacheWritePriceUsdPerMillion":0.068,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":40960,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen3 14B is a dense 14.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN)."},{"id":"qwen/qwen3-30b-a3b","routeId":"Qwen/Qwen3-30B-A3B","features":["streaming","tool-calling","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"Qwen3 30B A3B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":40960,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen3-30b-a3b","shortDescription":"Qwen3 30B A3B is a Mixture-of-Experts model in the Qwen3 family with 30.5B total and 3.3B active parameters from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.12,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-30b-a3b","routeId":"qwen3-30b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.078,"outputPriceUsdPerMillion":0.325,"cacheReadPriceUsdPerMillion":0.078,"cacheWritePriceUsdPerMillion":0.078,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-30b-a3b","routeId":"qwen3-30b-a3b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.084,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.0126,"cacheWritePriceUsdPerMillion":0.084,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen3 30B A3B is a Mixture-of-Experts model in the Qwen3 family with 30.5B total and 3.3B active parameters from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN)."},{"id":"qwen/qwen3-32b","routeId":"Qwen/Qwen3-32B","features":["streaming","tool-calling","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"Qwen3 32B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":40960,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen3-32b","shortDescription":"Qwen3 32B is a dense 32.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.08,"outputPriceUsdPerMillion":0.28,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"amazon-bedrock","providerName":"Amazon Bedrock","providerRouteId":"amazon-bedrock/qwen-qwen3-32b","routeId":"qwen.qwen3-32b","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":32000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-32b","routeId":"qwen3-32b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.104,"outputPriceUsdPerMillion":0.416,"cacheReadPriceUsdPerMillion":0.104,"cacheWritePriceUsdPerMillion":0.104,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":32000,"maxOutputTokens":8192,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-32b","routeId":"qwen3-32b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.056,"outputPriceUsdPerMillion":0.196,"cacheReadPriceUsdPerMillion":0.0084,"cacheWritePriceUsdPerMillion":0.056,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":32000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen3 32B is a dense 32.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN)."},{"id":"qwen/qwen3-vl-30b-a3b","routeId":"Qwen/Qwen3-VL-30B-A3B-Instruct","features":["streaming","tool-calling","vision"],"provider":"deepinfra","modalities":["text","image"],"moderation":"unknown","displayName":"Qwen3 VL 30B A3B Instruct","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen3-vl-30b-a3b-instruct","shortDescription":"Qwen3 VL 30B A3B Instruct is a Mixture-of-Experts vision-language model from Alibaba's Qwen team. It takes text, image and video input and produces text with a native 256K-token context window, and…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"qwen/qwen3-vl-30b-a3b-e2ee","routeId":"e2ee-qwen3-vl-30b-a3b-p","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":0.9,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":128000,"maxOutputTokens":4096,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct","label":"Model source"}]}],"description":"Qwen3 VL 30B A3B Instruct is a Mixture-of-Experts vision-language model from Alibaba's Qwen team. It takes text, image and video input and produces text with a native 256K-token context window, and handles visual agent tasks, visual coding, 2D and 3D grounding, long video understanding and OCR in 32 languages."},{"id":"qwen/qwen3.5-27b","routeId":"Qwen/Qwen3.5-27B","features":["streaming","tool-calling","vision","video-input","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","displayName":"Qwen3.5 27B","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":81920,"primaryModality":"text","providerRouteId":"deepinfra/qwen-qwen3-5-27b","shortDescription":"Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.26,"outputPriceUsdPerMillion":2.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-5-27b","routeId":"qwen3.5-27b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.255,"outputPriceUsdPerMillion":2.04,"cacheReadPriceUsdPerMillion":0.255,"cacheWritePriceUsdPerMillion":0.255,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance."},{"id":"sao10k/l3-8b-lunaris-v1-turbo","routeId":"Sao10K/L3-8B-Lunaris-v1-Turbo","features":["streaming"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"L3 8B Lunaris v1 Turbo","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":8192,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"deepinfra/sao10k-l3-8b-lunaris-v1-turbo","shortDescription":"L3 8B Lunaris v1 Turbo is a faster serving variant of Lunaris v1, Sao10K's 8B generalist and roleplay model. Lunaris is a merge of four Llama 3 8B fine-tunes on Meta Llama 3 8B Instruct, aimed at…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.04,"outputPriceUsdPerMillion":0.05,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"L3 8B Lunaris v1 Turbo is a faster serving variant of Lunaris v1, Sao10K's 8B generalist and roleplay model. Lunaris is a merge of four Llama 3 8B fine-tunes on Meta Llama 3 8B Instruct, aimed at better creativity and logic than Sao10K's Stheno v3.2."},{"id":"sao10k/l3.1-70b-euryale-v2.2","routeId":"Sao10K/L3.1-70B-Euryale-v2.2","features":["streaming"],"provider":"deepinfra","modalities":["text"],"moderation":"unknown","displayName":"L3.1 70B Euryale v2.2","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/sao10k-l3-1-70b-euryale-v2-2","shortDescription":"L3.1 70B Euryale v2.2 is Sao10K's fine-tune of Meta Llama 3.1 70B Instruct for creative writing and roleplay. Compared with v2.1 it was trained on more roleplay and creative writing data, with added…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.85,"outputPriceUsdPerMillion":0.85,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"L3.1 70B Euryale v2.2 is Sao10K's fine-tune of Meta Llama 3.1 70B Instruct for creative writing and roleplay. Compared with v2.1 it was trained on more roleplay and creative writing data, with added data for system-prompt adherence and reasoning."},{"id":"stepfun-ai/step-5-preview","routeId":"stepfun-ai/Step-5-Preview","features":["streaming","tool-calling","vision","video-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","displayName":"Step 5 Preview","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/stepfun-ai-step-5-preview","shortDescription":"Step 5 Preview is StepFun's flagship model for agentic work. It is a sparse Mixture-of-Experts model with 600B total parameters and 27B active per token, a 1M-token context window, and text and image input. It delivers frontier-level performance in software engineering, long-horizon agentic execution with repeated tool calls, and professional knowledge work, with particular strength in finance.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":2.7,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/step-5-preview","routeId":"step-5-preview","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.85,"outputPriceUsdPerMillion":2.295,"cacheReadPriceUsdPerMillion":0.0425,"cacheWritePriceUsdPerMillion":0.85,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Step 5 Preview is StepFun's flagship model for agentic work. It is a sparse Mixture-of-Experts model with 600B total parameters and 27B active per token, a 1M-token context window, and text and image input. It delivers frontier-level performance in software engineering, long-horizon agentic execution with repeated tool calls, and professional knowledge work, with particular strength in finance."},{"id":"tencent/hy4-preview","routeId":"tencent/Hy4-preview","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","displayName":"Hy4 Preview","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/tencent-hy4-preview","shortDescription":"Hy4 Preview is a 770B-parameter Mixture-of-Experts model from the Tencent Hy Team, with 49B parameters active per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention with…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.834,"outputPriceUsdPerMillion":2.501,"cacheReadPriceUsdPerMillion":0.042,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Hy4 Preview is a 770B-parameter Mixture-of-Experts model from the Tencent Hy Team, with 49B parameters active per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention with IndexCache and is post-trained for software engineering, office and data analysis, game development and scientific research, with adjustable reasoning effort."},{"id":"thinking-machines/inkling-small","routeId":"thinkingmachines/Inkling-Small","features":["streaming","tool-calling","vision","audio-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","audio"],"moderation":"unknown","displayName":"Inkling Small","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":524288,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":262144,"primaryModality":"text","providerRouteId":"deepinfra/thinkingmachines-inkling-small","shortDescription":"Inkling Small is a smaller model in Thinking Machines Lab's Inkling family, a Mixture-of-Experts with 276B total and 12B active parameters. Like Inkling, it accepts text, image and audio input and…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.45,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/inkling-small","routeId":"inkling-small","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.231,"outputPriceUsdPerMillion":0.924,"cacheReadPriceUsdPerMillion":0.0462,"cacheWritePriceUsdPerMillion":0.231,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Inkling Small is a smaller model in Thinking Machines Lab's Inkling family, a Mixture-of-Experts with 276B total and 12B active parameters. Like Inkling, it accepts text, image and audio input and generates text, with a context of up to 1M tokens and variable thinking effort."},{"id":"xiaomi/mimo-v2.6-pro","routeId":"XiaomiMiMo/MiMo-V2.6-Pro","features":["streaming","tool-calling","vision","audio-input","video-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","audio","video"],"moderation":"unknown","statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","displayName":"MiMo V2.6 Pro","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/xiaomimimo-mimo-v2-6-pro","shortDescription":"MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning and groupwise agentic grading, it is built for demanding agentic work including long-horizon coding, multi-tool agen…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.43,"outputPriceUsdPerMillion":0.87,"cacheReadPriceUsdPerMillion":0.0036,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/mimo-v2-6-pro","routeId":"mimo-v2.6-pro","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.302452,"outputPriceUsdPerMillion":0.604903,"cacheReadPriceUsdPerMillion":0.002503,"cacheWritePriceUsdPerMillion":0.302452,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/mimo-v2-6-pro","routeId":"mimo-v2.6-pro","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.3045,"outputPriceUsdPerMillion":0.609,"cacheReadPriceUsdPerMillion":0.00252,"cacheWritePriceUsdPerMillion":0.3045,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning and groupwise agentic grading, it is built for demanding agentic work including long-horizon coding, multi-tool agents and cybersecurity tasks."},{"id":"z-ai/glm-5.3-flash","routeId":"zai-org/GLM-5.3-Flash","features":["streaming","tool-calling","vision","video-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","displayName":"GLM 5.3 Flash","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/zai-org-glm-5-3-flash","shortDescription":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/zai-org-glm-5-3-flash","routeId":"zai-org/GLM-5.3-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/z-ai-glm-5-3-flash","routeId":"z-ai/glm-5.3-flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.075,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.0075,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/zai-org-glm-5-3-flash","routeId":"zai-org/GLM-5.3-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.11,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/glm-5-3-flash","routeId":"GLM-5.3-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3-flash","routeId":"z-ai-glm-5-3-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5.3-Flash","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5-3-flash","routeId":"glm-5.3-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":0.012,"cacheWritePriceUsdPerMillion":0.06,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5-3-flash","routeId":"glm-5.3-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3-flash-e2ee","routeId":"e2ee-glm-5-3-flash","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":0.16,"outputPriceUsdPerMillion":0.54,"cacheReadPriceUsdPerMillion":0.038,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/zai-org/GLM-5.3-Flash","label":"Model source"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/glm-5.3-flash","routeId":"z-ai/glm-5.3-flash","privacyLevel":"e2ee","privacySummary":"Direct TLS-in-TEE enclave (Intel TDX + NVIDIA CC)","inputPriceUsdPerMillion":0.08,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.012,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":1048576,"availability":"available","callable":false,"sourceReferences":[]}],"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead."},{"id":"z-ai/glm-5.3-uncensored","routeId":"abliterated-model-large-v2","features":["streaming","tool-calling","reasoning","json-schema","prompt-caching"],"provider":"abliteration","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GLM 5.3 Uncensored","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","abliteration.ai publishes that prompts and completions are processed in memory, are never stored by default and are never used for training. AnonRouter has confirmed this no-logging practice with abliteration.ai.","This route does not run in a trusted execution environment and is not end-to-end encrypted: abliteration.ai can read prompts and outputs in the clear while it processes them."],"providerName":"abliteration.ai","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Private route. abliteration.ai processes prompts and outputs in memory and, by default, does not store them or use them for training. It can read content while serving the request.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"abliteration/abliterated-model-large-v2","shortDescription":"GLM 5.3 Uncensored is an uncensored variant of Z.ai's GLM-5.3, with refusal behavior removed through abliteration and further fine-tuning. It takes text input and output with a 1M-token context…","sourceReferences":[],"inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":5,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"venice/abliterated-large-v2","routeId":"abliteration-abliterated-model-large-v2","privacyLevel":"anonymous","privacySummary":"Venice Anonymous routing","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":5,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.abliteration.ai/models","label":"Model source"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/abliteration-abliterated-model-large-v2","routeId":"abliteration-abliterated-model-large-v2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.1,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":0.21,"cacheWritePriceUsdPerMillion":2.1,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM 5.3 Uncensored is an uncensored variant of Z.ai's GLM-5.3, with refusal behavior removed through abliteration and further fine-tuning. It takes text input and output with a 1M-token context window, always reasons at low, high or max depth, and is aimed at red teaming, security research and agent testing."},{"id":"minimax/minimax-m2","routeId":"minimax.minimax-m2","features":["streaming","tool-calling"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"MiniMax M2","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":196000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/minimax-minimax-m2","shortDescription":"MiniMax-M2 is MiniMax's open-weight Mixture-of-Experts language model built for coding and agentic workflows, with 230 billion total parameters and 10 billion active per token. It takes text input…","sourceReferences":[],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/minimax-m2","routeId":"minimax-m2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.195,"outputPriceUsdPerMillion":0.78,"cacheReadPriceUsdPerMillion":0.0195,"cacheWritePriceUsdPerMillion":0.24375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":204800,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m2","routeId":"minimax-m2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1785,"outputPriceUsdPerMillion":0.714,"cacheReadPriceUsdPerMillion":0.02681,"cacheWritePriceUsdPerMillion":0.1785,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":204800,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiniMax-M2 is MiniMax's open-weight Mixture-of-Experts language model built for coding and agentic workflows, with 230 billion total parameters and 10 billion active per token. It takes text input and produces text output, with a context window of 204,800 tokens. It is designed for multi-file edits, code-run-fix loops and test-validated repairs, and for long tool-calling sequences across shell, browser, retrieval and code-execution tools."},{"id":"minimax/minimax-m2.1","routeId":"minimax.minimax-m2.1","features":["streaming","tool-calling"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"MiniMax M2.1","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":196000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/minimax-minimax-m2-1","shortDescription":"MiniMax-M2.1 is MiniMax's open-weight Mixture-of-Experts language model, an update to MiniMax-M2 focused on real-world coding and agentic tasks. It takes text input and produces text output. MiniMax…","sourceReferences":[],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/minimax-m2-1","routeId":"minimax-m2.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.195,"outputPriceUsdPerMillion":0.78,"cacheReadPriceUsdPerMillion":0.0195,"cacheWritePriceUsdPerMillion":0.24375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m2-1","routeId":"minimax-m2.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiniMax-M2.1 is MiniMax's open-weight Mixture-of-Experts language model, an update to MiniMax-M2 focused on real-world coding and agentic tasks. It takes text input and produces text output. MiniMax highlights multi-language programming across Rust, Java, Go, C++, Kotlin, Objective-C, TypeScript and JavaScript, native Android and iOS development, web and app development, tool use and long-horizon planning, and multi-step office workflows."},{"id":"mistralai/devstral-2-123b","routeId":"mistral.devstral-2-123b","features":["streaming","tool-calling","code-optimized"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"Devstral 2 123B","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":32000,"primaryModality":"text","providerRouteId":"amazon-bedrock/mistral-devstral-2-123b","shortDescription":"Devstral 2 is Mistral AI's 123B dense transformer for agentic software engineering, released with open weights under a modified MIT license. It takes text input and produces text output, with a 256K…","sourceReferences":[],"inputPriceUsdPerMillion":0.4,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/devstral-2-123b","routeId":"devstral-2-123b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.28,"outputPriceUsdPerMillion":1.4,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":0.28,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Devstral 2 is Mistral AI's 123B dense transformer for agentic software engineering, released with open weights under a modified MIT license. It takes text input and produces text output, with a 256K context window. It is built to power coding agents that explore codebases, call tools and make coordinated edits across multiple files, for work such as bug fixing and modernizing legacy systems."},{"id":"mistralai/magistral-small-2509","routeId":"mistral.magistral-small-2509","features":["streaming","tool-calling","vision","reasoning"],"provider":"amazon-bedrock","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"Magistral Small 2509","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":40000,"primaryModality":"text","providerRouteId":"amazon-bedrock/mistral-magistral-small-2509","shortDescription":"Magistral Small 1.2 (2509) is Mistral AI's 24B open-weight reasoning model, fine-tuned from Mistral Small 3.2. It takes text and image input and produces text output, generating a reasoning trace…","sourceReferences":[],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/magistral-small-2509","routeId":"magistral-small-2509","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.05,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.35,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":40000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Magistral Small 1.2 (2509) is Mistral AI's 24B open-weight reasoning model, fine-tuned from Mistral Small 3.2. It takes text and image input and produces text output, generating a reasoning trace before its final answer, with a 128K context window and support for 24 languages. It is built for multi-step reasoning tasks and is compact enough for local deployment once quantized."},{"id":"mistralai/ministral-3-14b-instruct","routeId":"mistral.ministral-3-14b-instruct","features":["streaming","tool-calling","vision"],"provider":"amazon-bedrock","modalities":["text","image"],"moderation":"unknown","displayName":"Ministral 3 14B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/mistral-ministral-3-14b-instruct","shortDescription":"Ministral 3 14B Instruct is the largest instruction-tuned model in Mistral AI's Ministral 3 family of dense open-weight models, combining a 13.5B language model with a 0.4B vision encoder. It takes…","sourceReferences":[],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/ministral-3-14b-instruct","routeId":"ministral-3-14b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.14,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":0.14,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Ministral 3 14B Instruct is the largest instruction-tuned model in Mistral AI's Ministral 3 family of dense open-weight models, combining a 13.5B language model with a 0.4B vision encoder. It takes text and image input and produces text output, with native function calling and JSON output, and multilingual support. It is built for private chat and assistant deployments, local agentic workflows and fine-tuning."},{"id":"mistralai/ministral-3-3b-instruct","routeId":"mistral.ministral-3-3b-instruct","features":["streaming","tool-calling","vision"],"provider":"amazon-bedrock","modalities":["text","image"],"moderation":"unknown","displayName":"Ministral 3 3B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/mistral-ministral-3-3b-instruct","shortDescription":"Ministral 3 3B Instruct is the instruction-tuned 3B model in Mistral AI's Ministral 3 family of small dense open-weight models, combining a 3.4B language model with a 0.4B vision encoder. It takes…","sourceReferences":[],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.1,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/ministral-3-3b-instruct","routeId":"ministral-3-3b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.07,"cacheReadPriceUsdPerMillion":0.007,"cacheWritePriceUsdPerMillion":0.07,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Ministral 3 3B Instruct is the instruction-tuned 3B model in Mistral AI's Ministral 3 family of small dense open-weight models, combining a 3.4B language model with a 0.4B vision encoder. It takes text and image input and produces text output, with native function calling and JSON output, and support for 11 languages. It is built for edge and local deployment, and for tasks such as image captioning, classification, translation and data extraction."},{"id":"mistralai/ministral-3-8b-instruct","routeId":"mistral.ministral-3-8b-instruct","features":["streaming","tool-calling","vision"],"provider":"amazon-bedrock","modalities":["text","image"],"moderation":"unknown","displayName":"Ministral 3 8B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/mistral-ministral-3-8b-instruct","shortDescription":"Ministral 3 8B Instruct is the instruction-tuned 8B model in Mistral AI's Ministral 3 family of small dense open-weight models, combining an 8.4B language model with a 0.4B vision encoder. It takes…","sourceReferences":[],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.15,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/ministral-3-8b-instruct","routeId":"ministral-3-8b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.105,"cacheReadPriceUsdPerMillion":0.0105,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Ministral 3 8B Instruct is the instruction-tuned 8B model in Mistral AI's Ministral 3 family of small dense open-weight models, combining an 8.4B language model with a 0.4B vision encoder. It takes text and image input and produces text output, with native function calling and JSON output, and multilingual support. It is built for local assistants, chat in constrained environments, image and document understanding, and agentic use cases."},{"id":"mistralai/mistral-large-3-675b-instruct","routeId":"mistral.mistral-large-3-675b-instruct","features":["streaming","tool-calling","vision"],"provider":"amazon-bedrock","modalities":["text","image"],"moderation":"unknown","displayName":"Mistral Large 3 675B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":32000,"primaryModality":"text","providerRouteId":"amazon-bedrock/mistral-mistral-large-3-675b-instruct","shortDescription":"Mistral Large 3 is Mistral AI's open-weight multimodal granular Mixture-of-Experts model, with 675B total and 41B active parameters. It takes text and image input with a 256K-token context window and…","sourceReferences":[],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/mistral-large-3","routeId":"mistral-large-3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.05,"cacheReadPriceUsdPerMillion":0.035,"cacheWritePriceUsdPerMillion":0.35,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"mistral.mistral-large-3-675b-instruct","routeId":"mistral.mistral-large-3-675b-instruct","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}],"description":"Mistral Large 3 is Mistral AI's open-weight multimodal granular Mixture-of-Experts model, with 675B total and 41B active parameters. It takes text and image input with a 256K-token context window and is built for agentic work, tool use, retrieval-augmented systems, long documents and coding across dozens of languages."},{"id":"mistralai/voxtral-mini-3b-2507","routeId":"mistral.voxtral-mini-3b-2507","features":["streaming","tool-calling"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"Voxtral Mini 3B","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32000,"privacySummary":"Private route","maxOutputTokens":32000,"primaryModality":"text","providerRouteId":"amazon-bedrock/mistral-voxtral-mini-3b-2507","shortDescription":"Voxtral Mini 3B is a text model.","sourceReferences":[],"inputPriceUsdPerMillion":0.04,"outputPriceUsdPerMillion":0.04,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-26","callable":true,"operationalAvailability":"available"},{"id":"moonshotai/kimi-k2-thinking","routeId":"moonshotai.kimi-k2-thinking","features":["streaming","tool-calling","reasoning"],"provider":"amazon-bedrock","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"Kimi K2 Thinking","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":16000,"primaryModality":"text","providerRouteId":"amazon-bedrock/moonshotai-kimi-k2-thinking","shortDescription":"Kimi K2 Thinking is Moonshot AI's open-weight thinking model, a Mixture-of-Experts model with about 1 trillion total parameters and 32 billion active per token. It takes text input and produces text…","sourceReferences":[],"inputPriceUsdPerMillion":0.6,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/kimi-k2-thinking","routeId":"kimi-k2-thinking","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.3055,"outputPriceUsdPerMillion":1.3,"cacheReadPriceUsdPerMillion":0.09165,"cacheWritePriceUsdPerMillion":0.3055,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":98304,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/kimi-k2-thinking","routeId":"kimi-k2-thinking","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.42,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.42,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Kimi K2 Thinking is Moonshot AI's open-weight thinking model, a Mixture-of-Experts model with about 1 trillion total parameters and 32 billion active per token. It takes text input and produces text output, with a 256K-token context window. It is built to interleave step-by-step reasoning with function calls, and is designed to stay goal-directed across 200 to 300 sequential tool calls for research, coding and writing tasks."},{"id":"nvidia/nvidia-nemotron-nano-12b-v2-vl","routeId":"nvidia.nemotron-nano-12b-v2","features":["streaming","tool-calling","vision"],"provider":"amazon-bedrock","modalities":["text","image"],"moderation":"unknown","displayName":"NVIDIA Nemotron Nano 12B v2 VL","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/nvidia-nemotron-nano-12b-v2","shortDescription":"NVIDIA Nemotron Nano 12B v2 VL is an open 12.6B-parameter vision-language model from NVIDIA. It pairs a CRadioV2-H vision encoder with the Nemotron Nano 12B v2 language model. It takes English text,…","sourceReferences":[],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/nvidia-nemotron-nano-12b-v2","routeId":"nvidia-nemotron-nano-12b-v2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.42,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.14,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"NVIDIA Nemotron Nano 12B v2 VL is an open 12.6B-parameter vision-language model from NVIDIA. It pairs a CRadioV2-H vision encoder with the Nemotron Nano 12B v2 language model. It takes English text, up to four images or a video as input and returns text, with 128K tokens of combined input and output context. It is built for document intelligence on invoices, receipts and manuals, visual question answering, summarization, multi-image reasoning and video understanding."},{"id":"nvidia/nvidia-nemotron-nano-9b-v2","routeId":"nvidia.nemotron-nano-9b-v2","features":["streaming","tool-calling"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"NVIDIA Nemotron Nano 9B v2","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/nvidia-nemotron-nano-9b-v2","shortDescription":"NVIDIA Nemotron Nano 9B v2 is an open 9B-parameter reasoning and chat model from NVIDIA, built on a hybrid Mamba-2 and Transformer architecture with only four attention layers. It was produced by…","sourceReferences":[],"inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.23,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/nvidia-nemotron-nano-9b-v2","routeId":"nvidia-nemotron-nano-9b-v2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.042,"outputPriceUsdPerMillion":0.161,"cacheReadPriceUsdPerMillion":0.0063,"cacheWritePriceUsdPerMillion":0.042,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":8000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"NVIDIA Nemotron Nano 9B v2 is an open 9B-parameter reasoning and chat model from NVIDIA, built on a hybrid Mamba-2 and Transformer architecture with only four attention layers. It was produced by pruning and aligning the 12B Nemotron Nano v2 base model. It handles text input and output with up to 128K tokens of context and supports tool calling. Reasoning is on by default and can be switched off, and an optional thinking budget caps reasoning tokens."},{"id":"openai/gpt-oss-safeguard-120b","routeId":"openai.gpt-oss-safeguard-120b","features":["streaming","tool-calling","reasoning"],"provider":"amazon-bedrock","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GPT OSS Safeguard 120B","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":16000,"primaryModality":"text","providerRouteId":"amazon-bedrock/openai-gpt-oss-safeguard-120b","shortDescription":"gpt-oss-safeguard-120b is an open-weight safety reasoning model from OpenAI, fine-tuned from gpt-oss-120b, with 117B total parameters and 5.1B active. It classifies content against a safety policy…","sourceReferences":[],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/openai-gpt-oss-safeguard-120b","routeId":"openai-gpt-oss-safeguard-120b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.42,"cacheReadPriceUsdPerMillion":0.01575,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"gpt-oss-safeguard-120b is an open-weight safety reasoning model from OpenAI, fine-tuned from gpt-oss-120b, with 117B total parameters and 5.1B active. It classifies content against a safety policy that the developer writes and supplies at inference time, and it produces a reviewable chain of thought for each decision. It is built for trust and safety tasks such as input and output filtering and content labeling, supports low, medium and high reasoning effort, and is released under Apache 2.0."},{"id":"openai/gpt-oss-safeguard-20b","routeId":"openai.gpt-oss-safeguard-20b","features":["streaming","tool-calling","reasoning"],"provider":"amazon-bedrock","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GPT OSS Safeguard 20B","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Private route","maxOutputTokens":16000,"primaryModality":"text","providerRouteId":"amazon-bedrock/openai-gpt-oss-safeguard-20b","shortDescription":"gpt-oss-safeguard-20b is the smaller open-weight safety reasoning model from OpenAI, fine-tuned from gpt-oss-20b, with about 21B total parameters and 3.6B active. It reads a developer-written safety…","sourceReferences":[],"inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/openai-gpt-oss-safeguard-20b","routeId":"openai-gpt-oss-safeguard-20b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0525,"outputPriceUsdPerMillion":0.21,"cacheReadPriceUsdPerMillion":0.02625,"cacheWritePriceUsdPerMillion":0.0525,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"gpt-oss-safeguard-20b is the smaller open-weight safety reasoning model from OpenAI, fine-tuned from gpt-oss-20b, with about 21B total parameters and 3.6B active. It reads a developer-written safety policy at inference time and classifies content against it with a visible chain of thought, for lower-latency trust and safety tasks such as input and output filtering and content labeling. It supports low, medium and high reasoning effort and is released under Apache 2.0."},{"id":"qwen/qwen3-235b-a22b-instruct-2507","routeId":"qwen.qwen3-235b-a22b-2507","features":["streaming","tool-calling"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"Qwen3 235B A22B Instruct 2507","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/qwen-qwen3-235b-a22b-2507","shortDescription":"Qwen3 235B A22B Instruct 2507 is a text model.","sourceReferences":[],"inputPriceUsdPerMillion":0.22,"outputPriceUsdPerMillion":0.88,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-26","callable":true,"operationalAvailability":"available"},{"id":"qwen/qwen3-coder-30b-a3b-instruct","routeId":"qwen.qwen3-coder-30b-a3b-instruct","features":["streaming","tool-calling","code-optimized"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"Qwen3 Coder 30B A3B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":16000,"primaryModality":"text","providerRouteId":"amazon-bedrock/qwen-qwen3-coder-30b-a3b-instruct","shortDescription":"Qwen3 Coder 30B A3B Instruct is an open-weight Mixture-of-Experts coding model from the Qwen team. It has 30.5B total parameters, with 3.3B active per token (8 of 128 experts), and a native…","sourceReferences":[],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-coder-30b-a3b-instruct","routeId":"qwen3-coder-30b-a3b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.2925,"outputPriceUsdPerMillion":1.4625,"cacheReadPriceUsdPerMillion":0.78,"cacheWritePriceUsdPerMillion":0.78,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":8192,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-coder-30b-a3b-instruct","routeId":"qwen3-coder-30b-a3b-instruct","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.049,"outputPriceUsdPerMillion":0.196,"cacheReadPriceUsdPerMillion":0.00735,"cacheWritePriceUsdPerMillion":0.049,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen3 Coder 30B A3B Instruct is an open-weight Mixture-of-Experts coding model from the Qwen team. It has 30.5B total parameters, with 3.3B active per token (8 of 128 experts), and a native 262,144-token context window. It is a text-only, non-thinking model built for agentic coding, agentic browser use and repository-scale code understanding, with a dedicated function-calling format, and is released under Apache 2.0."},{"id":"qwen/qwen3-coder-480b-a35b-instruct","routeId":"qwen.qwen3-coder-480b-a35b-instruct","features":["streaming","tool-calling","code-optimized"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"Qwen3 Coder 480B A35B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":16000,"primaryModality":"text","providerRouteId":"amazon-bedrock/qwen-qwen3-coder-480b-a35b-instruct","shortDescription":"Qwen3 Coder 480B A35B Instruct is a text model.","sourceReferences":[],"inputPriceUsdPerMillion":0.45,"outputPriceUsdPerMillion":1.8,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-26","callable":true,"operationalAvailability":"available"},{"id":"qwen/qwen3-coder-next","routeId":"qwen.qwen3-coder-next","features":["streaming","tool-calling","code-optimized"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"Qwen3 Coder Next","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":16000,"primaryModality":"text","providerRouteId":"amazon-bedrock/qwen-qwen3-coder-next","shortDescription":"Qwen3 Coder Next is an open-weight coding model from Alibaba's Qwen team, built for coding agents and local development on the Qwen3-Next hybrid-attention Mixture-of-Experts architecture with 80B…","sourceReferences":[],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-coder-next","routeId":"qwen3-coder-next","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.195,"outputPriceUsdPerMillion":0.975,"cacheReadPriceUsdPerMillion":0.52,"cacheWritePriceUsdPerMillion":0.52,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-coder-next","routeId":"qwen3-coder-next","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.084,"outputPriceUsdPerMillion":0.56,"cacheReadPriceUsdPerMillion":0.049,"cacheWritePriceUsdPerMillion":0.084,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"aws-bedrock","providerName":"AWS Bedrock","providerRouteId":"qwen.qwen3-coder-next","routeId":"qwen.qwen3-coder-next","privacyLevel":"private","privacySummary":"Bedrock Mantle zero-retention route","inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Bedrock Mantle pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html","label":"Amazon Bedrock Mantle models"},{"url":"https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html","label":"Amazon Bedrock data protection"}]}],"description":"Qwen3 Coder Next is an open-weight coding model from Alibaba's Qwen team, built for coding agents and local development on the Qwen3-Next hybrid-attention Mixture-of-Experts architecture with 80B total and 3B active parameters. It has a native 262K-token context window and is aimed at agentic coding, tool calling and recovery from execution failures."},{"id":"qwen/qwen3-next-80b-a3b-instruct","routeId":"qwen.qwen3-next-80b-a3b-instruct","features":["streaming","tool-calling"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"Qwen3 Next 80B A3B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Private route","maxOutputTokens":8000,"primaryModality":"text","providerRouteId":"amazon-bedrock/qwen-qwen3-next-80b-a3b-instruct","shortDescription":"Qwen3 Next 80B A3B Instruct is a text model.","sourceReferences":[],"inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-26","callable":true,"operationalAvailability":"available"},{"id":"writer/palmyra-vision-7b","routeId":"writer.palmyra-vision-7b","features":["streaming","tool-calling","vision"],"provider":"amazon-bedrock","modalities":["text","image"],"moderation":"unknown","displayName":"Palmyra Vision 7B","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":4000,"privacySummary":"Private route","maxOutputTokens":4000,"primaryModality":"text","providerRouteId":"amazon-bedrock/writer-palmyra-vision-7b","shortDescription":"Palmyra Vision 7B is a text model.","sourceReferences":[],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-26","callable":true,"operationalAvailability":"available"},{"id":"z-ai/glm-4.7-flash","routeId":"zai.glm-4.7-flash","features":["streaming","tool-calling"],"provider":"amazon-bedrock","modalities":["text"],"moderation":"unknown","displayName":"GLM 4.7 Flash","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Amazon Bedrock","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":203000,"privacySummary":"Private route","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"amazon-bedrock/zai-glm-4-7-flash","shortDescription":"GLM 4.7 Flash is a text model.","sourceReferences":[],"inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-4-7-flash","routeId":"glm-4.7-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0455,"outputPriceUsdPerMillion":0.26,"cacheReadPriceUsdPerMillion":0.0455,"cacheWritePriceUsdPerMillion":0.0455,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":131000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-4-7-flash","routeId":"glm-4.7-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.04235,"outputPriceUsdPerMillion":0.28,"cacheReadPriceUsdPerMillion":0.00637,"cacheWritePriceUsdPerMillion":0.04235,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[]}]},{"id":"deepseek/deepseek-v4.1-flash-fast","routeId":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"baseten","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"DeepSeek V4.1 Flash Fast","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Baseten","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Private route","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"baseten/deepseek-ai-deepseek-v4-1-flash-fast","shortDescription":"DeepSeek V4.1 Flash Fast is a lower-latency serving tier of DeepSeek V4.1 Flash, the same model served for faster output. It is a Mixture-of-Experts model with 552B backbone parameters (8B active on…","sourceReferences":[],"inputPriceUsdPerMillion":0.6,"outputPriceUsdPerMillion":2.4,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"DeepSeek V4.1 Flash Fast is a lower-latency serving tier of DeepSeek V4.1 Flash, the same model served for faster output. It is a Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window, with strong reasoning, coding, and agentic performance."},{"id":"z-ai/glm-5.2-fast","routeId":"zai-org/GLM-5.2-Fast","features":["streaming","tool-calling","reasoning","json-schema","prompt-caching"],"provider":"baseten","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GLM 5.2 Fast","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Baseten","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Private route","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"baseten/zai-org-glm-5-2-fast","shortDescription":"GLM-5.2 Fast is a lower-latency serving tier of GLM-5.2, Z.ai's model for long-horizon tasks, served for faster output. It takes text input and output with a 1M-token context window, and offers…","sourceReferences":[],"inputPriceUsdPerMillion":2.1,"outputPriceUsdPerMillion":6.6,"cacheReadPriceUsdPerMillion":0.21,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GLM-5.2 Fast is a lower-latency serving tier of GLM-5.2, Z.ai's model for long-horizon tasks, served for faster output. It takes text input and output with a 1M-token context window, and offers stronger coding than GLM-5.1 with multiple thinking effort levels to balance performance and latency."},{"id":"z-ai/glm-5.3-fast","routeId":"zai-org/GLM-5.3-Fast","features":["streaming","tool-calling","reasoning","json-schema","prompt-caching"],"provider":"baseten","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GLM 5.3 Fast","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Baseten","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Private route","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"baseten/zai-org-glm-5-3-fast","shortDescription":"GLM-5.3 Fast is a lower-latency serving tier of GLM-5.3, Z.ai's reasoning model for complex software engineering and long-horizon agent tasks. It shares GLM-5.2's base model with improved…","sourceReferences":[],"inputPriceUsdPerMillion":2.1,"outputPriceUsdPerMillion":6.6,"cacheReadPriceUsdPerMillion":0.21,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GLM-5.3 Fast is a lower-latency serving tier of GLM-5.3, Z.ai's reasoning model for complex software engineering and long-horizon agent tasks. It shares GLM-5.2's base model with improved post-training for coding, and supports text input and output with a 1M-token context window."},{"id":"google/gemma-4-12b-it","routeId":"google/gemma-4-12B-it","features":["streaming","prompt-caching"],"provider":"sail","modalities":["text"],"moderation":"unknown","displayName":"Gemma 4 12B Instruct","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Sail","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":15872,"privacySummary":"Private route","maxOutputTokens":15872,"primaryModality":"text","providerRouteId":"sail/google-gemma-4-12b-it","shortDescription":"Gemma 4 12B Instruct is the instruction-tuned 12B model in Google DeepMind's Gemma 4 family of open models. It is a dense 11.95B-parameter multimodal model with configurable thinking modes, native…","sourceReferences":[],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.15,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-15","callable":true,"operationalAvailability":"available","description":"Gemma 4 12B Instruct is the instruction-tuned 12B model in Google DeepMind's Gemma 4 family of open models. It is a dense 11.95B-parameter multimodal model with configurable thinking modes, native function calling, and support for over 140 languages."},{"id":"google/gemma-4-31b-it-nvfp4","routeId":"nvidia/Gemma-4-31B-IT-NVFP4","features":["streaming","prompt-caching"],"provider":"sail","modalities":["text"],"moderation":"unknown","displayName":"Gemma 4 31B Instruct NVFP4","pricingNote":"Owner-reviewed price table in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":[],"providerName":"Sail","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":260834,"privacySummary":"Private route","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"sail/nvidia-gemma-4-31b-it-nvfp4","shortDescription":"Gemma 4 31B Instruct NVFP4 is a 4-bit NVFP4 quantization of Gemma 4 31B IT, Google DeepMind's 30.7B-parameter dense open model, with both weights and activations quantized. It supports text and image…","sourceReferences":[],"inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-15","callable":true,"operationalAvailability":"available","description":"Gemma 4 31B Instruct NVFP4 is a 4-bit NVFP4 quantization of Gemma 4 31B IT, Google DeepMind's 30.7B-parameter dense open model, with both weights and activations quantized. It supports text and image input, configurable thinking, and function calling."},{"id":"aion-labs/aion-3.0","routeId":"aion-labs-aion-3-0","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-07-08","displayName":"Aion 3.0","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"aion-labs/aion-3.0","shortDescription":"Aion 3.0 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. It takes text input and output with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.aionlabs.ai/docs/models/","label":"Model source"}],"inputPriceUsdPerMillion":3.75,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.9375,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/aion-3-0","routeId":"aion-3.0","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.65,"outputPriceUsdPerMillion":3.3,"cacheReadPriceUsdPerMillion":0.4125,"cacheWritePriceUsdPerMillion":1.65,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/aion-labs-aion-3-0","routeId":"aion-labs-aion-3-0","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.1,"outputPriceUsdPerMillion":4.2,"cacheReadPriceUsdPerMillion":0.525,"cacheWritePriceUsdPerMillion":2.1,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Aion 3.0 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. It takes text input and output with a 128K-token context window and up to 32K output tokens, and supports reasoning."},{"id":"aion-labs/aion-3.0-mini","routeId":"aion-labs-aion-3-0-mini","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-07-08","displayName":"Aion 3.0 Mini","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"aion-labs/aion-3.0-mini","shortDescription":"Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.aionlabs.ai/docs/models/","label":"Model source"}],"inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.225,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/aion-3-0-mini","routeId":"aion-3.0-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.421182,"outputPriceUsdPerMillion":0.842365,"cacheReadPriceUsdPerMillion":0.108304,"cacheWritePriceUsdPerMillion":0.421182,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/aion-labs-aion-3-0-mini","routeId":"aion-labs-aion-3-0-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.49,"outputPriceUsdPerMillion":0.98,"cacheReadPriceUsdPerMillion":0.126,"cacheWritePriceUsdPerMillion":0.49,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction."},{"id":"aion-labs/aion-3.5","routeId":"aion-labs-aion-3-5","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-09-23","displayName":"Aion 3.5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"aion-labs/aion-3.5","shortDescription":"Aion 3.5 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. Compared with Aion 3.0 it doubles the…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.aionlabs.ai/docs/models/","label":"Model source"}],"inputPriceUsdPerMillion":3.75,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.9375,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Aion 3.5 is a roleplay and storytelling system from AionLabs, built on the GLM model family, in which several specialized models contribute to each response. Compared with Aion 3.0 it doubles the context window to 256K tokens, with up to 32K output tokens."},{"id":"aion-labs/aion-3.5-mini","routeId":"aion-labs-aion-3-5-mini","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-09-23","displayName":"Aion 3.5 Mini","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"aion-labs/aion-3.5-mini","shortDescription":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.aionlabs.ai/docs/models/","label":"Model source"}],"inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.225,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction."},{"id":"alibaba/wan-2.7-pro-t2i","routeId":"wan-2-7-pro-text-to-image","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-04-01","displayName":"Wan 2.7 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"alibaba/wan-2.7-pro-t2i","outputPriceLabel":"$0.09/image","shortDescription":"Wan 2.7 Pro is the high-fidelity tier of Wan 2.7, Alibaba's unified image generation and editing model family, with a focus on text rendering, brand colors and consistent multi-image output. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Wan 2.7 Pro is the high-fidelity tier of Wan 2.7, Alibaba's unified image generation and editing model family, with a focus on text rendering, brand colors and consistent multi-image output. This variant generates images from a text prompt at up to 4K resolution."},{"id":"alibaba/wan-2.7-t2i","routeId":"wan-2-7-text-to-image","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-04-01","displayName":"Wan 2.7","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"alibaba/wan-2.7-t2i","outputPriceLabel":"$0.04/image","shortDescription":"Wan 2.7 is Alibaba's unified image generation and editing model family. This standard tier has the same features as Wan 2.7 Pro, including text rendering and brand colors, with faster generation and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Wan 2.7 is Alibaba's unified image generation and editing model family. This standard tier has the same features as Wan 2.7 Pro, including text rendering and brand colors, with faster generation and a maximum resolution of 2048x2048. This variant generates images from a text prompt."},{"id":"anthropic/claude-fable-5","routeId":"claude-fable-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-06-10","displayName":"Claude Fable 5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-fable-5","shortDescription":"Claude Fable 5 is Anthropic's Mythos-class model released for general use, built for demanding reasoning and long-horizon agentic work. It takes text and image input and produces text output, with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":1,"cacheWritePriceUsdPerMillion":12.5,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-fable-5","routeId":"anthropic/claude-fable-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-fable-5","routeId":"anthropic/claude-fable-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-fable-5","routeId":"claude-fable-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":6.5,"outputPriceUsdPerMillion":32.5,"cacheReadPriceUsdPerMillion":0.65,"cacheWritePriceUsdPerMillion":8.125,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-fable-5","routeId":"claude-fable-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":7,"outputPriceUsdPerMillion":35,"cacheReadPriceUsdPerMillion":0.7,"cacheWritePriceUsdPerMillion":8.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Fable 5 is Anthropic's Mythos-class model released for general use, built for demanding reasoning and long-horizon agentic work. It takes text and image input and produces text output, with a 1M-token context window, up to 128K output tokens and always-on adaptive thinking."},{"id":"anthropic/claude-fable-5.1","routeId":"claude-fable-5-1","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-08-29","displayName":"Claude Fable 5.1","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-fable-5.1","shortDescription":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":0.25,"cacheWritePriceUsdPerMillion":12.5,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-fable-5.1","routeId":"anthropic/claude-fable-5-1","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-fable-5-1","routeId":"claude-fable-5.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":8.471471,"outputPriceUsdPerMillion":42.357357,"cacheReadPriceUsdPerMillion":0.211787,"cacheWritePriceUsdPerMillion":10.589339,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-fable-5-1","routeId":"claude-fable-5.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":7,"outputPriceUsdPerMillion":35,"cacheReadPriceUsdPerMillion":0.175,"cacheWritePriceUsdPerMillion":8.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries."},{"id":"anthropic/claude-haiku-5.5","routeId":"claude-haiku-5-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-07","displayName":"Claude Haiku 5.5","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 100,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-haiku-5.5","shortDescription":"Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.01,"cacheWritePriceUsdPerMillion":0.125,"priceTiers":[{"aboveInputTokens":100000,"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":0.625}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-haiku-5-5","routeId":"claude-haiku-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.065,"outputPriceUsdPerMillion":0.325,"cacheReadPriceUsdPerMillion":0.0325,"cacheWritePriceUsdPerMillion":0.40625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":100000,"maxOutputTokens":100000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-haiku-5-5","routeId":"claude-haiku-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.007,"cacheWritePriceUsdPerMillion":0.0875,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":100000,"maxOutputTokens":100000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding."},{"id":"anthropic/claude-opus-4.5","routeId":"claude-opus-4-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2025-12-06","displayName":"Claude Opus 4.5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-4.5","shortDescription":"Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":6.25,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-4-5","routeId":"claude-opus-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":4.25,"outputPriceUsdPerMillion":21.25,"cacheReadPriceUsdPerMillion":0.425,"cacheWritePriceUsdPerMillion":5.3125,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-4-5","routeId":"claude-opus-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.5,"outputPriceUsdPerMillion":17.5,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":4.375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection."},{"id":"anthropic/claude-opus-4.6","routeId":"claude-opus-4-6","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-02-05","displayName":"Claude Opus 4.6","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-4.6","shortDescription":"Claude Opus 4.6 is Anthropic's Opus model for demanding coding, long-running agentic work and knowledge work such as research, financial analysis and building documents. It takes text and image input…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":6.25,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-opus-4.6","routeId":"anthropic/claude-opus-4-6","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":200000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-4-6","routeId":"claude-opus-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.45,"outputPriceUsdPerMillion":17.25,"cacheReadPriceUsdPerMillion":0.345,"cacheWritePriceUsdPerMillion":4.3125,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-4-6","routeId":"claude-opus-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.5,"outputPriceUsdPerMillion":17.5,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":4.375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Opus 4.6 is Anthropic's Opus model for demanding coding, long-running agentic work and knowledge work such as research, financial analysis and building documents. It takes text and image input and produces text output, with a 1M-token context window, up to 128K output tokens and adaptive thinking with effort controls."},{"id":"anthropic/claude-opus-4.7","routeId":"claude-opus-4-7","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-04-16","displayName":"Claude Opus 4.7","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-4.7","shortDescription":"Claude Opus 4.7 is Anthropic's Opus model for advanced software engineering, especially complex, long-running coding tasks. It builds on Opus 4.6 with more precise instruction following, verification…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":6.25,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-opus-4-7","routeId":"anthropic/claude-opus-4-7","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-opus-4.7","routeId":"anthropic/claude-opus-4-7","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-4-7","routeId":"claude-opus-4.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.32248,"outputPriceUsdPerMillion":16.612399,"cacheReadPriceUsdPerMillion":0.332248,"cacheWritePriceUsdPerMillion":4.1531,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-4-7","routeId":"claude-opus-4.7","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.5,"outputPriceUsdPerMillion":17.5,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":4.375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Opus 4.7 is Anthropic's Opus model for advanced software engineering, especially complex, long-running coding tasks. It builds on Opus 4.6 with more precise instruction following, verification of its own outputs and higher-resolution vision, and offers a 1M-token context window, up to 128K output tokens and adaptive thinking."},{"id":"anthropic/claude-opus-4.8","routeId":"claude-opus-4-8","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-05-28","displayName":"Claude Opus 4.8","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-4.8","shortDescription":"Claude Opus 4.8 is Anthropic's Opus model for dependable, long-running agentic work and coding. It builds on Opus 4.7 with sharper judgment and more candid flagging of doubts about its own output,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":6.25,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-opus-4-8","routeId":"anthropic/claude-opus-4-8","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-4-8","routeId":"claude-opus-4.8","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.25,"outputPriceUsdPerMillion":16.25,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":4.0625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-4-8","routeId":"claude-opus-4.8","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.5,"outputPriceUsdPerMillion":17.5,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":4.375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-opus-4.8","routeId":"anthropic/claude-opus-4-8","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":null,"availability":"needs-verification","callable":false,"statusNote":"This relay route is not in the reviewed manifest and cannot be enabled.","sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]}],"description":"Claude Opus 4.8 is Anthropic's Opus model for dependable, long-running agentic work and coding. It builds on Opus 4.7 with sharper judgment and more candid flagging of doubts about its own output, and takes text and image input with a 1M-token context window, up to 128K output tokens and adaptive thinking."},{"id":"anthropic/claude-opus-4.8-fast","routeId":"claude-opus-4-8-fast","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-05-28","displayName":"Claude Opus 4.8 Fast","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-4.8-fast","shortDescription":"Claude Opus 4.8 Fast is Claude Opus 4.8 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged:…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":1,"cacheWritePriceUsdPerMillion":12.5,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-4-8-fast","routeId":"claude-opus-4.8-fast","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":8.5,"outputPriceUsdPerMillion":42.5,"cacheReadPriceUsdPerMillion":0.85,"cacheWritePriceUsdPerMillion":10.625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-4-8-fast","routeId":"claude-opus-4-8-fast","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":7,"outputPriceUsdPerMillion":35,"cacheReadPriceUsdPerMillion":0.7,"cacheWritePriceUsdPerMillion":8.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Opus 4.8 Fast is Claude Opus 4.8 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged: text and image input, text output, a 1M-token context window and adaptive thinking for agentic work and complex coding."},{"id":"anthropic/claude-opus-5","routeId":"claude-opus-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-23","displayName":"Claude Opus 5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-5","shortDescription":"Claude Opus 5 is Anthropic's Opus model for daily professional work, with gains over Opus 4.8 in software engineering, knowledge work and scientific research. It checks its own work and iterates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":6.25,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-opus-5","routeId":"anthropic/claude-opus-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-opus-5","routeId":"anthropic/claude-opus-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-5","routeId":"claude-opus-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.903035,"outputPriceUsdPerMillion":19.515176,"cacheReadPriceUsdPerMillion":0.390304,"cacheWritePriceUsdPerMillion":4.878794,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-5","routeId":"claude-opus-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.5,"outputPriceUsdPerMillion":17.5,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":4.375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Opus 5 is Anthropic's Opus model for daily professional work, with gains over Opus 4.8 in software engineering, knowledge work and scientific research. It checks its own work and iterates until a task succeeds, and takes text and image input with a 1M-token context window, up to 128K output tokens and adaptive thinking."},{"id":"anthropic/claude-opus-5-fast","routeId":"claude-opus-5-fast","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-23","displayName":"Claude Opus 5 Fast","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-5-fast","shortDescription":"Claude Opus 5 Fast is Claude Opus 5 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged: text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":1,"cacheWritePriceUsdPerMillion":12.5,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-5-fast","routeId":"claude-opus-5-fast","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":8.058292,"outputPriceUsdPerMillion":40.29146,"cacheReadPriceUsdPerMillion":0.805829,"cacheWritePriceUsdPerMillion":10.072865,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-5-fast","routeId":"claude-opus-5-fast","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":7,"outputPriceUsdPerMillion":35,"cacheReadPriceUsdPerMillion":0.7,"cacheWritePriceUsdPerMillion":8.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Opus 5 Fast is Claude Opus 5 run in Anthropic's fast mode, the same model weights with a faster inference configuration that raises output speed by up to 2.5x. Capabilities are unchanged: text and image input, text output, a 1M-token context window and adaptive thinking for coding, knowledge work and research."},{"id":"anthropic/claude-opus-5.5","routeId":"claude-opus-5-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-18","displayName":"Claude Opus 5.5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-5.5","shortDescription":"Claude Opus 5.5 is Anthropic's Opus model for long-running agentic coding and knowledge work. Compared with Opus 5 it uses fewer tokens per task and writes more clearly, and it takes text and image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":5,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-opus-5-5","routeId":"anthropic/claude-opus-5-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-opus-5.5","routeId":"anthropic/claude-opus-5-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-opus-5-5","routeId":"claude-opus-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.395632,"outputPriceUsdPerMillion":16.97816,"cacheReadPriceUsdPerMillion":0.169782,"cacheWritePriceUsdPerMillion":4.24454,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-opus-5-5","routeId":"claude-opus-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.8,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":3.5,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Opus 5.5 is Anthropic's Opus model for long-running agentic coding and knowledge work. Compared with Opus 5 it uses fewer tokens per task and writes more clearly, and it takes text and image input with a 1M-token context window, up to 128K output tokens and always-on adaptive thinking."},{"id":"anthropic/claude-opus-5.5-fast","routeId":"claude-opus-5-5-fast","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-26","displayName":"Claude Opus 5.5 Fast","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-opus-5.5-fast","shortDescription":"Claude Opus 5.5 Fast serves the same Opus 5.5 model with faster output generation, a 1M token context window, up to 128K output tokens, adaptive thinking, vision, and tool calling.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":8,"outputPriceUsdPerMillion":40,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":10,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Claude Opus 5.5 Fast serves the same Opus 5.5 model with faster output generation, a 1M token context window, up to 128K output tokens, adaptive thinking, vision, and tool calling."},{"id":"anthropic/claude-sonnet-4.5","routeId":"claude-sonnet-4-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2025-01-15","statusNote":"Venice removes this route on 2026-10-30.","displayName":"Claude Sonnet 4.5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"deprecated","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":198000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":64000,"primaryModality":"text","providerRouteId":"anthropic/claude-sonnet-4.5","shortDescription":"Claude Sonnet 4.5 is Anthropic's balanced model offering strong performance on coding, reasoning, and general tasks with good speed and cost efficiency.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":3.75,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-sonnet-4.5","routeId":"anthropic/claude-sonnet-4-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price. The model's developer bills prompts above 200,000 tokens at a higher rate, so AnonRouter caps this route's context there.","contextTokens":200000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-sonnet-4-5","routeId":"claude-sonnet-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.485433,"outputPriceUsdPerMillion":12.427167,"cacheReadPriceUsdPerMillion":0.248543,"cacheWritePriceUsdPerMillion":3.106792,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-sonnet-4-5","routeId":"claude-sonnet-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.1,"outputPriceUsdPerMillion":10.5,"cacheReadPriceUsdPerMillion":0.21,"cacheWritePriceUsdPerMillion":2.625,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":198000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Sonnet 4.5 is Anthropic's balanced model offering strong performance on coding, reasoning, and general tasks with good speed and cost efficiency."},{"id":"anthropic/claude-sonnet-4.6","routeId":"claude-sonnet-4-6","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-02-17","displayName":"Claude Sonnet 4.6","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":64000,"primaryModality":"text","providerRouteId":"anthropic/claude-sonnet-4.6","shortDescription":"Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":3.75,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-sonnet-4-6","routeId":"anthropic/claude-sonnet-4-6","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-sonnet-4.6","routeId":"anthropic/claude-sonnet-4-6","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-sonnet-4-6","routeId":"claude-sonnet-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.95,"outputPriceUsdPerMillion":9.75,"cacheReadPriceUsdPerMillion":0.195,"cacheWritePriceUsdPerMillion":2.4375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-sonnet-4-6","routeId":"claude-sonnet-4.6","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.1,"outputPriceUsdPerMillion":10.5,"cacheReadPriceUsdPerMillion":0.21,"cacheWritePriceUsdPerMillion":2.625,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens."},{"id":"anthropic/claude-sonnet-5","routeId":"claude-sonnet-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-06-29","displayName":"Claude Sonnet 5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":64000,"primaryModality":"text","providerRouteId":"anthropic/claude-sonnet-5","shortDescription":"Claude Sonnet 5 is Anthropic's Sonnet model built for agentic work: planning, using tools such as browsers and terminals, coding, reasoning and knowledge work. It takes text and image input and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":2.5,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-sonnet-5","routeId":"anthropic/claude-sonnet-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-sonnet-5","routeId":"anthropic/claude-sonnet-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-sonnet-5","routeId":"claude-sonnet-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":6.5,"cacheReadPriceUsdPerMillion":0.13,"cacheWritePriceUsdPerMillion":1.625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-sonnet-5","routeId":"claude-sonnet-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":7,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":1.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Sonnet 5 is Anthropic's Sonnet model built for agentic work: planning, using tools such as browsers and terminals, coding, reasoning and knowledge work. It takes text and image input and produces text, with a 1M-token context window, up to 128K output tokens and adaptive thinking, and improves on Sonnet 4.6."},{"id":"anthropic/claude-sonnet-5.5","routeId":"claude-sonnet-5-5","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-26","displayName":"Claude Sonnet 5.5","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"anthropic/claude-sonnet-5.5","shortDescription":"Claude Sonnet 5.5 is Anthropic's Sonnet model, balancing speed and intelligence for well-scoped everyday work such as building features, fixing bugs and creating documents, slides and spreadsheets.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":2.5,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/anthropic-claude-sonnet-5-5","routeId":"anthropic/claude-sonnet-5-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-sonnet-5.5","routeId":"anthropic/claude-sonnet-5-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"needs-verification","callable":true,"statusNote":"The provider changed this route's identity, limits, capabilities or pricing after it was reviewed; re-audit is required.","sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-sonnet-5-5","routeId":"claude-sonnet-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.685349,"outputPriceUsdPerMillion":8.426743,"cacheReadPriceUsdPerMillion":0.168535,"cacheWritePriceUsdPerMillion":2.106686,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-sonnet-5-5","routeId":"claude-sonnet-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":7,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":1.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Sonnet 5.5 is Anthropic's Sonnet model, balancing speed and intelligence for well-scoped everyday work such as building features, fixing bugs and creating documents, slides and spreadsheets. It improves on Sonnet 5 in coding, token efficiency and clear writing, with a 1M-token context window, up to 128K output tokens and adaptive thinking."},{"id":"black-forest-labs/flux-2-max","routeId":"flux-2-max","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-11-25","displayName":"FLUX.2 Max","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"black-forest-labs/flux-2-max","outputPriceLabel":"$0.09/image","shortDescription":"FLUX.2 [max] is the top tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"FLUX.2 [max] is the top tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one architecture. This variant generates images from a text prompt and can ground generation in real-time web context."},{"id":"black-forest-labs/flux-2-pro","routeId":"flux-2-pro","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-11-25","displayName":"FLUX.2 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"black-forest-labs/flux-2-pro","outputPriceLabel":"$0.03/image","shortDescription":"FLUX.2 [pro] is the production tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"FLUX.2 [pro] is the production tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one architecture. This variant generates images from a text prompt at up to 4 megapixels."},{"id":"bytedance/seed-2.1-turbo","routeId":"seed-2-1-turbo","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-06-28","displayName":"Seed 2.1 Turbo","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"venice/seed-2.1-turbo","shortDescription":"Seed 2.1 Turbo is one of ByteDance Seed's two Seed 2.1 models (with Pro), an agent model for general agents, end-to-end coding and multimodal understanding. It understands text, images and video with…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://console.byteplus.com/ark/region:ark+ap-southeast-1/model/detail?Id=dola-seed-2-1-turbo","label":"Model source"}],"inputPriceUsdPerMillion":0.625,"outputPriceUsdPerMillion":3.125,"cacheReadPriceUsdPerMillion":0.125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/seed-2-1-turbo","routeId":"seed-2.1-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.325,"outputPriceUsdPerMillion":1.625,"cacheReadPriceUsdPerMillion":0.065,"cacheWritePriceUsdPerMillion":0.325,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/seed-2-1-turbo","routeId":"seed-2-1-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.35,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Seed 2.1 Turbo is one of ByteDance Seed's two Seed 2.1 models (with Pro), an agent model for general agents, end-to-end coding and multimodal understanding. It understands text, images and video with a 256K-token context window and supports deep thinking, GUI tasks, tool calling and structured output."},{"id":"bytedance/seedream-v4.5","routeId":"seedream-v4","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-11-05","displayName":"Seedream 4.5","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"bytedance/seedream-v4.5","outputPriceLabel":"$0.05/image","shortDescription":"Seedream 4.5 is ByteDance Seed's image generation and editing model, scaled up from Seedream 4.0 with stronger typography, dense text rendering and closer preservation of reference details. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Seedream 4.5 is ByteDance Seed's image generation and editing model, scaled up from Seedream 4.0 with stronger typography, dense text rendering and closer preservation of reference details. This variant generates images from a text prompt."},{"id":"bytedance/seedream-v5-lite","routeId":"seedream-v5-lite","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-02-23","displayName":"Seedream 5.0 Lite","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"bytedance/seedream-v5-lite","outputPriceLabel":"$0.05/image","shortDescription":"Seedream 5.0 Lite is ByteDance Seed's unified multimodal image generation model with deep thinking and online search, which it uses to interpret the intent behind a prompt and depict current topics.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Seedream 5.0 Lite is ByteDance Seed's unified multimodal image generation model with deep thinking and online search, which it uses to interpret the intent behind a prompt and depict current topics. This variant generates images from a text prompt."},{"id":"elevenlabs/elevenlabs-turbo-v2.5","voices":["Alice","Aria","Bill","Brian","Callum","Charlie","Charlotte","Chris","Daniel","Eric","George","Jessica","Laura","Liam","Lily","Matilda","Rachel","River","Roger","Sarah","Will"],"routeId":"tts-elevenlabs-turbo-v2-5","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"ElevenLabs Turbo v2.5","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$62.50/1M chars","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-turbo-v2.5","outputPriceLabel":"–","shortDescription":"Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs that generates speech in 32 languages. It is built for real-time and conversational uses where fast audio output matters more…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs that generates speech in 32 languages. It is built for real-time and conversational uses where fast audio output matters more than maximum expressiveness."},{"id":"google/gemini-3-flash-preview","routeId":"gemini-3-flash-preview","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2025-12-19","displayName":"Gemini 3 Flash Preview","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"google/gemini-3-flash-preview","shortDescription":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://deepmind.google/models/gemini/flash/","label":"Model source"}],"inputPriceUsdPerMillion":0.7,"outputPriceUsdPerMillion":3.75,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-flash-preview","routeId":"gemini-3-flash-preview","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":2.1,"cacheReadPriceUsdPerMillion":0.035,"cacheWritePriceUsdPerMillion":0.05831,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency."},{"id":"google/gemini-3.1-flash-tts","voices":["Achernar","Achird","Algenib","Algieba","Alnilam","Aoede","Autonoe","Callirrhoe","Charon","Despina","Enceladus","Erinome","Fenrir","Gacrux","Iapetus","Kore","Laomedeia","Leda","Orus","Puck","Pulcherrima","Rasalgethi","Sadachbia","Sadaltager","Schedar","Sulafat","Umbriel","Vindemiatrix","Zephyr","Zubenelgenubi"],"routeId":"tts-gemini-3-1-flash","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-20","displayName":"Gemini 3.1 Flash TTS","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$187.50/1M chars","primaryModality":"audio","providerRouteId":"google/gemini-3.1-flash-tts","outputPriceLabel":"–","shortDescription":"Gemini 3.1 Flash TTS is Google's low-latency text-to-speech model that turns text into natural, expressive speech in more than 70 languages. It supports native multi-speaker dialogue and audio tags…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Gemini 3.1 Flash TTS is Google's low-latency text-to-speech model that turns text into natural, expressive speech in more than 70 languages. It supports native multi-speaker dialogue and audio tags written into the text to steer style, pace and delivery, and its audio carries a SynthID watermark."},{"id":"google/gemini-3.1-pro-preview","routeId":"gemini-3-1-pro-preview","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"low","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-02-19","displayName":"Gemini 3.1 Pro Preview","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"google/gemini-3.1-pro-preview","shortDescription":"Gemini 3.1 Pro Preview is the preview release of Google's Gemini 3.1 Pro, a reasoning model for software engineering and agentic workflows that need precise tool use. It refines the Gemini 3 Pro…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://deepmind.google/models/gemini/pro/","label":"Model source"}],"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":0.5,"priceTiers":[{"aboveInputTokens":200000,"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":22.5,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":0.5}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/google-gemini-3-1-pro","routeId":"google/gemini-3.1-pro","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":12,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-3-1-pro-preview","routeId":"gemini-3.1-pro-preview","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.310199,"outputPriceUsdPerMillion":7.861192,"cacheReadPriceUsdPerMillion":0.26204,"cacheWritePriceUsdPerMillion":2.620397,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-1-pro-preview","routeId":"gemini-3.1-pro-preview","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":8.4,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":0.2625,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 3.1 Pro Preview is the preview release of Google's Gemini 3.1 Pro, a reasoning model for software engineering and agentic workflows that need precise tool use. It refines the Gemini 3 Pro series with better thinking, improved token efficiency and more grounded, factually consistent answers. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens."},{"id":"google/gemini-3.5-flash","routeId":"gemini-3-5-flash","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-05-22","displayName":"Gemini 3.5 Flash","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"google/gemini-3.5-flash","shortDescription":"Gemini 3.5 Flash is a Flash model in Google's Gemini 3 series, optimized for real-world tasks at higher speed and lower cost. It supports thinking. It takes text, image, video, audio and PDF input…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://deepmind.google/models/gemini/flash/","label":"Model source"}],"inputPriceUsdPerMillion":1.55,"outputPriceUsdPerMillion":9.45,"cacheReadPriceUsdPerMillion":0.155,"cacheWritePriceUsdPerMillion":0.086,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/google-gemini-3-5-flash","routeId":"google/gemini-3.5-flash","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":1.5,"outputPriceUsdPerMillion":9,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gemini-3.5-flash","routeId":"google/gemini-3.5-flash","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Google Gemini; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":1.5,"outputPriceUsdPerMillion":9,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":8192,"availability":"available","callable":true,"sourceReferences":[{"url":"https://ai.google.dev/gemini-api/terms","label":"Gemini API terms"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-3-5-flash","routeId":"gemini-3.5-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.975,"outputPriceUsdPerMillion":5.85,"cacheReadPriceUsdPerMillion":0.0975,"cacheWritePriceUsdPerMillion":0.975,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-5-flash","routeId":"gemini-3-5-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.05,"outputPriceUsdPerMillion":6.3,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.05831,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 3.5 Flash is a Flash model in Google's Gemini 3 series, optimized for real-world tasks at higher speed and lower cost. It supports thinking. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens."},{"id":"google/gemini-3.5-flash-lite","routeId":"gemini-3-5-flash-lite","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-07-09","displayName":"Gemini 3.5 Flash-Lite","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"google/gemini-3.5-flash-lite","shortDescription":"Gemini 3.5 Flash-Lite is the fastest, most cost-efficient Gemini 3.5 model with 1M context, ideal for everyday questions, summarization, and lightweight coding tasks.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.375,"outputPriceUsdPerMillion":3.125,"cacheReadPriceUsdPerMillion":0.0375,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-3-5-flash-lite","routeId":"gemini-3.5-flash-lite","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.200264,"outputPriceUsdPerMillion":1.66887,"cacheReadPriceUsdPerMillion":0.020026,"cacheWritePriceUsdPerMillion":0.200264,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-5-flash-lite","routeId":"gemini-3-5-flash-lite","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.05831,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 3.5 Flash-Lite is the fastest, most cost-efficient Gemini 3.5 model with 1M context, ideal for everyday questions, summarization, and lightweight coding tasks."},{"id":"google/gemini-3.6-flash","routeId":"gemini-3-6-flash","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-07-09","displayName":"Gemini 3.6 Flash","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"google/gemini-3.6-flash","shortDescription":"Gemini 3.6 Flash is a Flash model in Google's Gemini 3 series designed for agentic work, with strengths in code generation, agentic execution and spatial reasoning. It suits fast agentic loops with…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.9375,"outputPriceUsdPerMillion":4.6875,"cacheReadPriceUsdPerMillion":0.09375,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-3-6-flash","routeId":"gemini-3.6-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.4875,"outputPriceUsdPerMillion":2.4375,"cacheReadPriceUsdPerMillion":0.04875,"cacheWritePriceUsdPerMillion":0.4875,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-6-flash","routeId":"gemini-3-6-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.525,"outputPriceUsdPerMillion":2.625,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.02919,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 3.6 Flash is a Flash model in Google's Gemini 3 series designed for agentic work, with strengths in code generation, agentic execution and spatial reasoning. It suits fast agentic loops with complex coding cycles. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and up to 65K output tokens."},{"id":"google/gemini-3.7-flash","routeId":"gemini-3-7-flash","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-08-14","displayName":"Gemini 3.7 Flash","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"google/gemini-3.7-flash","shortDescription":"Gemini 3.7 Flash is a Flash model in Google's Gemini 3 series of natively multimodal reasoning models, built as a workhorse for coding and agentic work. It improves on Gemini 3.6 Flash in coding and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.9375,"outputPriceUsdPerMillion":4.6875,"cacheReadPriceUsdPerMillion":0.09375,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/google-gemini-3-7-flash","routeId":"google/gemini-3.7-flash","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":3.75,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-3-7-flash","routeId":"gemini-3.7-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.4875,"outputPriceUsdPerMillion":2.4375,"cacheReadPriceUsdPerMillion":0.04875,"cacheWritePriceUsdPerMillion":0.4875,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65535,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-7-flash","routeId":"gemini-3.7-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.525,"outputPriceUsdPerMillion":2.625,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.02919,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 3.7 Flash is a Flash model in Google's Gemini 3 series of natively multimodal reasoning models, built as a workhorse for coding and agentic work. It improves on Gemini 3.6 Flash in coding and web development, supports low, medium and high thinking levels, and has a 1M-token context window with up to 65K output tokens."},{"id":"google/gemini-3.8-flash","routeId":"gemini-3-8-flash","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-09-02","displayName":"Gemini 3.8 Flash","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"google/gemini-3.8-flash","shortDescription":"Gemini 3.8 Flash is a Flash model in Google's Gemini 3 series, engineered for long-horizon software engineering, autonomous agents and complex enterprise workflows at Flash-level speed and cost. It…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.9375,"outputPriceUsdPerMillion":4.6875,"cacheReadPriceUsdPerMillion":0.09375,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-3-8-flash","routeId":"gemini-3.8-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.4875,"outputPriceUsdPerMillion":2.4375,"cacheReadPriceUsdPerMillion":0.04875,"cacheWritePriceUsdPerMillion":0.4875,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65535,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-8-flash","routeId":"gemini-3.8-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.5775,"outputPriceUsdPerMillion":2.8875,"cacheReadPriceUsdPerMillion":0.05775,"cacheWritePriceUsdPerMillion":0.02919,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gemini-3.8-flash","routeId":"google/gemini-3.8-flash","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Google Gemini; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":3.75,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":null,"availability":"needs-verification","callable":false,"statusNote":"This relay route is not in the reviewed manifest and cannot be enabled.","sourceReferences":[{"url":"https://ai.google.dev/gemini-api/terms","label":"Gemini API terms"}]}],"description":"Gemini 3.8 Flash is a Flash model in Google's Gemini 3 series, engineered for long-horizon software engineering, autonomous agents and complex enterprise workflows at Flash-level speed and cost. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window, up to 65K output tokens and low, medium and high thinking levels."},{"id":"google/gemini-4-argon","routeId":"gemini-4-argon","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-10-13","displayName":"Gemini 4 Argon","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"google/gemini-4-argon","shortDescription":"Gemini 4 Argon is Google's frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":12.5,"cacheReadPriceUsdPerMillion":0.125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-4-argon","routeId":"gemini-4-argon","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":6.5,"cacheReadPriceUsdPerMillion":0.065,"cacheWritePriceUsdPerMillion":1.3,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-4-argon","routeId":"gemini-4-argon","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":7,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":0.13125,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 4 Argon is Google's frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking."},{"id":"google/gemini-embedding-2-preview","routeId":"gemini-embedding-2-preview","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Gemini Embedding 2 Preview","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":2048,"privacySummary":"Venice Anonymous routing","primaryModality":"embeddings","providerRouteId":"google/gemini-embedding-2-preview","shortDescription":"Gemini Embedding 2 is Google's natively multimodal embedding model, in preview. It maps text, images, video, audio and PDF documents into a single embedding space across more than 100 languages,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":0.25,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Gemini Embedding 2 is Google's natively multimodal embedding model, in preview. It maps text, images, video, audio and PDF documents into a single embedding space across more than 100 languages, accepting up to 8,192 text tokens, with 3,072-dimensional output that can be shortened through Matryoshka Representation Learning."},{"id":"google/nano-banana-2-lite","routeId":"nano-banana-2-lite","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-30","displayName":"Nano Banana 2 Lite","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-2-lite","outputPriceLabel":"$0.06/image","shortDescription":"Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is the speed- and cost-focused model in Google DeepMind's Nano Banana image family, built for high-volume generation and editing. This variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is the speed- and cost-focused model in Google DeepMind's Nano Banana image family, built for high-volume generation and editing. This variant generates images from a text prompt."},{"id":"gradium/gradium-tts","voices":["Alice","Davi","Elise","Emma","Eva","Jack","Kent","Leo","Maximilian","Mia","Sergio","Valentina"],"routeId":"tts-gradium-v1","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-06-05","displayName":"Gradium TTS","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$47.50/1M chars","primaryModality":"audio","providerRouteId":"venice/gradium-tts","outputPriceLabel":"–","shortDescription":"Gradium TTS is a real-time streaming text-to-speech model from Gradium, built for voice agents. It speaks English, French, German, Spanish and Portuguese with mid-sentence code-switching, works with…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Gradium TTS is a real-time streaming text-to-speech model from Gradium, built for voice agents. It speaks English, French, German, Spanish and Portuguese with mid-sentence code-switching, works with instant and professional voice clones, and reads hard cases such as phone numbers and email addresses without separate text normalization."},{"id":"ideogram/ideogram-v4","routeId":"ideogram-v4","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-03","displayName":"Ideogram 4.0","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"ideogram/ideogram-v4","outputPriceLabel":"$0.06/image","shortDescription":"Ideogram 4.0 is Ideogram's 9.3B-parameter open-weight text-to-image model, a single-stream diffusion transformer trained from scratch. It is built for in-image text and design layouts, with…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Ideogram 4.0 is Ideogram's 9.3B-parameter open-weight text-to-image model, a single-stream diffusion transformer trained from scratch. It is built for in-image text and design layouts, with structured JSON prompts, bounding-box placement, hex color palettes and output up to 2K, including very wide aspect ratios."},{"id":"ideogram/ideogram-v4.5","routeId":"ideogram-v4-5","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-30","displayName":"Ideogram 4.5","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"ideogram/ideogram-v4.5","outputPriceLabel":"$0.26/image","shortDescription":"Ideogram 4.5 is Ideogram's image generation and editing model, built for precise multi-turn edits that change part of an image while leaving the rest untouched. This variant generates images at…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Ideogram 4.5 is Ideogram's image generation and editing model, built for precise multi-turn edits that change part of an image while leaving the rest untouched. This variant generates images at native 2K from a text prompt, optionally guided by up to five reference images."},{"id":"inception/mercury-2","routeId":"mercury-2","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-02-20","displayName":"Mercury 2","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":50000,"primaryModality":"text","providerRouteId":"inception/mercury-2","shortDescription":"Mercury 2 is Inception's diffusion-based reasoning language model, which generates by refining many tokens in parallel rather than one at a time. It takes text input and output with a 128K-token…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.inceptionlabs.ai/models","label":"Model source"}],"inputPriceUsdPerMillion":0.3125,"outputPriceUsdPerMillion":0.9375,"cacheReadPriceUsdPerMillion":0.03125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/mercury-2","routeId":"mercury-2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1625,"outputPriceUsdPerMillion":0.4875,"cacheReadPriceUsdPerMillion":0.01625,"cacheWritePriceUsdPerMillion":0.1625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/mercury-2","routeId":"mercury-2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.175,"outputPriceUsdPerMillion":0.525,"cacheReadPriceUsdPerMillion":0.0175,"cacheWritePriceUsdPerMillion":0.175,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[]}],"description":"Mercury 2 is Inception's diffusion-based reasoning language model, which generates by refining many tokens in parallel rather than one at a time. It takes text input and output with a 128K-token context window and supports tunable reasoning depth, native tool calling and schema-aligned JSON output."},{"id":"inception/mercury-3","routeId":"mercury-3","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-10-19","displayName":"Mercury 3","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"inception/mercury-3","shortDescription":"Mercury 3 is Inception's most capable diffusion-based reasoning model, generating over 1,000 tokens per second with a 1M-token context window, tunable reasoning, tool calling, and structured output…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.inceptionlabs.ai/models","label":"Model source"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.01,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Mercury 3 is Inception's most capable diffusion-based reasoning model, generating over 1,000 tokens per second with a 1M-token context window, tunable reasoning, tool calling, and structured output support."},{"id":"inworld/inworld-tts-1.5-max","voices":["Alex","Ashley","Craig","Edward","Elizabeth","Hades","Luna","Mark","Olivia","Pixie","Priya","Ronald","Sarah","Theodore"],"routeId":"tts-inworld-1-5-max","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Inworld TTS-1.5 Max","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$12.50/1M chars","primaryModality":"audio","providerRouteId":"venice/inworld-tts-1.5-max","outputPriceLabel":"–","shortDescription":"Inworld TTS-1.5 Max is a text-to-speech model from Inworld AI for real-time, expressive voice applications. It speaks 15 languages, supports voice cloning from a sample, and is the higher-quality…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Inworld TTS-1.5 Max is a text-to-speech model from Inworld AI for real-time, expressive voice applications. It speaks 15 languages, supports voice cloning from a sample, and is the higher-quality option in the TTS-1.5 family, alongside the lower-latency TTS-1.5 Mini."},{"id":"krea/krea-v2-large","routeId":"krea-v2-large","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-05-22","displayName":"Krea 2 Large","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"krea/krea-v2-large","outputPriceLabel":"$0.07/image","shortDescription":"Krea 2 Large is the larger tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. It is more than twice the size of Krea 2 Medium with…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Krea 2 Large is the larger tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. It is more than twice the size of Krea 2 Medium with lighter post-training, giving rawer, more textured output suited to photorealism, and generates images from a text prompt with optional style references and moodboards."},{"id":"krea/krea-v2-medium","routeId":"krea-v2-medium","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-05-22","displayName":"Krea 2 Medium","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"krea/krea-v2-medium","outputPriceLabel":"$0.04/image","shortDescription":"Krea 2 Medium is the smaller, faster tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. Its post-training keeps output stable across…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Krea 2 Medium is the smaller, faster tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. Its post-training keeps output stable across generations and suits illustration, anime and painting, and it generates images from a text prompt with optional style references and moodboards."},{"id":"luma/luma-uni-1","routeId":"luma-uni-1","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Luma Uni-1","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"luma/luma-uni-1","outputPriceLabel":"$0.05/image","shortDescription":"Uni-1 is Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Uni-1 is Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant generates images from a text prompt, optionally guided by up to nine reference images."},{"id":"luma/luma-uni-1-max","routeId":"luma-uni-1-max","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Luma Uni-1 Max","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"luma/luma-uni-1-max","outputPriceLabel":"$0.12/image","shortDescription":"Uni-1 Max is the higher-quality tier of Uni-1, Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Uni-1 Max is the higher-quality tier of Uni-1, Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant generates images from a text prompt, optionally guided by up to nine reference images."},{"id":"meta/muse-image","routeId":"muse-image","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-03","displayName":"Muse Image","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/muse-image","outputPriceLabel":"$0.02/image","shortDescription":"Muse Image is Meta's image generation and editing model, the first from Meta Superintelligence Labs. It works with Meta's Muse Spark reasoning model to plan layouts, draw on web context and combine…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Muse Image is Meta's image generation and editing model, the first from Meta Superintelligence Labs. It works with Meta's Muse Spark reasoning model to plan layouts, draw on web context and combine multiple references, and renders legible in-image text. This variant generates images from a text prompt."},{"id":"meta/muse-wonder","routeId":"muse-wonder","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","max"],"effortConfigurable":true},"modalities":["text","image","video","audio"],"moderation":"unknown","releasedAt":"2026-10-12","displayName":"Muse Wonder","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"venice/muse-wonder","shortDescription":"Muse Wonder is a reasoning model from Meta Superintelligence Labs for long-running personal and professional agentic work, released in October 2026 as a larger class of model than the Muse Spark…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":25,"cacheReadPriceUsdPerMillion":0.25,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/muse-wonder","routeId":"muse-wonder","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.8,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":2.8,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Muse Wonder is a reasoning model from Meta Superintelligence Labs for long-running personal and professional agentic work, released in October 2026 as a larger class of model than the Muse Spark family. It accepts text, images, audio, video and PDF documents and returns text, with a context window of about 1M tokens. It is built to plan, call tools in parallel, keep track of what matters across a long task and try another approach when it hits a blocker."},{"id":"minimax/minimax-m3.1-flash","routeId":"minimax-m3-1-flash","features":["streaming","tool-calling","reasoning","vision","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"max","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-10-18","displayName":"MiniMax M3.1 Flash","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"minimax/minimax-m3.1-flash","shortDescription":"MiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.minimax.io/models/text/m3","label":"Model source"}],"inputPriceUsdPerMillion":0.1875,"outputPriceUsdPerMillion":0.75,"cacheReadPriceUsdPerMillion":0.01875,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/minimax-m3-1-flash","routeId":"minimax-m3.1-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.101269,"outputPriceUsdPerMillion":0.405076,"cacheReadPriceUsdPerMillion":0.010127,"cacheWritePriceUsdPerMillion":0.101269,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max (max by default)."},{"id":"minimax/minimax-speech-02-hd","voices":["CalmWoman","CasualGuy","DeepVoiceMan","DeterminedMan","ElegantMan","ExuberantGirl","FriendlyPerson","ImposingManner","InspirationalGirl","LivelyGirl","LovelyGirl","PatientMan","SweetGirl","WiseWoman","YoungKnight"],"routeId":"tts-minimax-speech-02-hd","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"MiniMax Speech-02 HD","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$125.00/1M chars","primaryModality":"audio","providerRouteId":"minimax/minimax-speech-02-hd","outputPriceLabel":"–","shortDescription":"Clone your voice from a short recording and generate natural speech in it across 30+ languages.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Clone your voice from a short recording and generate natural speech in it across 30+ languages."},{"id":"moonshotai/kimi-k3.1-pro","routeId":"kimi-k3-1-pro","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"max","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-23","displayName":"Kimi K3.1 Pro","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"moonshotai/kimi-k3.1-pro","shortDescription":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, agentic…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.kimi.ai/blog/kimi-k3-1-pro","label":"Model source"}],"inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, agentic workflows, financial research, and 3D modeling through CAD code."},{"id":"moonshotai/kimi-k3.1-pro-highspeed","routeId":"kimi-k3-1-pro-highspeed","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"max","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-23","displayName":"Kimi K3.1 Pro Highspeed","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"moonshotai/kimi-k3.1-pro-highspeed","shortDescription":"Kimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, Moonshot AI's flagship open-weight multimodal reasoning model. It offers the same quality and 1M-token context window with…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.kimi.ai/blog/kimi-k3-1-pro","label":"Model source"}],"inputPriceUsdPerMillion":6,"outputPriceUsdPerMillion":30,"cacheReadPriceUsdPerMillion":0.6,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Kimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, Moonshot AI's flagship open-weight multimodal reasoning model. It offers the same quality and 1M-token context window with substantially higher output speed for latency-sensitive coding and agentic workflows."},{"id":"openai/gpt-4o","routeId":"openai-gpt-4o-2024-11-20","features":["streaming","tool-calling","vision","json-schema","web-search","prompt-caching"],"provider":"venice","modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-02-28","displayName":"GPT-4o","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"openai/gpt-4o","shortDescription":"OpenAI's multimodal flagship model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-4o","label":"Model source"}],"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":1.25,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-4o","routeId":"gpt-4o","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.663186,"outputPriceUsdPerMillion":6.652745,"cacheReadPriceUsdPerMillion":0.831593,"cacheWritePriceUsdPerMillion":1.663186,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-4o","routeId":"gpt-4o","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":7,"cacheReadPriceUsdPerMillion":0.875,"cacheWritePriceUsdPerMillion":1.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"OpenAI's multimodal flagship model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20."},{"id":"openai/gpt-4o-mini","routeId":"openai-gpt-4o-mini-2024-07-18","features":["streaming","tool-calling","vision","json-schema","web-search","prompt-caching"],"provider":"venice","modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-02-28","displayName":"GPT-4o Mini","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"openai/gpt-4o-mini","shortDescription":"OpenAI's cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-4o-mini","label":"Model source"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.075,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-4o-mini","routeId":"gpt-4o-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0975,"outputPriceUsdPerMillion":0.39,"cacheReadPriceUsdPerMillion":0.04875,"cacheWritePriceUsdPerMillion":0.0975,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-4o-mini","routeId":"gpt-4o-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.42,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[]}],"description":"OpenAI's cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18."},{"id":"openai/gpt-5.2","routeId":"openai-gpt-52","features":["streaming","tool-calling","reasoning","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2025-12-13","displayName":"GPT-5.2","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"openai/gpt-5.2","shortDescription":"GPT-5.2 is OpenAI's GPT-5 series model for complex professional work. It takes text and image input and produces text output, with a 400K-token context window, up to 128K output tokens and reasoning…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.2","label":"Model source"}],"inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.175,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-5.2","routeId":"openai/gpt-5.2","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.175,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":400000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-2","routeId":"gpt-5.2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.1375,"outputPriceUsdPerMillion":9.1,"cacheReadPriceUsdPerMillion":0.11375,"cacheWritePriceUsdPerMillion":1.1375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-2","routeId":"gpt-5.2","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.225,"outputPriceUsdPerMillion":9.8,"cacheReadPriceUsdPerMillion":0.1225,"cacheWritePriceUsdPerMillion":1.225,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.2 is OpenAI's GPT-5 series model for complex professional work. It takes text and image input and produces text output, with a 400K-token context window, up to 128K output tokens and reasoning effort from none to xhigh."},{"id":"openai/gpt-5.3-codex","routeId":"openai-gpt-53-codex","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-02-24","displayName":"GPT-5.3 Codex","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":400000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.3-codex","shortDescription":"GPT-5.3 Codex is OpenAI's coding model built on GPT-5.3 and optimized for agentic coding tasks in Codex and similar environments. It takes text and image input and produces text output, with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.3-codex","label":"Model source"}],"inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.175,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-3-codex","routeId":"gpt-5.3-codex","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.1375,"outputPriceUsdPerMillion":9.1,"cacheReadPriceUsdPerMillion":0.11375,"cacheWritePriceUsdPerMillion":1.1375,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-3-codex","routeId":"gpt-5.3-codex","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.225,"outputPriceUsdPerMillion":9.8,"cacheReadPriceUsdPerMillion":0.1225,"cacheWritePriceUsdPerMillion":1.225,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.3 Codex is OpenAI's coding model built on GPT-5.3 and optimized for agentic coding tasks in Codex and similar environments. It takes text and image input and produces text output, with a 400K-token context window, up to 128K output tokens and low to xhigh reasoning effort."},{"id":"openai/gpt-5.4","routeId":"openai-gpt-54","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-03-05","displayName":"GPT-5.4","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"openai/gpt-5.4","shortDescription":"GPT-5.4 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.4","label":"Model source"}],"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.25,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":22.5,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-5.4","routeId":"openai/gpt-5.4","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.25,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":272000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-4","routeId":"gpt-5.4","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.625,"outputPriceUsdPerMillion":9.75,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":3.25,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-4","routeId":"gpt-5.4","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":10.5,"cacheReadPriceUsdPerMillion":0.175,"cacheWritePriceUsdPerMillion":1.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.4 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to xhigh."},{"id":"openai/gpt-5.4-mini","routeId":"openai-gpt-54-mini","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-03-27","displayName":"GPT-5.4 Mini","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":400000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.4-mini","shortDescription":"GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.4-mini","label":"Model source"}],"inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":4.5,"cacheReadPriceUsdPerMillion":0.075,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-5.4-mini","routeId":"openai/gpt-5.4-mini","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":4.5,"cacheReadPriceUsdPerMillion":0.075,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":400000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-4-mini","routeId":"gpt-5.4-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.4875,"outputPriceUsdPerMillion":2.925,"cacheReadPriceUsdPerMillion":0.04875,"cacheWritePriceUsdPerMillion":0.4875,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-4-mini","routeId":"gpt-5.4-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.525,"outputPriceUsdPerMillion":3.15,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.525,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use."},{"id":"openai/gpt-5.4-pro","routeId":"openai-gpt-54-pro","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"medium","supportedEfforts":["medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-03-05","displayName":"GPT-5.4 Pro","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.4-pro","shortDescription":"GPT-5.4 Pro is a version of OpenAI's GPT-5.4 that uses more compute to think harder and give more precise answers on complex, high-stakes tasks. It takes text and image input and produces text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.4-pro","label":"Model source"}],"inputPriceUsdPerMillion":30,"outputPriceUsdPerMillion":180,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":60,"outputPriceUsdPerMillion":270,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT-5.4 Pro is a version of OpenAI's GPT-5.4 that uses more compute to think harder and give more precise answers on complex, high-stakes tasks. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and medium to xhigh reasoning effort."},{"id":"openai/gpt-5.5","routeId":"openai-gpt-55","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-04-23","displayName":"GPT-5.5","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"openai/gpt-5.5","shortDescription":"GPT-5.5 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.5","label":"Model source"}],"inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":30,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":45,"cacheReadPriceUsdPerMillion":1,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-5.5","routeId":"openai/gpt-5.5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":5,"outputPriceUsdPerMillion":30,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":272000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-5","routeId":"gpt-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.25,"outputPriceUsdPerMillion":19.5,"cacheReadPriceUsdPerMillion":0.65,"cacheWritePriceUsdPerMillion":6.5,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-5","routeId":"gpt-5.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":3.5,"outputPriceUsdPerMillion":21,"cacheReadPriceUsdPerMillion":0.35,"cacheWritePriceUsdPerMillion":3.5,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.5 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to xhigh."},{"id":"openai/gpt-5.5-pro","routeId":"openai-gpt-55-pro","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["medium","high","xhigh"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-04-24","displayName":"GPT-5.5 Pro","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.5-pro","shortDescription":"GPT-5.5 Pro is a version of OpenAI's GPT-5.5 that uses more compute to think harder and give more precise answers on complex tasks. It takes text and image input and produces text output, with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.5-pro","label":"Model source"}],"inputPriceUsdPerMillion":30,"outputPriceUsdPerMillion":180,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":60,"outputPriceUsdPerMillion":270,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT-5.5 Pro is a version of OpenAI's GPT-5.5 that uses more compute to think harder and give more precise answers on complex tasks. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and medium to xhigh reasoning effort."},{"id":"openai/gpt-5.6-sol","routeId":"openai-gpt-56-sol","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-09","displayName":"GPT-5.6 Sol","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.6-sol","shortDescription":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 family, built for complex professional work such as reasoning, coding and agentic workflows. It takes text and image input and produces text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":8,"outputPriceUsdPerMillion":30,"cacheReadPriceUsdPerMillion":0.8,"cacheWritePriceUsdPerMillion":10}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-5.6-sol","routeId":"openai/gpt-5.6-sol","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":5,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":272000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-6-sol","routeId":"gpt-5.6-sol","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.284294,"outputPriceUsdPerMillion":11.421472,"cacheReadPriceUsdPerMillion":0.456859,"cacheWritePriceUsdPerMillion":5.710736,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-6-sol","routeId":"gpt-5.6-sol","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":2.8,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.28,"cacheWritePriceUsdPerMillion":3.5,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 family, built for complex professional work such as reasoning, coding and agentic workflows. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to max."},{"id":"openai/gpt-5.6-sol-pro","routeId":"openai-gpt-56-sol-pro","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-09","displayName":"GPT-5.6 Sol Pro","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.6-sol-pro","shortDescription":"GPT-5.6 Sol Pro is GPT-5.6 Sol run in OpenAI's pro reasoning mode, which performs more model work per request for difficult tasks that justify higher latency and token use. It is the same underlying…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":8,"outputPriceUsdPerMillion":30,"cacheReadPriceUsdPerMillion":0.8,"cacheWritePriceUsdPerMillion":10}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT-5.6 Sol Pro is GPT-5.6 Sol run in OpenAI's pro reasoning mode, which performs more model work per request for difficult tasks that justify higher latency and token use. It is the same underlying model, with text and image input, text output and a context window of about 1.05M tokens."},{"id":"openai/gpt-5.6-terra","routeId":"openai-gpt-56-terra","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-09","displayName":"GPT-5.6 Terra","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.6-terra","shortDescription":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","label":"Model source"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":12,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":2.5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":18,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":5}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-6-terra","routeId":"gpt-5.6-terra","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.8,"outputPriceUsdPerMillion":4.8,"cacheReadPriceUsdPerMillion":0.16,"cacheWritePriceUsdPerMillion":2,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-6-terra","routeId":"gpt-5.6-terra","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":8.4,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":1.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced."},{"id":"openai/gpt-5.6-terra-pro","routeId":"openai-gpt-56-terra-pro","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-09","displayName":"GPT-5.6 Terra Pro","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.6-terra-pro","shortDescription":"GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","label":"Model source"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":12,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":2.5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":18,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":5}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks."},{"id":"openai/gpt-6-astra","routeId":"openai-gpt-6-astra","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-05","displayName":"GPT-6 Astra","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1050000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-6-astra","shortDescription":"GPT-6 Astra is the top tier of OpenAI's GPT-6 family, built for demanding work such as complex reasoning, coding, computer use, research and document creation. It takes text and image input and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-6-astra","label":"Model source"}],"inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":1,"cacheWritePriceUsdPerMillion":12.5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":20,"outputPriceUsdPerMillion":75,"cacheReadPriceUsdPerMillion":2,"cacheWritePriceUsdPerMillion":25}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-6-astra","routeId":"openai/gpt-6-astra","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":1,"cacheWritePriceUsdPerMillion":12.5,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":272000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-6-astra","routeId":"gpt-6-astra","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":7.978438,"outputPriceUsdPerMillion":39.89219,"cacheReadPriceUsdPerMillion":1.595688,"cacheWritePriceUsdPerMillion":19.946095,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-6-astra","routeId":"gpt-6-astra","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":7,"outputPriceUsdPerMillion":35,"cacheReadPriceUsdPerMillion":0.7,"cacheWritePriceUsdPerMillion":8.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-6 Astra is the top tier of OpenAI's GPT-6 family, built for demanding work such as complex reasoning, coding, computer use, research and document creation. It takes text and image input and produces text, with a 1.05M-token context window (up to 922K input and 128K output tokens) and configurable reasoning effort."},{"id":"openai/gpt-6-astra-pro","routeId":"openai-gpt-6-astra-pro","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-05","displayName":"GPT-6 Astra Pro","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1050000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-6-astra-pro","shortDescription":"GPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-6-astra","label":"Model source"}],"inputPriceUsdPerMillion":10,"outputPriceUsdPerMillion":50,"cacheReadPriceUsdPerMillion":1,"cacheWritePriceUsdPerMillion":12.5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":20,"outputPriceUsdPerMillion":75,"cacheReadPriceUsdPerMillion":2,"cacheWritePriceUsdPerMillion":25}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra."},{"id":"openai/gpt-6-luna","routeId":"openai-gpt-6-luna","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-22","displayName":"GPT-6 Luna","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1050000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-6-luna","shortDescription":"GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-6-luna","label":"Model source"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.01,"cacheWritePriceUsdPerMillion":0.125,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.75,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":0.25}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-6-luna","routeId":"openai/gpt-6-luna","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.01,"cacheWritePriceUsdPerMillion":0.125,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":272000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-6-luna","routeId":"gpt-6-luna","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.066998,"outputPriceUsdPerMillion":0.334988,"cacheReadPriceUsdPerMillion":0.0134,"cacheWritePriceUsdPerMillion":0.167494,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-6-luna","routeId":"gpt-6-luna","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.07,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.007,"cacheWritePriceUsdPerMillion":0.0875,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K input, 128K output), text and image inputs, and capable reasoning for its price tier."},{"id":"openai/gpt-6-sol","routeId":"openai-gpt-6-sol","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-22","displayName":"GPT-6 Sol","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1050000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-6-sol","shortDescription":"GPT-6 Sol is built for complex coding and agentic workflows. It is OpenAI's GPT-6 coding and agent model, with a 1.05M token context window (922K input, 128K output), support for text and image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-6-sol","label":"Model source"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":2.5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.4,"cacheWritePriceUsdPerMillion":5}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-6-sol","routeId":"openai/gpt-6-sol","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":2.5,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":272000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-6-sol","routeId":"gpt-6-sol","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.322058,"outputPriceUsdPerMillion":6.610289,"cacheReadPriceUsdPerMillion":0.264412,"cacheWritePriceUsdPerMillion":3.305144,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-6-sol","routeId":"gpt-6-sol","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":7,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":1.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-6 Sol is built for complex coding and agentic workflows. It is OpenAI's GPT-6 coding and agent model, with a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max."},{"id":"openai/gpt-6.1-sol","routeId":"openai-gpt-61-sol","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-09-29","displayName":"GPT-6.1 Sol","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1050000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-6.1-sol","shortDescription":"GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It has a 1.05M token context window (922K input, 128K output), support for text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-6.1-sol","label":"Model source"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":2.5,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":5}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gpt-6.1-sol","routeId":"openai/gpt-6.1-sol","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":2.5,"pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","contextTokens":272000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-6-1-sol","routeId":"gpt-6.1-sol","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.7,"outputPriceUsdPerMillion":8.5,"cacheReadPriceUsdPerMillion":0.17,"cacheWritePriceUsdPerMillion":4.25,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-6-1-sol","routeId":"gpt-6.1-sol","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":7,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":1.75,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max."},{"id":"openai/gpt-6.1-sol-ultrafast","routeId":"openai-gpt-61-sol-ultrafast","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-08","displayName":"GPT-6.1 Sol Ultrafast","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1050000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-6.1-sol-ultrafast","shortDescription":"GPT-6.1 Sol Ultrafast is the same model served in OpenAI's Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-6.1-sol","label":"Model source"}],"inputPriceUsdPerMillion":12,"outputPriceUsdPerMillion":60,"cacheReadPriceUsdPerMillion":0.6,"cacheWritePriceUsdPerMillion":15,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":24,"outputPriceUsdPerMillion":90,"cacheReadPriceUsdPerMillion":1.2,"cacheWritePriceUsdPerMillion":30}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT-6.1 Sol Ultrafast is the same model served in OpenAI's Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max."},{"id":"openai/gpt-image-1.5","routeId":"gpt-image-1-5","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-12-17","displayName":"GPT Image 1.5","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-1.5","outputPriceLabel":"$0.26/image","shortDescription":"GPT Image 1.5 is OpenAI's image generation model that takes text and image input, with improved instruction following and prompt adherence over earlier GPT Image models. This variant generates images…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT Image 1.5 is OpenAI's image generation model that takes text and image input, with improved instruction following and prompt adherence over earlier GPT Image models. This variant generates images from a text prompt."},{"id":"openai/text-embedding-3-large","routeId":"text-embedding-3-large","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Text Embedding 3 Large","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":8191,"privacySummary":"Venice Anonymous routing","primaryModality":"embeddings","providerRouteId":"openai/text-embedding-3-large","shortDescription":"text-embedding-3-large is OpenAI's larger text embedding model for search, clustering, recommendations and classification. It accepts up to 8,192 input tokens and returns 3,072-dimensional embeddings…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.1625,"outputPriceUsdPerMillion":0.1625,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"text-embedding-3-large is OpenAI's larger text embedding model for search, clustering, recommendations and classification. It accepts up to 8,192 input tokens and returns 3,072-dimensional embeddings by default, which can be shortened with the dimensions parameter to trade accuracy for storage."},{"id":"openai/text-embedding-3-small","routeId":"text-embedding-3-small","features":["embeddings"],"provider":"venice","modalities":["text","embeddings"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Text Embedding 3 Small","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":8191,"privacySummary":"Venice Anonymous routing","primaryModality":"embeddings","providerRouteId":"openai/text-embedding-3-small","shortDescription":"text-embedding-3-small is OpenAI's smaller, more efficient text embedding model for search, clustering, recommendations and classification. It accepts up to 8,192 input tokens and returns…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":0.025,"outputPriceUsdPerMillion":0.025,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"text-embedding-3-small is OpenAI's smaller, more efficient text embedding model for search, clustering, recommendations and classification. It accepts up to 8,192 input tokens and returns 1,536-dimensional embeddings by default, which can be shortened with the dimensions parameter."},{"id":"qwen/qwen-3.6-plus-uncensored","routeId":"qwen-3-6-plus","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"uncensored","releasedAt":"2026-04-06","displayName":"Qwen 3.6 Plus Uncensored","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 256,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3.6-plus-uncensored","shortDescription":"Qwen 3.6 Plus Uncensored is an uncensored variant of Qwen3.6 Plus, the vision-language Plus model from Alibaba's Qwen team. The base model accepts text, image and video input with a 1M-token context…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/blog/qwen3-6-plus-towards-real-world-agents_603005","label":"Model source"}],"inputPriceUsdPerMillion":0.625,"outputPriceUsdPerMillion":3.75,"cacheReadPriceUsdPerMillion":0.0625,"cacheWritePriceUsdPerMillion":0.78,"priceTiers":[{"aboveInputTokens":256000,"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.0625,"cacheWritePriceUsdPerMillion":0.78}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-6-plus-uncensored","routeId":"qwen3.6-plus-uncensored","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.4375,"outputPriceUsdPerMillion":2.625,"cacheReadPriceUsdPerMillion":0.04375,"cacheWritePriceUsdPerMillion":0.546,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3.6 Plus Uncensored is an uncensored variant of Qwen3.6 Plus, the vision-language Plus model from Alibaba's Qwen team. The base model accepts text, image and video input with a 1M-token context window and supports switchable thinking and function calling."},{"id":"qwen/qwen-3.7-max","routeId":"qwen-3-7-max","features":["streaming","tool-calling","reasoning","vision","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-05-22","displayName":"Qwen 3.7 Max","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3.7-max","shortDescription":"Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":2.7,"outputPriceUsdPerMillion":8.05,"cacheReadPriceUsdPerMillion":0.27,"cacheWritePriceUsdPerMillion":3.35,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-7-max","routeId":"Qwen/Qwen3.7-Max","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen-3-7-max","routeId":"qwen-3-7-max","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.89,"outputPriceUsdPerMillion":5.635,"cacheReadPriceUsdPerMillion":0.189,"cacheWritePriceUsdPerMillion":2.345,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/qwen3.7-max","routeId":"qwen/qwen3.7-max","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay through a third-party routing service; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":2.8,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"available","callable":false,"sourceReferences":[]}],"description":"Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows."},{"id":"qwen/qwen-3.7-plus","routeId":"qwen-3-7-plus","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-06-02","displayName":"Qwen 3.7 Plus","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 256,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3.7-plus","shortDescription":"Qwen 3.7 Plus is a multimodal agent model from Alibaba's Qwen team, built on the Qwen3.7 text model and able to operate graphical interfaces and the command line. It accepts text, image and video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":0.625,"priceTiers":[{"aboveInputTokens":256000,"inputPriceUsdPerMillion":1.5,"outputPriceUsdPerMillion":6,"cacheReadPriceUsdPerMillion":0.15,"cacheWritePriceUsdPerMillion":1.875}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen-3-7-plus","routeId":"qwen-3-7-plus","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.4,"cacheReadPriceUsdPerMillion":0.035,"cacheWritePriceUsdPerMillion":0.4375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3.7 Plus is a multimodal agent model from Alibaba's Qwen team, built on the Qwen3.7 text model and able to operate graphical interfaces and the command line. It accepts text, image and video input with a 1M-token context window and supports switchable thinking and function calling."},{"id":"qwen/qwen-3.8-flash","routeId":"qwen-3-8-flash","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-09-10","displayName":"Qwen 3.8 Flash","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"qwen/qwen-3.8-flash","shortDescription":"Qwen 3.8 Flash is an efficient multimodal model from Alibaba's Qwen team, built on the open-weight Qwen3.8 Flash Next Mixture-of-Experts model with 125B total and 6B active parameters. It accepts…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.49,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-8-flash","routeId":"Qwen/Qwen3.8-Flash","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":0.113,"outputPriceUsdPerMillion":0.382,"cacheReadPriceUsdPerMillion":0.0141,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-8-flash","routeId":"qwen3.8-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0975,"outputPriceUsdPerMillion":0.3055,"cacheReadPriceUsdPerMillion":0.0104,"cacheWritePriceUsdPerMillion":0.13,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-8-flash","routeId":"qwen3.8-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.329,"cacheReadPriceUsdPerMillion":0.0112,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3.8 Flash is an efficient multimodal model from Alibaba's Qwen team, built on the open-weight Qwen3.8 Flash Next Mixture-of-Experts model with 125B total and 6B active parameters. It accepts text, image and video input with a 1M-token context window, supports function calling and structured output, and has a thinking mode that can be turned off."},{"id":"qwen/qwen-3.8-max","routeId":"qwen-3-8-max","features":["streaming","tool-calling","reasoning","vision","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-07-22","displayName":"Qwen 3.8 Max","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"qwen/qwen-3.8-max","shortDescription":"Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.3125,"cacheWritePriceUsdPerMillion":3.125,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-8-max","routeId":"Qwen/Qwen3.8-Max","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":1.65,"outputPriceUsdPerMillion":4.951,"cacheReadPriceUsdPerMillion":0.206,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-8-max","routeId":"qwen3.8-max","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.7,"outputPriceUsdPerMillion":5.1,"cacheReadPriceUsdPerMillion":0.17,"cacheWritePriceUsdPerMillion":2.125,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen-3-8-max","routeId":"qwen-3-8-max","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":5.25,"cacheReadPriceUsdPerMillion":0.21875,"cacheWritePriceUsdPerMillion":2.1875,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window."},{"id":"qwen/qwen-image","routeId":"qwen-image","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-01-11","displayName":"Qwen Image","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image","outputPriceLabel":"$0.03/image","shortDescription":"Qwen-Image is a 20B-parameter open-weight MMDiT image foundation model from Alibaba's Qwen team, released under Apache 2.0. It generates images from a text prompt across many styles, with particular…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen-Image","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen-Image is a 20B-parameter open-weight MMDiT image foundation model from Alibaba's Qwen team, released under Apache 2.0. It generates images from a text prompt across many styles, with particular strength in rendering complex text, including Chinese."},{"id":"qwen/qwen-image-2","routeId":"qwen-image-2","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-03-04","displayName":"Qwen Image 2.0","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2","outputPriceLabel":"$0.05/image","shortDescription":"Qwen-Image-2.0 is an image model from Alibaba's Qwen team that unifies generation and editing in one smaller, faster model, with instructions up to 1K tokens for infographics and native 2K…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen-Image-2.0 is an image model from Alibaba's Qwen team that unifies generation and editing in one smaller, faster model, with instructions up to 1K tokens for infographics and native 2K resolution. This variant generates images from a text prompt."},{"id":"qwen/qwen-image-2-pro","routeId":"qwen-image-2-pro","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-03-04","displayName":"Qwen Image 2.0 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2-pro","outputPriceLabel":"$0.10/image","shortDescription":"Qwen-Image-2.0 Pro is the Pro tier of Qwen-Image-2.0, an image model from Alibaba's Qwen team that unifies generation and editing. It accepts instructions up to 1K tokens for infographics and has…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen-Image-2.0 Pro is the Pro tier of Qwen-Image-2.0, an image model from Alibaba's Qwen team that unifies generation and editing. It accepts instructions up to 1K tokens for infographics and has native 2K resolution. This variant generates images from a text prompt."},{"id":"qwen/qwen-image-2.1-pro","routeId":"qwen-image-2-1-pro","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-20","displayName":"Qwen Image 2.1 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2.1-pro","outputPriceLabel":"$0.05/image","shortDescription":"Qwen-Image-2.1 Pro is the Pro tier of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen-Image-2.1 Pro is the Pro tier of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant generates images from a text prompt."},{"id":"qwen/qwen-image-2.1-turbo","routeId":"qwen-image-2-1-turbo","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-10-09","displayName":"Qwen Image 2.1 Turbo","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2.1-turbo","outputPriceLabel":"$0.02/image","shortDescription":"Qwen-Image-2.1 Turbo is an accelerated 8-step checkpoint of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen-Image-2.1 Turbo is an accelerated 8-step checkpoint of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant generates images from a text prompt."},{"id":"qwen/qwen-image-3","routeId":"qwen-image-3","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-08-05","displayName":"Qwen Image 3.0","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-3","outputPriceLabel":"$0.04/image","shortDescription":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders text as small as 10px, with native text in 12 languages. This standard tier is a faster version of Qwen-Image-3.0 Pro. This variant generates images from a text prompt."},{"id":"recraft/recraft-v4","routeId":"recraft-v4","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-02-12","displayName":"Recraft V4","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"recraft/recraft-v4","outputPriceLabel":"$0.05/image","shortDescription":"Recraft V4 is Recraft's rebuilt image model focused on design taste, prompt accuracy and production-grade composition. This standard tier generates 1K images from a text prompt for everyday design…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Recraft V4 is Recraft's rebuilt image model focused on design taste, prompt accuracy and production-grade composition. This standard tier generates 1K images from a text prompt for everyday design work and fast iteration."},{"id":"recraft/recraft-v4-pro","routeId":"recraft-v4-pro","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-02-12","displayName":"Recraft V4 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"recraft/recraft-v4-pro","outputPriceLabel":"$0.29/image","shortDescription":"Recraft V4 Pro is the Pro tier of Recraft V4, Recraft's rebuilt image model focused on design taste and prompt accuracy. It generates 2K images from a text prompt with finer detail and better anatomy…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Recraft V4 Pro is the Pro tier of Recraft V4, Recraft's rebuilt image model focused on design taste and prompt accuracy. It generates 2K images from a text prompt with finer detail and better anatomy and realism in complex scenes, for high-detail, print-ready visuals."},{"id":"x-ai/xai-tts-v1","voices":["altair","ara","atlas","carina","castor","celeste","cosmo","eve","helios","helix","iris","kepler","leo","lumen","luna","lux","naksh","orion","perseus","rex","rigel","sal","sirius","ursa","zagan","zenith"],"routeId":"tts-xai-v1","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Grok Text to Speech","pricingNote":"Priced per 1M input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$18.75/1M chars","primaryModality":"audio","providerRouteId":"x-ai/xai-tts-v1","outputPriceLabel":"–","shortDescription":"Grok Text to Speech is xAI's text-to-speech model for long-form and real-time speech generation. It offers built-in voices with distinct styles, speaks 20 languages, and uses inline and wrapping…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Grok Text to Speech is xAI's text-to-speech model for long-form and real-time speech generation. It offers built-in voices with distinct styles, speaks 20 languages, and uses inline and wrapping speech tags such as [laugh], [pause] and <whisper> to control delivery."},{"id":"z-ai/glm-5-turbo","routeId":"z-ai-glm-5-turbo","features":["streaming","tool-calling","reasoning","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-03-15","displayName":"GLM 5 Turbo","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"z-ai/glm-5-turbo","shortDescription":"GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5","label":"Model source"}],"inputPriceUsdPerMillion":1.2,"outputPriceUsdPerMillion":4,"cacheReadPriceUsdPerMillion":0.24,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5-turbo","routeId":"glm-5-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.78,"outputPriceUsdPerMillion":2.6,"cacheReadPriceUsdPerMillion":0.156,"cacheWritePriceUsdPerMillion":0.78,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5-turbo","routeId":"glm-5-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.84,"outputPriceUsdPerMillion":2.8,"cacheReadPriceUsdPerMillion":0.168,"cacheWritePriceUsdPerMillion":0.84,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows."},{"id":"z-ai/glm-5v-turbo","routeId":"z-ai-glm-5v-turbo","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-04-01","displayName":"GLM 5V Turbo","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"z-ai/glm-5v-turbo","shortDescription":"GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image, video, and text inputs.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.z.ai/guides/vlm/glm-5v-turbo","label":"Model source"}],"inputPriceUsdPerMillion":1.5,"outputPriceUsdPerMillion":5,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5v-turbo","routeId":"glm-5v-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.02,"outputPriceUsdPerMillion":3.4,"cacheReadPriceUsdPerMillion":0.204,"cacheWritePriceUsdPerMillion":1.02,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5v-turbo","routeId":"glm-5v-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.84,"outputPriceUsdPerMillion":2.8,"cacheReadPriceUsdPerMillion":0.168,"cacheWritePriceUsdPerMillion":0.84,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image, video, and text inputs."},{"id":"anthropic/claude-haiku-4-5","routeId":"anthropic/claude-haiku-4-5","features":["streaming","tool-calling","vision","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Claude Haiku 4.5","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/anthropic-claude-haiku-4-5","shortDescription":"Claude Haiku 4.5 is Anthropic's small, fast model for real-time, low-latency work such as chat assistants, customer support agents and pair programming. It takes text and image input and produces…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/claude-haiku-4.5","routeId":"anthropic/claude-haiku-4-5","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Anthropic; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":200000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data","label":"Anthropic API data retention"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/claude-haiku-4-5","routeId":"claude-haiku-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.65,"outputPriceUsdPerMillion":3.25,"cacheReadPriceUsdPerMillion":0.065,"cacheWritePriceUsdPerMillion":0.8125,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/claude-haiku-4-5","routeId":"claude-haiku-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.7,"outputPriceUsdPerMillion":3.5,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":0.875,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Claude Haiku 4.5 is Anthropic's small, fast model for real-time, low-latency work such as chat assistants, customer support agents and pair programming. It takes text and image input and produces text output, with a 200K-token context window, up to 64K output tokens and extended thinking."},{"id":"bytedance/seed-1.8","routeId":"ByteDance/Seed-1.8","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Seed 1.8","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/bytedance-seed-1-8","shortDescription":"Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/seed-1-8","routeId":"seed-1.8","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.2125,"outputPriceUsdPerMillion":1.7,"cacheReadPriceUsdPerMillion":0.0425,"cacheWritePriceUsdPerMillion":0.425,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":64000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management."},{"id":"bytedance/seed-2.0-code","routeId":"ByteDance/Seed-2.0-code","features":["streaming","tool-calling","vision","reasoning","code-optimized","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","displayName":"Seed 2.0 Code","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/bytedance-seed-2-0-code","shortDescription":"Seed 2.0 Code is the dedicated programming model in ByteDance Seed's Seed 2.0 family, built for software development and coding agents. It supports deep thinking and tool calling with a 256K-token…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/seed-2-0-code","routeId":"seed-2.0-code","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.325,"outputPriceUsdPerMillion":1.95,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":0.325,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/seed-2-0-code","routeId":"seed-2.0-code","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":2.1,"cacheReadPriceUsdPerMillion":0.0525,"cacheWritePriceUsdPerMillion":0.35,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":262144,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Seed 2.0 Code is the dedicated programming model in ByteDance Seed's Seed 2.0 family, built for software development and coding agents. It supports deep thinking and tool calling with a 256K-token context window and up to 128K output tokens."},{"id":"bytedance/seed-2.0-mini","routeId":"ByteDance/Seed-2.0-mini","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Seed 2.0 Mini","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/bytedance-seed-2-0-mini","shortDescription":"Seed 2.0 Mini is the throughput-optimized model in ByteDance Seed's Seed 2.0 family, built for low-latency, high-concurrency and batch workloads. It supports multimodal understanding, tool calling…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Seed 2.0 Mini is the throughput-optimized model in ByteDance Seed's Seed 2.0 family, built for low-latency, high-concurrency and batch workloads. It supports multimodal understanding, tool calling and four thinking levels from minimal to high, with a 256K-token context window."},{"id":"bytedance/seed-2.0-pro","routeId":"ByteDance/Seed-2.0-pro","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Seed 2.0 Pro","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/bytedance-seed-2-0-pro","shortDescription":"Seed 2.0 Pro is the general agent model in ByteDance Seed's Seed 2.0 family that focuses on long-chain reasoning and robustness in complex, multi-step workflows. It supports adjustable deep thinking,…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Seed 2.0 Pro is the general agent model in ByteDance Seed's Seed 2.0 family that focuses on long-chain reasoning and robustness in complex, multi-step workflows. It supports adjustable deep thinking, multimodal understanding and tool calling, with a 256K-token context window and up to 128K output tokens."},{"id":"google/gemini-2.5-flash","routeId":"google/gemini-2.5-flash","features":["streaming","tool-calling","vision","audio-input","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","audio"],"moderation":"unknown","displayName":"Gemini 2.5 Flash","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/google-gemini-2-5-flash","shortDescription":"Gemini 2.5 Flash is Google's thinking model built for price-performance, suited to large-scale processing, low-latency, high-volume tasks and agentic use cases. It takes text, image, video and audio…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gemini-2.5-flash","routeId":"google/gemini-2.5-flash","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Google Gemini; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":2.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1000000,"maxOutputTokens":8192,"availability":"available","callable":true,"sourceReferences":[{"url":"https://ai.google.dev/gemini-api/terms","label":"Gemini API terms"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-2-5-flash","routeId":"gemini-2.5-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.195,"outputPriceUsdPerMillion":1.625,"cacheReadPriceUsdPerMillion":0.0195,"cacheWritePriceUsdPerMillion":0.195,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65535,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-2-5-flash","routeId":"gemini-2.5-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":1.75,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.05831,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65535,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 2.5 Flash is Google's thinking model built for price-performance, suited to large-scale processing, low-latency, high-volume tasks and agentic use cases. It takes text, image, video and audio input and produces text output, with a 1M-token context window and up to 65K output tokens."},{"id":"google/gemini-3.1-flash-lite","routeId":"google/gemini-3.1-flash-lite","features":["streaming","tool-calling","vision","audio-input","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","audio"],"moderation":"unknown","displayName":"Gemini 3.1 Flash-Lite","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/google-gemini-3-1-flash-lite","shortDescription":"Gemini 3.1 Flash-Lite is Google's low-latency, cost-effective multimodal model for high-frequency, lightweight tasks such as high-volume agentic workflows and simple data extraction. It takes text,…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/gemini-3.1-flash-lite","routeId":"google/gemini-3.1-flash-lite","privacyLevel":"anonymous","privacySummary":"Identity-shielded relay to Google Gemini; not hardware-protected, and zero retention is not guaranteed","inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","contextTokens":1048576,"maxOutputTokens":8192,"availability":"available","callable":true,"sourceReferences":[{"url":"https://ai.google.dev/gemini-api/terms","label":"Gemini API terms"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-3-1-flash-lite","routeId":"gemini-3.1-flash-lite","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.163214,"outputPriceUsdPerMillion":0.979282,"cacheReadPriceUsdPerMillion":0.016321,"cacheWritePriceUsdPerMillion":0.163214,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-3-1-flash-lite","routeId":"gemini-3.1-flash-lite","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.175,"outputPriceUsdPerMillion":1.05,"cacheReadPriceUsdPerMillion":0.0175,"cacheWritePriceUsdPerMillion":0.05831,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 3.1 Flash-Lite is Google's low-latency, cost-effective multimodal model for high-frequency, lightweight tasks such as high-volume agentic workflows and simple data extraction. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window, up to 65K output tokens and thinking support."},{"id":"google/gemma-4-31b-it-ultra","routeId":"google/gemma-4-31B-it-Ultra","features":["streaming","tool-calling","vision","video-input","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","displayName":"Gemma 4 31B Instruct Ultra","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"deepinfra/google-gemma-4-31b-it-ultra","shortDescription":"Gemma 4 31B Instruct Ultra is a speed-optimized serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.27,"outputPriceUsdPerMillion":0.76,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Gemma 4 31B Instruct Ultra is a speed-optimized serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling."},{"id":"openai/gpt-oss-120b-ultra","routeId":"openai/gpt-oss-120b-Ultra","features":["streaming","tool-calling","reasoning"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GPT OSS 120B Ultra","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward the end user's identity, but DeepInfra marks this as a partner route and the partner inference endpoint can see the prompt and response.","DeepInfra says data for certain models may be shared with the relevant model API endpoint; that endpoint's retention and training policies apply.","DeepInfra specifically discloses retention exceptions for Google and Anthropic models. AnonRouter therefore does not claim zero retention for any DeepInfra partner route."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":131072,"privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"deepinfra/openai-gpt-oss-120b-ultra","shortDescription":"GPT OSS 120B Ultra is a speed-optimized serving variant of gpt-oss-120b, OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters. The base model takes text…","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.95,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT OSS 120B Ultra is a speed-optimized serving variant of gpt-oss-120b, OpenAI's open-weight Mixture-of-Experts language model with 117B total and 5.1B active parameters. The base model takes text input and produces text output with a 128K-token context window, configurable reasoning effort and native tool use."},{"id":"google/gemini-2.5-flash-lite","routeId":"google/gemini-2.5-flash-lite","features":["streaming","tool-calling"],"provider":"near-ai","modalities":["text"],"moderation":"unknown","displayName":"Gemini 2.5 Flash-Lite","pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls the Gemini Developer API directly. Google logs prompts for a limited period for abuse monitoring, and the provider does not publish which Gemini API tier its account uses."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Identity-shielded relay to Google Gemini; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"near-ai/gemini-2.5-flash-lite","shortDescription":"Gemini 2.5 Flash-Lite is Google's cost-efficient multimodal model in the Gemini 2.5 family, built for high-frequency, lightweight tasks such as high-volume classification and simple data extraction.…","sourceReferences":[{"url":"https://ai.google.dev/gemini-api/terms","label":"Gemini API terms"}],"inputPriceUsdPerMillion":0.1,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-2-5-flash-lite","routeId":"gemini-2.5-flash-lite","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.079286,"outputPriceUsdPerMillion":0.317143,"cacheReadPriceUsdPerMillion":0.007929,"cacheWritePriceUsdPerMillion":0.079286,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65535,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Gemini 2.5 Flash-Lite is Google's cost-efficient multimodal model in the Gemini 2.5 family, built for high-frequency, lightweight tasks such as high-volume classification and simple data extraction. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and thinking support."},{"id":"google/gemini-2.5-pro","routeId":"google/gemini-2.5-pro","features":["streaming","tool-calling","vision","reasoning"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"Gemini 2.5 Pro","pricingNote":"Standard-tier pricing in USD per 1M tokens. Prompt caching is not available on this route; every prompt token bills at the input price. The model's developer bills prompts above 200,000 tokens at a higher rate, so AnonRouter caps this route's context there.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls the Gemini Developer API directly. Google logs prompts for a limited period for abuse monitoring, and the provider does not publish which Gemini API tier its account uses."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Identity-shielded relay to Google Gemini; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gemini-2.5-pro","shortDescription":"Gemini 2.5 Pro is Google's thinking model for reasoning over complex problems in code, math and STEM. It can analyze large datasets, codebases and documents using long context, taking text, image,…","sourceReferences":[{"url":"https://ai.google.dev/gemini-api/terms","label":"Gemini API terms"}],"inputPriceUsdPerMillion":1.25,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gemini-2-5-pro","routeId":"gemini-2.5-pro","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.8125,"outputPriceUsdPerMillion":6.5,"cacheReadPriceUsdPerMillion":0.1625,"cacheWritePriceUsdPerMillion":1.625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65535,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gemini-2-5-pro","routeId":"gemini-2.5-pro","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":7,"cacheReadPriceUsdPerMillion":0.0875,"cacheWritePriceUsdPerMillion":0.2625,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/google-gemini-2-5-pro","routeId":"google/gemini-2.5-pro","privacyLevel":"anonymous","privacySummary":"Identity-shielded DeepInfra partner route; zero retention is not guaranteed","inputPriceUsdPerMillion":1.25,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":16384,"availability":"needs-verification","callable":false,"statusNote":"DeepInfra's Google bridge rejected repeated Chat Completions probes because it supplied an unsupported zero thinking budget; this route is disabled pending a provider fix.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]}],"description":"Gemini 2.5 Pro is Google's thinking model for reasoning over complex problems in code, math and STEM. It can analyze large datasets, codebases and documents using long context, taking text, image, video, audio and PDF input and producing text output, with a 1M-token context window and up to 65K output tokens."},{"id":"openai/gpt-4.1","routeId":"openai/gpt-4.1","features":["streaming","tool-calling","vision","prompt-caching"],"provider":"near-ai","modalities":["text","image"],"moderation":"unknown","displayName":"GPT-4.1","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gpt-4.1","shortDescription":"GPT-4.1 is OpenAI's non-reasoning model that excels at instruction following and tool calling, with broad knowledge across domains. It takes text and image input and produces text output, with a…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":8,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-4-1","routeId":"gpt-4.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.595238,"outputPriceUsdPerMillion":6.380952,"cacheReadPriceUsdPerMillion":0.39881,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1047576,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-4.1 is OpenAI's non-reasoning model that excels at instruction following and tool calling, with broad knowledge across domains. It takes text and image input and produces text output, with a 1M-token context window, up to 32K output tokens and low latency without a reasoning step."},{"id":"openai/gpt-4.1-mini","routeId":"openai/gpt-4.1-mini","features":["streaming","tool-calling","vision","prompt-caching"],"provider":"near-ai","modalities":["text","image"],"moderation":"unknown","displayName":"GPT-4.1 Mini","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gpt-4.1-mini","shortDescription":"GPT-4.1 Mini is a smaller, faster version of OpenAI's GPT-4.1, built for instruction following and tool calling without a reasoning step. It takes text and image input and produces text output, with…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":0.4,"outputPriceUsdPerMillion":1.6,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-4-1-mini","routeId":"gpt-4.1-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.310909,"outputPriceUsdPerMillion":1.243636,"cacheReadPriceUsdPerMillion":0.077727,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1047576,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-4.1 Mini is a smaller, faster version of OpenAI's GPT-4.1, built for instruction following and tool calling without a reasoning step. It takes text and image input and produces text output, with a 1M-token context window and up to 32K output tokens."},{"id":"openai/gpt-5","routeId":"openai/gpt-5","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"GPT-5","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":400000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gpt-5","shortDescription":"GPT-5 is OpenAI's reasoning model for coding, reasoning and agentic tasks across domains, with configurable reasoning effort (minimal, low, medium and high). It takes text and image input and…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":1.25,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5","routeId":"gpt-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.0125,"outputPriceUsdPerMillion":8.1,"cacheReadPriceUsdPerMillion":0.10125,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5 is OpenAI's reasoning model for coding, reasoning and agentic tasks across domains, with configurable reasoning effort (minimal, low, medium and high). It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens."},{"id":"openai/gpt-5-mini","routeId":"openai/gpt-5-mini","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GPT-5 Mini","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":400000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gpt-5-mini","shortDescription":"GPT-5 Mini is a faster, more cost-efficient version of OpenAI's GPT-5 reasoning model, suited to well-defined tasks, precise prompts and high-volume, low-latency workloads. It takes text and image…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.025,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-mini","routeId":"gpt-5-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1625,"outputPriceUsdPerMillion":1.3,"cacheReadPriceUsdPerMillion":0.01625,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-mini","routeId":"gpt-5-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.175,"outputPriceUsdPerMillion":1.4,"cacheReadPriceUsdPerMillion":0.0175,"cacheWritePriceUsdPerMillion":0.175,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5 Mini is a faster, more cost-efficient version of OpenAI's GPT-5 reasoning model, suited to well-defined tasks, precise prompts and high-volume, low-latency workloads. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens."},{"id":"openai/gpt-5-nano","routeId":"openai/gpt-5-nano","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GPT-5 Nano","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":400000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gpt-5-nano","shortDescription":"GPT-5 Nano is the fastest, lowest-cost version of OpenAI's GPT-5 reasoning model, suited to summarization and classification tasks. It takes text and image input and produces text output, with a…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":0.4,"cacheReadPriceUsdPerMillion":0.005,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-nano","routeId":"gpt-5-nano","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.0325,"outputPriceUsdPerMillion":0.26,"cacheReadPriceUsdPerMillion":0.00325,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-nano","routeId":"gpt-5-nano","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.035,"outputPriceUsdPerMillion":0.28,"cacheReadPriceUsdPerMillion":0.0035,"cacheWritePriceUsdPerMillion":0.035,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5 Nano is the fastest, lowest-cost version of OpenAI's GPT-5 reasoning model, suited to summarization and classification tasks. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens."},{"id":"openai/gpt-5.1","routeId":"openai/gpt-5.1","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GPT-5.1","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":400000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gpt-5.1","shortDescription":"GPT-5.1 is OpenAI's GPT-5 series model for coding and agentic tasks, with configurable reasoning effort that includes a non-reasoning setting. It takes text and image input and produces text output,…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":1.25,"outputPriceUsdPerMillion":10,"cacheReadPriceUsdPerMillion":0.125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-1","routeId":"gpt-5.1","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.026816,"outputPriceUsdPerMillion":8.214528,"cacheReadPriceUsdPerMillion":0.102682,"cacheWritePriceUsdPerMillion":1.026816,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.1 is OpenAI's GPT-5 series model for coding and agentic tasks, with configurable reasoning effort that includes a non-reasoning setting. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens."},{"id":"openai/gpt-5.4-nano","routeId":"openai/gpt-5.4-nano","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GPT-5.4 Nano","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":400000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"near-ai/gpt-5.4-nano","shortDescription":"GPT-5.4 Nano is the lowest-cost GPT-5.4-class model from OpenAI, designed for simple, high-volume tasks where speed and cost matter most, such as classification and data extraction. It takes text and…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":1.25,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-4-nano","routeId":"gpt-5.4-nano","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.17,"outputPriceUsdPerMillion":1.0625,"cacheReadPriceUsdPerMillion":0.017,"cacheWritePriceUsdPerMillion":0.17,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-4-nano","routeId":"gpt-5.4-nano","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.875,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":0.14,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":400000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GPT-5.4 Nano is the lowest-cost GPT-5.4-class model from OpenAI, designed for simple, high-volume tasks where speed and cost matter most, such as classification and data extraction. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens."},{"id":"openai/gpt-5.6-luna","routeId":"openai/gpt-5.6-luna","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"GPT-5.6 Luna","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider bills a higher tier above 272,000 input tokens, so AnonRouter caps this route's context there. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":272000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"near-ai/gpt-5.6-luna","shortDescription":"GPT-5.6 Luna is OpenAI's GPT-5.6 model for cost-sensitive, high-volume workloads, roughly matching the nano tier of earlier GPT-5 families. It takes text and image input and produces text output,…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":0.25,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/gpt-5-6-luna","routeId":"gpt-5.6-luna","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.095561,"outputPriceUsdPerMillion":0.573365,"cacheReadPriceUsdPerMillion":0.019112,"cacheWritePriceUsdPerMillion":0.238902,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/gpt-5-6-luna","routeId":"gpt-5.6-luna","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.14,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.014,"cacheWritePriceUsdPerMillion":0.175,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1050000,"maxOutputTokens":128000,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"openai/gpt-5.6-luna","routeId":"openai-gpt-56-luna","privacyLevel":"anonymous","privacySummary":"Venice Anonymous routing","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":0.25,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":128000,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.6-luna","label":"Model source"}]}],"description":"GPT-5.6 Luna is OpenAI's GPT-5.6 model for cost-sensitive, high-volume workloads, roughly matching the nano tier of earlier GPT-5 families. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output tokens and reasoning effort from none to max."},{"id":"openai/o3","routeId":"openai/o3","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"o3","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"near-ai/o3","shortDescription":"o3 is OpenAI's well-rounded reasoning model for complex tasks across domains. It takes text and image input and produces text output, with a 200K-token context window and up to 100K output tokens.","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":8,"cacheReadPriceUsdPerMillion":0.5,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/o3","routeId":"o3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":5.2,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":100000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"o3 is OpenAI's well-rounded reasoning model for complex tasks across domains. It takes text and image input and produces text output, with a 200K-token context window and up to 100K output tokens."},{"id":"openai/o3-mini","routeId":"openai/o3-mini","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"o3-mini","pricingNote":"Standard-tier pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"near-ai/o3-mini","shortDescription":"o3-mini is OpenAI's small reasoning model, offering strong reasoning at the cost and latency targets of o1-mini. It takes text input and produces text output, with a 200K-token context window and up…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":1.1,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.55,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/o3-mini","routeId":"o3-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.715,"outputPriceUsdPerMillion":2.86,"cacheReadPriceUsdPerMillion":0.3575,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":100000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"o3-mini is OpenAI's small reasoning model, offering strong reasoning at the cost and latency targets of o1-mini. It takes text input and produces text output, with a 200K-token context window and up to 100K output tokens."},{"id":"openai/o4-mini","routeId":"openai/o4-mini","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"near-ai","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"o4-mini","pricingNote":"Standard-tier pricing in USD per 1M tokens. The provider's optional flex and priority tiers are not exposed by AnonRouter.","availability":"available","privacyLevel":"anonymous","privacyNotes":["This is a relayed route: the provider's gateway forwards the prompt to the model's developer, or to an aggregator, using the provider's own account. The model runs outside any TEE and nothing about the serving path is attested.","AnonRouter calls the provider with its own account and forwards no end-user identity or user field. The upstream developer can see the provider's account identifier, which all AnonRouter traffic shares, and anything inside the prompt itself.","The provider's terms say it will not use customer data to train models. That promise does not bind the upstream developer, whose own terms and retention apply.","The provider calls OpenAI's API directly. OpenAI's standard API policy applies (abuse-monitoring logs kept up to 30 days), and the provider publishes no zero-retention approval for its account."],"providerName":"NEAR AI","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":200000,"privacySummary":"Identity-shielded relay to OpenAI; not hardware-protected, and zero retention is not guaranteed","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"near-ai/o4-mini","shortDescription":"o4-mini is OpenAI's fast, cost-efficient reasoning model, optimized for efficient performance in coding and visual tasks. It takes text and image input and produces text output, with a 200K-token…","sourceReferences":[{"url":"https://developers.openai.com/api/docs/guides/your-data","label":"OpenAI API data controls"}],"inputPriceUsdPerMillion":1.1,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.275,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/o4-mini","routeId":"o4-mini","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.715,"outputPriceUsdPerMillion":2.86,"cacheReadPriceUsdPerMillion":0.17875,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":100000,"availability":"available","callable":true,"sourceReferences":[]}],"description":"o4-mini is OpenAI's fast, cost-efficient reasoning model, optimized for efficient performance in coding and visual tasks. It takes text and image input and produces text output, with a 200K-token context window and up to 100K output tokens."},{"id":"inception/mercury-2.5","routeId":"mercury-2.5","features":["streaming","reasoning","prompt-caching"],"provider":"cheaperinference","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"Mercury 2.5","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Cheaper Inference","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":260000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"cheaperinference/mercury-2-5","shortDescription":"Mercury 2.5 is a diffusion-based reasoning model from Inception with fast parallel token generation, tunable reasoning, tool calling, and structured output support.","sourceReferences":[],"inputPriceUsdPerMillion":0.026,"outputPriceUsdPerMillion":0.0975,"cacheReadPriceUsdPerMillion":0.0026,"cacheWritePriceUsdPerMillion":0.026,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"inception/mercury-2.5","routeId":"mercury-2-5","privacyLevel":"anonymous","privacySummary":"Venice Anonymous routing","inputPriceUsdPerMillion":0.25,"outputPriceUsdPerMillion":0.9375,"cacheReadPriceUsdPerMillion":0.025,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":260000,"maxOutputTokens":65536,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.inceptionlabs.ai/models","label":"Model source"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/mercury-2-5","routeId":"mercury-2.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.028,"outputPriceUsdPerMillion":0.105,"cacheReadPriceUsdPerMillion":0.0028,"cacheWritePriceUsdPerMillion":0.028,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":260000,"maxOutputTokens":65536,"availability":"available","callable":false,"sourceReferences":[]}],"description":"Mercury 2.5 is a diffusion-based reasoning model from Inception with fast parallel token generation, tunable reasoning, tool calling, and structured output support."},{"id":"openai/gpt-4.1-nano","routeId":"gpt-4.1-nano","features":["streaming","vision","prompt-caching"],"provider":"cheaperinference","modalities":["text","image"],"moderation":"unknown","displayName":"GPT-4.1 Nano","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Cheaper Inference","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1047576,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"cheaperinference/gpt-4-1-nano","shortDescription":"GPT-4.1 Nano is the fastest, most cost-efficient version of OpenAI's GPT-4.1, built for instruction following and tool calling without a reasoning step. It takes text and image input and produces…","sourceReferences":[],"inputPriceUsdPerMillion":0.083452,"outputPriceUsdPerMillion":0.333808,"cacheReadPriceUsdPerMillion":0.020863,"cacheWritePriceUsdPerMillion":0.083452,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"GPT-4.1 Nano is the fastest, most cost-efficient version of OpenAI's GPT-4.1, built for instruction following and tool calling without a reasoning step. It takes text and image input and produces text output, with a 1M-token context window and up to 32K output tokens."},{"id":"thinking-machines/inkling","routeId":"inkling","features":["streaming","vision","prompt-caching"],"provider":"cheaperinference","modalities":["text","image"],"moderation":"unknown","displayName":"Inkling","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Cheaper Inference","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"cheaperinference/inkling","shortDescription":"Inkling is Thinking Machines Lab's general-purpose multimodal model, a sparse Mixture-of-Experts with 975B total and 41B active parameters. It accepts text, image and audio input and generates text,…","sourceReferences":[],"inputPriceUsdPerMillion":0.65,"outputPriceUsdPerMillion":2.6325,"cacheReadPriceUsdPerMillion":0.1105,"cacheWritePriceUsdPerMillion":0.65,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/inkling","routeId":"inkling","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.39375,"outputPriceUsdPerMillion":1.05,"cacheReadPriceUsdPerMillion":0.0875,"cacheWritePriceUsdPerMillion":0.39375,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":4096,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"thinking-machines/inkling","routeId":"inkling","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.5625,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":0.125,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":524288,"maxOutputTokens":65536,"availability":"deprecated","callable":false,"statusNote":"Venice removes this route on 2026-10-29.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/thinkingmachines/Inkling-NVFP4","label":"Model source"}]}],"description":"Inkling is Thinking Machines Lab's general-purpose multimodal model, a sparse Mixture-of-Experts with 975B total and 41B active parameters. It accepts text, image and audio input and generates text, with a context of up to 1M tokens and variable thinking effort, for chat, coding, tool use and agentic workflows."},{"id":"xiaomi/mimo-v2.5","routeId":"mimo-v2.5","features":["streaming","vision","reasoning","prompt-caching"],"provider":"cheaperinference","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"MiMo-V2.5","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Cheaper Inference","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"cheaperinference/mimo-v2-5","shortDescription":"MiMo-V2.5 is Xiaomi's native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts…","sourceReferences":[],"inputPriceUsdPerMillion":0.091,"outputPriceUsdPerMillion":0.182,"cacheReadPriceUsdPerMillion":0.00182,"cacheWritePriceUsdPerMillion":0.091,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"venice","providerName":"Venice","providerRouteId":"xiaomi/mimo-v2.5","routeId":"xiaomi-mimo-v2-5","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":0.4,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.08,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","label":"Model source"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/xiaomi-mimo-v2-5","routeId":"xiaomi-mimo-v2-5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.28,"outputPriceUsdPerMillion":1.4,"cacheReadPriceUsdPerMillion":0.056,"cacheWritePriceUsdPerMillion":0.28,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":65536,"availability":"available","callable":false,"sourceReferences":[]}],"description":"MiMo-V2.5 is Xiaomi's native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts backbone with 310B total and 15B active parameters, it delivers long-context reasoning up to 1M tokens, function calling, and multimodal perception."},{"id":"z-ai/glm-4.5","routeId":"glm-4.5","features":["streaming","reasoning","prompt-caching"],"provider":"cheaperinference","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GLM 4.5","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Cheaper Inference","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":96000,"primaryModality":"text","providerRouteId":"cheaperinference/glm-4-5","shortDescription":"GLM-4.5 is Z.ai's open-weight foundation model built for agent-oriented applications, a Mixture-of-Experts model with 355 billion total parameters and 32 billion active. It takes text input and…","sourceReferences":[],"inputPriceUsdPerMillion":0.33,"outputPriceUsdPerMillion":1.21,"cacheReadPriceUsdPerMillion":0.0605,"cacheWritePriceUsdPerMillion":0.33,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-4-5","routeId":"glm-4.5","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.42,"outputPriceUsdPerMillion":1.54,"cacheReadPriceUsdPerMillion":0.077,"cacheWritePriceUsdPerMillion":0.42,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-4.5 is Z.ai's open-weight foundation model built for agent-oriented applications, a Mixture-of-Experts model with 355 billion total parameters and 32 billion active. It takes text input and produces text output, with a 128K-token context window. It is a hybrid reasoning model with a thinking mode for complex reasoning and tool use and a non-thinking mode for fast replies, and supports function calling for coding, web browsing and agentic task automation."},{"id":"z-ai/glm-4.5-air","routeId":"glm-4.5-air","features":["streaming","reasoning","prompt-caching"],"provider":"cheaperinference","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"GLM 4.5 Air","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Cheaper Inference","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":98304,"primaryModality":"text","providerRouteId":"cheaperinference/glm-4-5-air","shortDescription":"GLM-4.5-Air is Z.ai's compact open-weight model in the GLM-4.5 series, a Mixture-of-Experts model with 106 billion total parameters and 12 billion active. It takes text input and produces text…","sourceReferences":[],"inputPriceUsdPerMillion":0.11,"outputPriceUsdPerMillion":0.605,"cacheReadPriceUsdPerMillion":0.0165,"cacheWritePriceUsdPerMillion":0.11,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-4-5-air","routeId":"glm-4.5-air","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.091,"outputPriceUsdPerMillion":0.595,"cacheReadPriceUsdPerMillion":0.0175,"cacheWritePriceUsdPerMillion":0.091,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":128000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]}],"description":"GLM-4.5-Air is Z.ai's compact open-weight model in the GLM-4.5 series, a Mixture-of-Experts model with 106 billion total parameters and 12 billion active. It takes text input and produces text output, with a 128K-token context window. It offers a thinking mode for complex reasoning and tool use and a non-thinking mode for fast replies, and is built for agent applications, coding and function calling."},{"id":"google/gemma-4-26b-a4b-it:free","routeId":"@cf/google/gemma-4-26b-a4b-it","features":["streaming","tool-calling","free"],"provider":"cloudflare","modalities":["text"],"moderation":"unknown","displayName":"Gemma 4 26B A4B","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Cloudflare Workers AI","routingModes":["anonrouter-hosted"],"contextTokens":32768,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"cloudflare/gemma-4-26b-a4b-it-free","shortDescription":"Free access to Gemma 4 26B A4B on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-21","callable":true,"operationalAvailability":"available","free":{"baseModelId":"google/gemma-4-26b-a4b-it","promotion":"limited-shared-capacity"}},{"id":"meta/llama-3.1-8b-instruct:free","routeId":"@cf/meta/llama-3.1-8b-instruct-fp8-fast","features":["streaming","free"],"provider":"cloudflare","modalities":["text"],"moderation":"unknown","displayName":"Llama 3.1 8B Instruct","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Cloudflare Workers AI","routingModes":["anonrouter-hosted"],"contextTokens":16384,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"cloudflare/llama-3-1-8b-instruct-free","shortDescription":"Free access to Llama 3.1 8B Instruct on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-21","callable":true,"operationalAvailability":"available","free":{"baseModelId":"meta/llama-3.1-8b-instruct","promotion":"limited-shared-capacity"}},{"id":"mistralai/mistral-small-3.1-24b-instruct:free","routeId":"@cf/mistralai/mistral-small-3.1-24b-instruct","features":["streaming","tool-calling","free"],"provider":"cloudflare","modalities":["text"],"moderation":"unknown","displayName":"Mistral Small 3.1 24B","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Cloudflare Workers AI","routingModes":["anonrouter-hosted"],"contextTokens":32768,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"cloudflare/mistral-small-3-1-24b-instruct-free","shortDescription":"Free access to Mistral Small 3.1 24B on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-21","callable":true,"operationalAvailability":"available","free":{"baseModelId":"mistralai/mistral-small-3.1-24b-instruct","promotion":"limited-shared-capacity"}},{"id":"qwen/qwen3-30b-a3b:free","routeId":"@cf/qwen/qwen3-30b-a3b-fp8","features":["streaming","tool-calling","free"],"provider":"cloudflare","modalities":["text"],"moderation":"unknown","displayName":"Qwen3 30B A3B","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Cloudflare Workers AI","routingModes":["anonrouter-hosted"],"contextTokens":32768,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"cloudflare/qwen3-30b-a3b-free","shortDescription":"Free access to Qwen3 30B A3B on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-21","callable":true,"operationalAvailability":"available","free":{"baseModelId":"qwen/qwen3-30b-a3b","promotion":"limited-shared-capacity"}},{"id":"openai/gpt-oss-120b:free","routeId":"openai/gpt-oss-120b","features":["streaming","tool-calling","reasoning","json-schema","free"],"provider":"groq","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GPT OSS 120B","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Groq","routingModes":["anonrouter-hosted"],"contextTokens":8000,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":4000,"primaryModality":"text","providerRouteId":"groq/gpt-oss-120b-free","shortDescription":"Free access to GPT OSS 120B on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-21","callable":true,"operationalAvailability":"available","free":{"baseModelId":"openai/gpt-oss-120b","promotion":"limited-shared-capacity"}},{"id":"openai/gpt-oss-20b:free","routeId":"openai/gpt-oss-20b","features":["streaming","tool-calling","reasoning","json-schema","free"],"provider":"groq","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GPT OSS 20B","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Groq","routingModes":["anonrouter-hosted"],"contextTokens":8000,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":4000,"primaryModality":"text","providerRouteId":"groq/gpt-oss-20b-free","shortDescription":"Free access to GPT OSS 20B on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-21","callable":true,"operationalAvailability":"available","free":{"baseModelId":"openai/gpt-oss-20b","promotion":"limited-shared-capacity"}},{"id":"cohere/north-mini-code:free","routeId":"cohere/north-mini-code:free","features":["streaming","tool-calling","code-optimized","free"],"provider":"kilo","modalities":["text"],"moderation":"unknown","displayName":"North Mini Code","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Kilo","routingModes":["anonrouter-hosted"],"contextTokens":65536,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"kilo/north-mini-code-free","shortDescription":"Free access to North Mini Code on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-22","callable":true,"operationalAvailability":"available","free":{"baseModelId":"cohere/north-mini-code","promotion":"limited-shared-capacity"}},{"id":"dots-studio/dots-3-note-preview:free","routeId":"dots-studio/dots-3-note-preview:free","features":["streaming","tool-calling","json-schema","free"],"provider":"kilo","modalities":["text"],"moderation":"unknown","statusNote":"Free access ends on 2026-12-31.","displayName":"Dots3 Note Preview","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Kilo","routingModes":["anonrouter-hosted"],"contextTokens":65536,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"kilo/dots-3-note-preview-free","shortDescription":"Free access to Dots3 Note Preview on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-22","callable":true,"operationalAvailability":"available","free":{"baseModelId":"dots-studio/dots-3-note-preview","promotion":"limited-shared-capacity"}},{"id":"liquid/lfm-2.5-2.6b:free","routeId":"liquid/lfm-2.5-2.6b:free","features":["streaming","tool-calling","json-schema","free"],"provider":"kilo","modalities":["text"],"moderation":"unknown","displayName":"LFM 2.5 2.6B","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Kilo","routingModes":["anonrouter-hosted"],"contextTokens":65536,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"kilo/lfm-2-5-2-6b-free","shortDescription":"Free access to LFM 2.5 2.6B on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-22","callable":true,"operationalAvailability":"available","free":{"baseModelId":"liquid/lfm-2.5-2.6b","promotion":"limited-shared-capacity"}},{"id":"poolside/laguna-s-2.1:free","routeId":"poolside/laguna-s-2.1:free","features":["streaming","tool-calling","free"],"provider":"kilo","modalities":["text"],"moderation":"unknown","statusNote":"Free access ends on 2026-10-31.","displayName":"Laguna S 2.1","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"deprecated","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Kilo","routingModes":["anonrouter-hosted"],"contextTokens":65536,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"kilo/laguna-s-2-1-free","shortDescription":"Free access to Laguna S 2.1 on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-22","callable":true,"operationalAvailability":"available","free":{"baseModelId":"poolside/laguna-s-2.1","promotion":"limited-shared-capacity"}},{"id":"reflection/beam:free","routeId":"reflection/beam-free","features":["streaming","tool-calling","free"],"provider":"kilo","modalities":["text"],"moderation":"unknown","displayName":"Beam","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Kilo","routingModes":["anonrouter-hosted"],"contextTokens":65536,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"kilo/beam-free","shortDescription":"Free access to Beam on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-22","callable":true,"operationalAvailability":"available","free":{"baseModelId":"reflection/beam","promotion":"limited-shared-capacity"}},{"id":"meta/muse-spark-1.1","routeId":"muse-spark-1.1","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"surplusintelligence","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Muse Spark 1.1","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"surplusintelligence/muse-spark-1-1","shortDescription":"Muse Spark 1.1 is a multimodal reasoning model from Meta Superintelligence Labs, built for agentic tasks. It accepts text, image, video, audio and PDF input, returns text, and has a 1,048,576-token…","sourceReferences":[],"inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":2.975,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.875,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Muse Spark 1.1 is a multimodal reasoning model from Meta Superintelligence Labs, built for agentic tasks. It accepts text, image, video, audio and PDF input, returns text, and has a 1,048,576-token context window that it can actively manage and compact. It is trained for tool use that generalizes to new tools and MCP servers, computer use across multiple applications, coding on large codebases, and orchestrating parallel subagents."},{"id":"meta/muse-spark-1.2","routeId":"muse-spark-1.2","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"surplusintelligence","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Muse Spark 1.2","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"surplusintelligence/muse-spark-1-2","shortDescription":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 from Meta, co-trained with Meta's Muse Code terminal coding agent. It is a reasoning model with adjustable thinking effort that accepts…","sourceReferences":[],"inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":2.975,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.875,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 from Meta, co-trained with Meta's Muse Code terminal coding agent. It is a reasoning model with adjustable thinking effort that accepts text, image, video, audio and PDF input, returns text, and has a 1,048,576-token context window. It targets code generation, complex debugging, codebase understanding and long-horizon developer workflows, using planning, goal conditioning, context compaction and parallel tool calls."},{"id":"meta/muse-spark-1.3","routeId":"muse-spark-1.3","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"surplusintelligence","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Muse Spark 1.3","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"surplusintelligence/muse-spark-1-3","shortDescription":"Muse Spark 1.3 is a reasoning model from Meta and an update to Muse Spark 1.2, with improved performance on agentic and coding tasks. It accepts text, image, video and PDF input and returns text,…","sourceReferences":[],"inputPriceUsdPerMillion":0.875,"outputPriceUsdPerMillion":2.975,"cacheReadPriceUsdPerMillion":0.105,"cacheWritePriceUsdPerMillion":0.875,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Muse Spark 1.3 is a reasoning model from Meta and an update to Muse Spark 1.2, with improved performance on agentic and coding tasks. It accepts text, image, video and PDF input and returns text, with a 1,048,576-token context window and adjustable reasoning effort. It is trained for longer-horizon work, follows long instructions more reliably, asks clarifying questions, confirms consequential actions, and is more resistant to prompt injection."},{"id":"mistralai/mistral-large-4","routeId":"mistral-large-4-0","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"surplusintelligence","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Mistral Large 4","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":524288,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"surplusintelligence/mistral-large-4-0","shortDescription":"Mistral Large 4 is Mistral AI's general-purpose multimodal Mixture-of-Experts model, with 1.05 trillion total parameters, 52 billion active, and a 1.6B vision encoder. It takes text and image input…","sourceReferences":[],"inputPriceUsdPerMillion":0.952,"outputPriceUsdPerMillion":2.926,"cacheReadPriceUsdPerMillion":0.098,"cacheWritePriceUsdPerMillion":0.952,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Mistral Large 4 is Mistral AI's general-purpose multimodal Mixture-of-Experts model, with 1.05 trillion total parameters, 52 billion active, and a 1.6B vision encoder. It takes text and image input and produces text output, and works as a hybrid instruct and reasoning model with function calling and structured outputs. It is built for coding, agentic workflows and multimodal understanding, and is natively fluent in more than 160 languages."},{"id":"mistralai/mistral-small-4","routeId":"mistral-small-4","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"surplusintelligence","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"Mistral Small 4","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"surplusintelligence/mistral-small-4","shortDescription":"Mistral Small 4 is Mistral AI's open-weight hybrid model that unifies instruct, reasoning and coding capabilities in a single model. It is a Mixture-of-Experts model with 119 billion total parameters…","sourceReferences":[],"inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.42,"cacheReadPriceUsdPerMillion":0.0105,"cacheWritePriceUsdPerMillion":0.105,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Mistral Small 4 is Mistral AI's open-weight hybrid model that unifies instruct, reasoning and coding capabilities in a single model. It is a Mixture-of-Experts model with 119 billion total parameters and 128 experts, 4 active per token, and a 256K-token context window. It accepts text and image input and produces text output, supports function calling and structured outputs, and offers a configurable reasoning effort for switching between fast replies and step-by-step reasoning on complex problems."},{"id":"qwen/qwen-3-coder-480b","routeId":"qwen3-coder","features":["streaming","tool-calling","prompt-caching"],"provider":"surplusintelligence","modalities":["text"],"moderation":"unknown","displayName":"Qwen 3 Coder 480B","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"surplusintelligence/qwen3-coder","shortDescription":"Qwen3-Coder-480B-A35B-Instruct is an open-weight coding model from Alibaba's Qwen team, a Mixture-of-Experts model with 480 billion total parameters and 35 billion active per token. It takes text…","sourceReferences":[],"inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.7,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":0.21,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3-Coder-480B-A35B-Instruct is an open-weight coding model from Alibaba's Qwen team, a Mixture-of-Experts model with 480 billion total parameters and 35 billion active per token. It takes text input and produces text output, with a native context window of 262,144 tokens. It is built for agentic coding, browser use and tool calling, and runs in non-thinking mode only."},{"id":"qwen/qwen-3.8-omni-flash","routeId":"qwen3.8-omni-flash","features":["streaming","tool-calling","vision","reasoning","prompt-caching"],"provider":"surplusintelligence","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image"],"moderation":"unknown","displayName":"Qwen 3.8 Omni Flash","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"surplusintelligence/qwen3-8-omni-flash","shortDescription":"Qwen3.8-Omni-Flash is an omni-modal model from Alibaba's Qwen team, built around agentic audio and video understanding. It takes text, image, audio and video input and produces text output, with a…","sourceReferences":[],"inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.329,"cacheReadPriceUsdPerMillion":0.0112,"cacheWritePriceUsdPerMillion":0.105,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3.8-Omni-Flash is an omni-modal model from Alibaba's Qwen team, built around agentic audio and video understanding. It takes text, image, audio and video input and produces text output, with a 1M-token context window, thinking enabled by default with adjustable effort, and tool calling. It is built to plan and complete tasks from audio-visual content, such as video editing, film commentary, meeting minutes and audio-visual summarization, and accepts audio in 113 languages and dialects."},{"id":"qwen/qwen3-vl-235b-a22b-thinking","routeId":"qwen3-vl-235b-a22b-thinking","features":["streaming","tool-calling","vision","prompt-caching"],"provider":"surplusintelligence","modalities":["text","image"],"moderation":"unknown","displayName":"Qwen3 VL 235B A22B Thinking","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"surplusintelligence/qwen3-vl-235b-a22b-thinking","shortDescription":"Qwen3-VL-235B-A22B-Thinking is the reasoning-enhanced Thinking edition of the Qwen team's Qwen3-VL vision-language series, a Mixture-of-Experts model with about 235 billion total parameters and 22…","sourceReferences":[],"inputPriceUsdPerMillion":0.147,"outputPriceUsdPerMillion":1.33,"cacheReadPriceUsdPerMillion":0.07,"cacheWritePriceUsdPerMillion":0.147,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3-VL-235B-A22B-Thinking is the reasoning-enhanced Thinking edition of the Qwen team's Qwen3-VL vision-language series, a Mixture-of-Experts model with about 235 billion total parameters and 22 billion active. It accepts text, image and video input and produces text output. It is built for multimodal reasoning in STEM and math, visual agent tasks on PC and mobile interfaces, generating code from images or video, 2D and 3D grounding, and OCR in 32 languages."},{"id":"qwen/qwen3-vl-30b-a3b-thinking","routeId":"qwen3-vl-30b-a3b-thinking","features":["streaming","vision","prompt-caching"],"provider":"surplusintelligence","modalities":["text","image"],"moderation":"unknown","displayName":"Qwen3 VL 30B A3B Thinking","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":128000,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"surplusintelligence/qwen3-vl-30b-a3b-thinking","shortDescription":"Qwen3-VL-30B-A3B-Thinking is the reasoning-enhanced Thinking edition of the Qwen team's mid-size Qwen3-VL vision-language model, a Mixture-of-Experts model with about 30 billion total parameters and…","sourceReferences":[],"inputPriceUsdPerMillion":0.175,"outputPriceUsdPerMillion":0.63,"cacheReadPriceUsdPerMillion":0.02625,"cacheWritePriceUsdPerMillion":0.175,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Qwen3-VL-30B-A3B-Thinking is the reasoning-enhanced Thinking edition of the Qwen team's mid-size Qwen3-VL vision-language model, a Mixture-of-Experts model with about 30 billion total parameters and 3 billion active. It accepts text, image and video input and produces text output. It is built for STEM and math reasoning, visual question answering, OCR in 32 languages, video understanding and visual agent tasks."},{"id":"tencent/hy3","routeId":"hy3","features":["streaming","tool-calling","reasoning","prompt-caching"],"provider":"surplusintelligence","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","displayName":"Hy3","pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","availability":"available","privacyLevel":"anonymous","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","The upstream service and its serving partners may retain prompts and outputs. Upstream zero retention is not guaranteed."],"providerName":"Surplus Intelligence","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"surplusintelligence/hy3","shortDescription":"Hy3 is an open-weight Mixture-of-Experts language model from the Tencent Hy team, with 295B total parameters, 21B active per token and a 256K-token context window. It is a text model that combines…","sourceReferences":[],"inputPriceUsdPerMillion":0.05775,"outputPriceUsdPerMillion":0.231,"cacheReadPriceUsdPerMillion":0.01442,"cacheWritePriceUsdPerMillion":0.05775,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","description":"Hy3 is an open-weight Mixture-of-Experts language model from the Tencent Hy team, with 295B total parameters, 21B active per token and a 256K-token context window. It is a text model that combines fast and slow thinking, with selectable reasoning effort, and it supports tool calling. It is built for agentic work, coding, office tasks, financial modeling, frontend design and game development, and is released under Apache 2.0."},{"id":"z-ai/glm-4.5-flash:free","routeId":"glm-4.5-flash","features":["streaming","tool-calling","free"],"provider":"zai","modalities":["text"],"moderation":"unknown","displayName":"GLM 4.5 Flash","pricingNote":"Free variant: $0 for every token, with no AnonRouter fee. Limited shared capacity; never falls back to a paid route.","availability":"available","privacyLevel":"anonymous","privacyNotes":["The serving provider can see prompts and responses, including anything in them that identifies you, and may retain them or use them to improve its models.","Do not send sensitive or personal information to a free model."],"providerName":"Z.ai","routingModes":["anonrouter-hosted"],"contextTokens":65536,"privacySummary":"You stay anonymous: the provider receives the request from AnonRouter, with no account details, IP address or user identifier of yours.","maxOutputTokens":8192,"primaryModality":"text","providerRouteId":"zai/glm-4-5-flash-free","shortDescription":"Free access to GLM 4.5 Flash on limited shared capacity. Anonymous route; account opt-in required.","sourceReferences":[],"inputPriceUsdPerMillion":0,"outputPriceUsdPerMillion":0,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-21","callable":true,"operationalAvailability":"available","free":{"baseModelId":"z-ai/glm-4.5-flash","promotion":"limited-shared-capacity"}},{"id":"qwen/qwen-3.6-35b-a3b-fp8","routeId":"e2ee-qwen3-6-35b-a3b","features":["streaming","tool-calling","reasoning","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-05-20","displayName":"Qwen 3.6 35B A3B FP8","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"e2ee","privacyNotes":["The client encrypts prompts before relay and only the verified enclave it encrypted to can decrypt them.","On some routes that enclave is a verified gateway rather than the machine running the model, and it forwards the prompt onward after decrypting it.","E2EE requires attestation verification, encrypted messages, E2EE headers, and response decryption."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":32000,"privacySummary":"End-to-end encrypted inference","maxOutputTokens":4096,"primaryModality":"text","providerRouteId":"qwen/qwen-3.6-35b-a3b-fp8-e2ee","shortDescription":"Qwen 3.6 35B A3B FP8 running in a Trusted Execution Environment (TEE). A fast mixture-of-experts model with ~3B active parameters per token. Hardware attestation evidence is available for independent…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8","label":"Model source"}],"inputPriceUsdPerMillion":0.182,"outputPriceUsdPerMillion":1.18,"cacheReadPriceUsdPerMillion":0.06,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"unavailable","description":"Qwen 3.6 35B A3B FP8 running in a Trusted Execution Environment (TEE). A fast mixture-of-experts model with ~3B active parameters per token. Hardware attestation evidence is available for independent verification of enclave identity and configuration."},{"id":"black-forest-labs/flux-3-max-i2v","routeId":"flux-3-max-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-10-16","displayName":"Flux 3 Max","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"black-forest-labs/flux-3-max-i2v","outputPriceLabel":"Varies","shortDescription":"Flux 3 Max is a video generation model. Photorealistic, high-detail output with excellent typography and layout.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Flux 3 Max is a video generation model. Photorealistic, high-detail output with excellent typography and layout."},{"id":"black-forest-labs/flux-3-max-t2v","routeId":"flux-3-max-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-10-16","displayName":"Flux 3 Max","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"black-forest-labs/flux-3-max-t2v","outputPriceLabel":"Varies","shortDescription":"Flux 3 Max is a video generation model. Photorealistic, high-detail output with excellent typography and layout.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Flux 3 Max is a video generation model. Photorealistic, high-detail output with excellent typography and layout."},{"id":"bytedance/seedance-2.5-us-i2v","routeId":"seedance-2-5-us-image-to-video-private","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-09-28","statusNote":"Venice removes this route on 2026-10-28; replacement: seedance-2-5-image-to-video-basic.","displayName":"Seedance 2.5 US","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"deprecated","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.5-us-i2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.5 US is a separately listed release of Seedance 2.5, ByteDance Seed's audio-video joint generation model that produces up to 30 seconds of video with synchronized audio in one pass. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.5 US is a separately listed release of Seedance 2.5, ByteDance Seed's audio-video joint generation model that produces up to 30 seconds of video with synchronized audio in one pass. This variant animates a still image guided by a text prompt."},{"id":"bytedance/seedance-2.5-us-r2v","routeId":"seedance-2-5-us-reference-to-video-private","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-09-28","statusNote":"Venice removes this route on 2026-10-28; replacement: seedance-2-5-reference-to-video-basic.","displayName":"Seedance 2.5 US R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"deprecated","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.5-us-r2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.5 US is a separately listed release of Seedance 2.5, ByteDance Seed's audio-video joint generation model that produces up to 30 seconds of video with synchronized audio in one pass. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.5 US is a separately listed release of Seedance 2.5, ByteDance Seed's audio-video joint generation model that produces up to 30 seconds of video with synchronized audio in one pass. This reference-to-video variant uses reference images, video clips and audio to carry characters, framing and camera language into a new clip."},{"id":"bytedance/seedance-2.5-us-t2v","routeId":"seedance-2-5-us-text-to-video-private","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-09-28","statusNote":"Venice removes this route on 2026-10-28; replacement: seedance-2-5-text-to-video-basic.","displayName":"Seedance 2.5 US","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"deprecated","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.5-us-t2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.5 US is a separately listed release of Seedance 2.5, ByteDance Seed's audio-video joint generation model that produces up to 30 seconds of video with synchronized audio in one pass. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.5 US is a separately listed release of Seedance 2.5, ByteDance Seed's audio-video joint generation model that produces up to 30 seconds of video with synchronized audio in one pass. This variant generates video with audio from a text prompt."},{"id":"character-ai/ovi","routeId":"ovi-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2025-09-25","displayName":"Ovi","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/ovi","outputPriceLabel":"Varies","shortDescription":"Ovi is Character.AI's open-weight audio-video model, an 11B-parameter twin-backbone design that fuses a video branch and an audio branch to generate synchronized video and sound. This variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/chetwinlow1/Ovi","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Ovi is Character.AI's open-weight audio-video model, an 11B-parameter twin-backbone design that fuses a video branch and an audio branch to generate synchronized video and sound. This variant animates a source image guided by a text prompt into a 5 or 10 second clip at 24 fps."},{"id":"deepseek/deepseek-v4.1-flash-1017-uncensored","routeId":"deepseek-v4-1-flash-1017-uncensored","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"uncensored","releasedAt":"2026-10-27","displayName":"DeepSeek V4.1 Flash 1017 Uncensored","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"deepseek/deepseek-v4.1-flash-1017-uncensored","shortDescription":"DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8","label":"Model source"}],"inputPriceUsdPerMillion":0.33,"outputPriceUsdPerMillion":1.32,"cacheReadPriceUsdPerMillion":0.00825,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails."},{"id":"fireredteam/firered-image-edit","routeId":"firered-image-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-03-25","displayName":"FireRed Image Edit","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/firered","outputPriceLabel":"$0.04/edit","shortDescription":"FireRed Image Edit is an open-weight, general-purpose image editing model from FireRedTeam, released under Apache 2.0. It edits an existing image from a text instruction, with a focus on identity…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"FireRed Image Edit is an open-weight, general-purpose image editing model from FireRedTeam, released under Apache 2.0. It edits an existing image from a text instruction, with a focus on identity consistency, text-style preservation, old photo restoration and multi-image edits such as virtual try-on."},{"id":"krea/krea-2-turbo","routeId":"krea-2-turbo","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-30","displayName":"Krea 2 Turbo","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"krea/krea-2-turbo","outputPriceLabel":"from $0.04/image","shortDescription":"Krea 2 Turbo is a distilled, faster variant of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. It generates images from a text prompt for…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/krea/Krea-2-Turbo","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Krea 2 Turbo is a distilled, faster variant of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. It generates images from a text prompt for quick, low-cost iteration on expressive illustrations, and works with style references, moodboards and LoRAs."},{"id":"meituan/longcat-distilled-i2v","routeId":"longcat-distilled-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2025-12-04","displayName":"LongCat-Video Distilled","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"meituan/longcat-distilled-i2v","outputPriceLabel":"Varies","shortDescription":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This distilled…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/meituan-longcat/LongCat-Video","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This distilled variant samples in fewer steps for faster generation and animates a source image guided by a text prompt."},{"id":"meituan/longcat-distilled-t2v","routeId":"longcat-distilled-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2025-12-04","displayName":"LongCat-Video Distilled","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"meituan/longcat-distilled-t2v","outputPriceLabel":"Varies","shortDescription":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This distilled…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/meituan-longcat/LongCat-Video","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This distilled variant samples in fewer steps for faster generation and creates video from a text prompt."},{"id":"meituan/longcat-full-quality-i2v","routeId":"longcat-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2025-12-04","displayName":"LongCat-Video Full Quality","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"meituan/longcat-full-quality-i2v","outputPriceLabel":"Varies","shortDescription":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/meituan-longcat/LongCat-Video","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This full-quality variant uses the standard, non-distilled sampling path and animates a source image guided by a text prompt."},{"id":"meituan/longcat-full-quality-t2v","routeId":"longcat-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2025-12-04","displayName":"LongCat-Video Full Quality","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"meituan/longcat-full-quality-t2v","outputPriceLabel":"Varies","shortDescription":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/meituan-longcat/LongCat-Video","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LongCat-Video is the Meituan LongCat team's open-weight 13.6B-parameter video model, which handles text-to-video, image-to-video and video continuation in one model at 720p and 30 fps. This full-quality variant uses the standard, non-distilled sampling path and creates video from a text prompt."},{"id":"minimax/minimax-h3-max-i2v","routeId":"minimax-h3-max-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-27","displayName":"MiniMax H3 Max","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-max-i2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Max is a post-trained version of MiniMax's open-weight H3 video model, tuned for prompt adherence, visual quality and fast generation while keeping H3's joint audio and video output. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Max is a post-trained version of MiniMax's open-weight H3 video model, tuned for prompt adherence, visual quality and fast generation while keeping H3's joint audio and video output. This variant animates a first-frame image, optionally with a last frame, guided by a text prompt."},{"id":"minimax/minimax-h3-max-multi-angle","routeId":"minimax-h3-max-multi-angle","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-09-12","displayName":"MiniMax H3 Max Multi-Angle","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-max-multi-angle","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Max Multi-Angle is a camera-control mode of MiniMax H3 Max, a post-trained version of MiniMax's open-weight H3 video model. It turns a single still image into a short video by moving the…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Max Multi-Angle is a camera-control mode of MiniMax H3 Max, a post-trained version of MiniMax's open-weight H3 video model. It turns a single still image into a short video by moving the camera through keyframed angles and distances while the scene stays still."},{"id":"minimax/minimax-h3-max-r2v","routeId":"minimax-h3-max-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-27","displayName":"MiniMax H3 Max R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-max-r2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Max is a post-trained version of MiniMax's open-weight H3 video model, tuned for prompt adherence, visual quality and fast generation while keeping H3's joint audio and video output. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Max is a post-trained version of MiniMax's open-weight H3 video model, tuned for prompt adherence, visual quality and fast generation while keeping H3's joint audio and video output. This variant generates video from reference images and other reference media plus a text prompt."},{"id":"minimax/minimax-h3-max-recast","routeId":"minimax-h3-max-recast","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-10-07","displayName":"MiniMax H3 Max Recast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-max-recast","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Max Recast is a video-to-video mode of MiniMax H3 Max, a post-trained version of MiniMax's open-weight H3 video model. It replaces the people in an existing clip with identities from…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Max Recast is a video-to-video mode of MiniMax H3 Max, a post-trained version of MiniMax's open-weight H3 video model. It replaces the people in an existing clip with identities from reference photos, keeping the original motion, camera work and audio."},{"id":"minimax/minimax-h3-max-t2v","routeId":"minimax-h3-max-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-08-27","displayName":"MiniMax H3 Max","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-max-t2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Max is a post-trained version of MiniMax's open-weight H3 video model, tuned for prompt adherence, visual quality and fast generation while keeping H3's joint audio and video output. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Max is a post-trained version of MiniMax's open-weight H3 video model, tuned for prompt adherence, visual quality and fast generation while keeping H3's joint audio and video output. This variant generates video from a text prompt."},{"id":"minimax/minimax-h3-max-turbo-i2v","routeId":"minimax-h3-max-turbo-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-09-02","displayName":"MiniMax H3 Max Turbo","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-max-turbo-i2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Max Turbo is a faster version of MiniMax H3 Max, itself a post-trained version of MiniMax's open-weight H3 video model. This variant animates a first-frame image into a video with audio…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Max Turbo is a faster version of MiniMax H3 Max, itself a post-trained version of MiniMax's open-weight H3 video model. This variant animates a first-frame image into a video with audio guided by a text prompt."},{"id":"minimax/minimax-h3-max-turbo-t2v","routeId":"minimax-h3-max-turbo-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-09-02","displayName":"MiniMax H3 Max Turbo","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-max-turbo-t2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Max Turbo is a faster version of MiniMax H3 Max, itself a post-trained version of MiniMax's open-weight H3 video model. This variant generates video with audio from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Max Turbo is a faster version of MiniMax H3 Max, itself a post-trained version of MiniMax's open-weight H3 video model. This variant generates video with audio from a text prompt."},{"id":"nvidia/parakeet-asr","routeId":"nvidia/parakeet-tdt-0.6b-v3","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2025-10-10","displayName":"Parakeet TDT 0.6B v3","pricingNote":"Priced at $0.0001 per second of input audio.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$0.006/min","primaryModality":"audio","providerRouteId":"nvidia/parakeet-asr","outputPriceLabel":"–","shortDescription":"Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech recognition model with a FastConformer encoder and TDT decoder. It transcribes 25 European languages with automatic language…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech recognition model with a FastConformer encoder and TDT decoder. It transcribes 25 European languages with automatic language detection, punctuation and capitalization, and word and segment timestamps."},{"id":"openai/whisper-large-v3","routeId":"openai/whisper-large-v3","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2025-01-15","displayName":"Whisper Large V3","pricingNote":"Priced at $0.0001 per second of input audio.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$0.006/min","primaryModality":"audio","providerRouteId":"openai/whisper-large-v3","outputPriceLabel":"–","shortDescription":"Whisper Large V3 is OpenAI's open-weight speech recognition model with about 1.55B parameters, trained on more than 5 million hours of audio. It transcribes speech in 99 languages and can translate…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/openai/whisper-large-v3","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Whisper Large V3 is OpenAI's open-weight speech recognition model with about 1.55B parameters, trained on more than 5 million hours of audio. It transcribes speech in 99 languages and can translate speech into English, and compared with Large V2 it uses 128 Mel frequency bins and adds Cantonese."},{"id":"openai/wizper-whisper-v3","routeId":"fal-ai/wizper","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"Wizper (Whisper v3)","pricingNote":"Priced at $0.0001 per second of input audio.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"$0.006/min","primaryModality":"audio","providerRouteId":"openai/wizper-whisper-v3","outputPriceLabel":"–","shortDescription":"Wizper is a faster serving variant of OpenAI's Whisper Large V3 speech recognition model. It transcribes speech in many languages and can translate speech into English, keeping the underlying Whisper…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/openai/whisper-large-v3","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wizper is a faster serving variant of OpenAI's Whisper Large V3 speech recognition model. It transcribes speech in many languages and can translate speech into English, keeping the underlying Whisper V3 model's language coverage."},{"id":"qwen/qwen-edit-uncensored","routeId":"qwen-edit-uncensored","features":[],"provider":"venice","modalities":["image"],"moderation":"uncensored","releasedAt":"2026-06-04","displayName":"Qwen Edit Uncensored","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-edit-uncensored","outputPriceLabel":"$0.04/edit","shortDescription":"Qwen Edit Uncensored is an image editing model based on the Qwen-Image-Edit family from Alibaba's Qwen team, in a variant with fewer content restrictions. It edits an existing image from a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen Edit Uncensored is an image editing model based on the Qwen-Image-Edit family from Alibaba's Qwen team, in a variant with fewer content restrictions. It edits an existing image from a text instruction."},{"id":"venice/clef-system-one","routeId":"clef-api","features":[],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2026-10-06","statusNote":"Beta","displayName":"Clef (System One)","availability":"preview","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","primaryModality":"text","providerRouteId":"venice/clef-system-one","shortDescription":"Clef (System One) is a text model.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Clef (System One) is a text model."},{"id":"venice/upscaler","routeId":"upscaler","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-04-12","displayName":"Upscaler","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/upscaler","outputPriceLabel":"$0.01/upscale","shortDescription":"Upscaler is an image upscaling model that takes an existing image and returns a higher-resolution version, with an optional enhancement step that can add new detail.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Upscaler is an image upscaling model that takes an existing image and returns a higher-resolution version, with an optional enhancement step that can add new detail."},{"id":"x-ai/grok-imagine","routeId":"grok-imagine-image","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-04-09","displayName":"Grok Imagine","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"x-ai/grok-imagine","outputPriceLabel":"from $0.03/image","shortDescription":"Grok Imagine is xAI's first-generation (1.0) image model, taking text and image input and producing images. This variant generates images from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine is xAI's first-generation (1.0) image model, taking text and image input and producing images. This variant generates images from a text prompt."},{"id":"x-ai/grok-imagine-1.5-i2v","routeId":"grok-imagine-1-5-image-to-video-private","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-05-31","displayName":"Grok Imagine 1.5","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-1.5-i2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine 1.5 is xAI's updated video generation model, which generates clips of up to 15 seconds from text and image input. This variant animates a still image guided by a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine 1.5 is xAI's updated video generation model, which generates clips of up to 15 seconds from text and image input. This variant animates a still image guided by a text prompt."},{"id":"x-ai/grok-imagine-1.5-lite-i2v","routeId":"grok-imagine-1-5-lite-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-09-30","displayName":"Grok Imagine 1.5 Lite","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-1.5-lite-i2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine 1.5 Lite is a lighter version of xAI's Grok Imagine 1.5 video generation model that takes text and image input. This variant animates a still image guided by a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine 1.5 Lite is a lighter version of xAI's Grok Imagine 1.5 video generation model that takes text and image input. This variant animates a still image guided by a text prompt."},{"id":"x-ai/grok-imagine-1.5-lite-t2v","routeId":"grok-imagine-1-5-lite-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-09-30","displayName":"Grok Imagine 1.5 Lite","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-1.5-lite-t2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine 1.5 Lite is a lighter version of xAI's Grok Imagine 1.5 video generation model that takes text and image input. This variant generates video from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine 1.5 Lite is a lighter version of xAI's Grok Imagine 1.5 video generation model that takes text and image input. This variant generates video from a text prompt."},{"id":"x-ai/grok-imagine-1.5-r2v","routeId":"grok-imagine-1-5-reference-to-video-private","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-07-29","displayName":"Grok Imagine 1.5 R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-1.5-r2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine 1.5 is xAI's updated video generation model, which generates clips of up to 15 seconds from text and image input. This variant guides generation with up to 14 reference images and 3…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine 1.5 is xAI's updated video generation model, which generates clips of up to 15 seconds from text and image input. This variant guides generation with up to 14 reference images and 3 voice references plus a text prompt."},{"id":"x-ai/grok-imagine-1.5-t2v","routeId":"grok-imagine-1-5-text-to-video-private","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-05-31","displayName":"Grok Imagine 1.5","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-1.5-t2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine 1.5 is xAI's updated video generation model, which generates clips of up to 15 seconds from text and image input. This variant generates video from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine 1.5 is xAI's updated video generation model, which generates clips of up to 15 seconds from text and image input. This variant generates video from a text prompt."},{"id":"x-ai/grok-imagine-2.0","routeId":"grok-imagine-image-2-0","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-08-11","displayName":"Grok Imagine 2.0","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"x-ai/grok-imagine-2.0","outputPriceLabel":"from $0.07/image","shortDescription":"Grok Imagine Image 2.0 is xAI's second-generation image model, built for close instruction following and designer-style typography and layout, so dense multi-part visuals and small text stay sharp.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine Image 2.0 is xAI's second-generation image model, built for close instruction following and designer-style typography and layout, so dense multi-part visuals and small text stay sharp. This variant generates images from a text prompt."},{"id":"x-ai/grok-imagine-2.0-edit","routeId":"grok-imagine-image-2-0-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-08-11","displayName":"Grok Imagine 2.0","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"x-ai/grok-imagine-2.0-edit","outputPriceLabel":"from $0.07/edit","shortDescription":"Grok Imagine Image 2.0 is xAI's second-generation image model, built for close instruction following and designer-style typography and layout, so dense multi-part visuals and small text stay sharp.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine Image 2.0 is xAI's second-generation image model, built for close instruction following and designer-style typography and layout, so dense multi-part visuals and small text stay sharp. This variant edits images from a text instruction, including region-only edits and multi-reference edits with up to five input images."},{"id":"x-ai/grok-imagine-edit","routeId":"grok-imagine-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-01-29","displayName":"Grok Imagine","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"x-ai/grok-imagine-edit","outputPriceLabel":"from $0.03/edit","shortDescription":"Grok Imagine is xAI's first-generation (1.0) image model, taking text and image input and producing images. This variant edits an existing image from a text instruction.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine is xAI's first-generation (1.0) image model, taking text and image input and producing images. This variant edits an existing image from a text instruction."},{"id":"x-ai/grok-imagine-high-quality","routeId":"grok-imagine-quality-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-05-08","statusNote":"Venice removes this route on 2026-11-02; replacement: grok-imagine-image-2-0-edit.","displayName":"Grok Imagine Quality","pricingNote":"Price varies by resolution or quality tier.","availability":"deprecated","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"x-ai/grok-imagine-high-quality","outputPriceLabel":"from $0.06/edit","shortDescription":"Grok Imagine Quality is xAI's quality-mode image model, aimed at realism, fine detail, clean multilingual text and tighter prompt following. This variant edits images from a prompt and reference…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine Quality is xAI's quality-mode image model, aimed at realism, fine detail, clean multilingual text and tighter prompt following. This variant edits images from a prompt and reference images, keeping people and products consistent."},{"id":"x-ai/grok-imagine-high-quality-sota","routeId":"grok-imagine-image-quality","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-05-07","statusNote":"Venice removes this route on 2026-11-02; replacement: grok-imagine-image-2-0.","displayName":"Grok Imagine Quality","pricingNote":"Price varies by resolution or quality tier.","availability":"deprecated","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"x-ai/grok-imagine-high-quality-sota","outputPriceLabel":"from $0.06/image","shortDescription":"Grok Imagine Quality is xAI's quality-mode image model, aimed at realism, fine detail, clean multilingual text and tighter prompt following. This variant generates images from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine Quality is xAI's quality-mode image model, aimed at realism, fine detail, clean multilingual text and tighter prompt following. This variant generates images from a text prompt."},{"id":"x-ai/grok-imagine-i2v","routeId":"grok-imagine-image-to-video-private","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-15","displayName":"Grok Imagine","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-i2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant animates a still image guided by a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant animates a still image guided by a text prompt."},{"id":"x-ai/grok-imagine-r2v","routeId":"grok-imagine-reference-to-video-private","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-15","displayName":"Grok Imagine R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-r2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant generates video guided by reference images and a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant generates video guided by reference images and a text prompt."},{"id":"x-ai/grok-imagine-t2v","routeId":"grok-imagine-text-to-video-private","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-13","displayName":"Grok Imagine","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-t2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant generates video from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant generates video from a text prompt."},{"id":"x-ai/grok-imagine-v2v","routeId":"grok-imagine-video-to-video-private","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-15","displayName":"Grok Imagine Edit","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Private routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"x-ai/grok-imagine-v2v","outputPriceLabel":"Varies","shortDescription":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant modifies an existing video according to a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Imagine is xAI's video generation model, which takes text, image and video input and produces video. This variant modifies an existing video according to a text prompt."},{"id":"abliteration-ai/abliterated-model","routeId":"abliterated-model","features":["streaming","tool-calling","vision","reasoning","json-schema","prompt-caching"],"provider":"abliteration","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Abliterated Model","pricingNote":"Provider list pricing in USD per 1M tokens.","availability":"available","privacyLevel":"private","privacyNotes":["AnonRouter does not forward your AnonRouter account credentials to this provider.","abliteration.ai publishes that prompts and completions are processed in memory, are never stored by default and are never used for training. AnonRouter has confirmed this no-logging practice with abliteration.ai.","This route does not run in a trusted execution environment and is not end-to-end encrypted: abliteration.ai can read prompts and outputs in the clear while it processes them."],"providerName":"abliteration.ai","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Private route. abliteration.ai processes prompts and outputs in memory and, by default, does not store them or use them for training. It can read content while serving the request.","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"abliteration/abliterated-model","shortDescription":"Abliterated Model is Abliteration AI's general-purpose abliterated model, with refusal behavior removed. It takes text and image input, supports tool calling, structured outputs and configurable…","sourceReferences":[],"inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":3,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-24","callable":false,"operationalAvailability":"unavailable","description":"Abliterated Model is Abliteration AI's general-purpose abliterated model, with refusal behavior removed. It takes text and image input, supports tool calling, structured outputs and configurable reasoning that can be turned off, and has a 262K token context window."},{"id":"ace-step/ace-step-1.5","routeId":"ace-step-15","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-23","displayName":"ACE-Step 1.5","pricingNote":"Price scales with track duration.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"ace-step/ace-step-1.5","outputPriceLabel":"from $0.03/track","shortDescription":"Feature-rich song generation with optional lyrics and detailed musical controls.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/ACE-Step/Ace-Step1.5","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Feature-rich song generation with optional lyrics and detailed musical controls."},{"id":"alibaba/happyhorse-1.0-edit","routeId":"happyhorse-1-0-video-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-27","displayName":"HappyHorse 1.0 Edit","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/happyhorse-1.0-edit","outputPriceLabel":"Varies","shortDescription":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant edits an existing video according to a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant edits an existing video according to a text instruction."},{"id":"alibaba/happyhorse-1.0-i2v","routeId":"happyhorse-1-0-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-25","displayName":"HappyHorse 1.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/happyhorse-1.0-i2v","outputPriceLabel":"Varies","shortDescription":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant animates a source image guided by a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant animates a source image guided by a text prompt."},{"id":"alibaba/happyhorse-1.0-reference","routeId":"happyhorse-1-0-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-27","displayName":"HappyHorse 1.0 Reference","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/happyhorse-1.0-reference","outputPriceLabel":"Varies","shortDescription":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant generates video from reference images and a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant generates video from reference images and a text prompt, keeping subjects consistent."},{"id":"alibaba/happyhorse-1.0-t2v","routeId":"happyhorse-1-0-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-24","displayName":"HappyHorse 1.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/happyhorse-1.0-t2v","outputPriceLabel":"Varies","shortDescription":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant generates video from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"HappyHorse 1.0 is a video generation model from Alibaba, developed by the AI Innovation Division of its Alibaba Token Hub business group. This variant generates video from a text prompt."},{"id":"alibaba/happyhorse-1.1-i2v","routeId":"happyhorse-1-1-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-22","displayName":"HappyHorse 1.1","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/happyhorse-1.1-i2v","outputPriceLabel":"Varies","shortDescription":"HappyHorse 1.1 is an update to Alibaba's HappyHorse video generation model, with improved motion, subject consistency, prompt adherence, visual quality and audio generation. This variant animates a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"HappyHorse 1.1 is an update to Alibaba's HappyHorse video generation model, with improved motion, subject consistency, prompt adherence, visual quality and audio generation. This variant animates a source image guided by a text prompt."},{"id":"alibaba/happyhorse-1.1-reference","routeId":"happyhorse-1-1-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-22","displayName":"HappyHorse 1.1 Reference","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/happyhorse-1.1-reference","outputPriceLabel":"Varies","shortDescription":"HappyHorse 1.1 is an update to Alibaba's HappyHorse video generation model, with improved motion, subject consistency, prompt adherence, visual quality and audio generation. This variant generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"HappyHorse 1.1 is an update to Alibaba's HappyHorse video generation model, with improved motion, subject consistency, prompt adherence, visual quality and audio generation. This variant generates video from reference images and a text prompt, keeping subjects consistent."},{"id":"alibaba/happyhorse-1.1-t2v","routeId":"happyhorse-1-1-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-06-22","displayName":"HappyHorse 1.1","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/happyhorse-1.1-t2v","outputPriceLabel":"Varies","shortDescription":"HappyHorse 1.1 is an update to Alibaba's HappyHorse video generation model, with improved motion, subject consistency, prompt adherence, visual quality and audio generation. This variant generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"HappyHorse 1.1 is an update to Alibaba's HappyHorse video generation model, with improved motion, subject consistency, prompt adherence, visual quality and audio generation. This variant generates video from a text prompt."},{"id":"alibaba/wan-2.2-enhanced","routeId":"wan-2-2-enhanced-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-14","displayName":"Wan 2.2 Enhanced","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.2-enhanced","outputPriceLabel":"Varies","shortDescription":"Wan 2.2 Enhanced is an image-to-video variant listed under Wan 2.2, Alibaba's open-weight video generation family that introduced a Mixture-of-Experts design. It animates a still image, guided by a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.2 Enhanced is an image-to-video variant listed under Wan 2.2, Alibaba's open-weight video generation family that introduced a Mixture-of-Experts design. It animates a still image, guided by a text prompt, into a short video clip."},{"id":"alibaba/wan-2.5-preview-i2v","routeId":"wan-2.5-preview-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2025-09-25","displayName":"Wan 2.5 Preview","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.5-preview-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.5 Preview is Alibaba's Wan video generation model that generates synchronized audio with the video, in 5 or 10 second clips at up to 1080p. This image-to-video variant animates a still image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.5 Preview is Alibaba's Wan video generation model that generates synchronized audio with the video, in 5 or 10 second clips at up to 1080p. This image-to-video variant animates a still image guided by a text prompt."},{"id":"alibaba/wan-2.5-preview-t2v","routeId":"wan-2.5-preview-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2025-09-25","displayName":"Wan 2.5 Preview","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.5-preview-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.5 Preview is Alibaba's Wan video generation model that generates synchronized audio with the video, in 5 or 10 second clips at up to 1080p. This text-to-video variant generates a clip from a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.5 Preview is Alibaba's Wan video generation model that generates synchronized audio with the video, in 5 or 10 second clips at up to 1080p. This text-to-video variant generates a clip from a text prompt."},{"id":"alibaba/wan-2.6-flash","routeId":"wan-2.6-flash-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-01-19","displayName":"Wan 2.6 Flash","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.6-flash","outputPriceLabel":"Varies","shortDescription":"Wan 2.6 Flash is the fast-generation image-to-video version of Wan 2.6, Alibaba's Wan video generation model. It animates a still image, guided by a text prompt, into a clip of 2 to 15 seconds at…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.6 Flash is the fast-generation image-to-video version of Wan 2.6, Alibaba's Wan video generation model. It animates a still image, guided by a text prompt, into a clip of 2 to 15 seconds at 720p or 1080p with generated audio."},{"id":"alibaba/wan-2.6-i2v","routeId":"wan-2.6-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2025-12-16","displayName":"Wan 2.6","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.6-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.6 is Alibaba's Wan video generation model with synchronized audio and multi-shot storytelling, producing clips of 2 to 15 seconds at 720p or 1080p. This image-to-video variant animates a still…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.6 is Alibaba's Wan video generation model with synchronized audio and multi-shot storytelling, producing clips of 2 to 15 seconds at 720p or 1080p. This image-to-video variant animates a still image guided by a text prompt."},{"id":"alibaba/wan-2.6-t2v","routeId":"wan-2.6-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2025-12-16","displayName":"Wan 2.6","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.6-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.6 is Alibaba's Wan video generation model with synchronized audio and multi-shot storytelling, producing clips of 2 to 15 seconds at 720p or 1080p. This text-to-video variant generates a clip…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.6 is Alibaba's Wan video generation model with synchronized audio and multi-shot storytelling, producing clips of 2 to 15 seconds at 720p or 1080p. This text-to-video variant generates a clip from a text prompt."},{"id":"alibaba/wan-2.7-edit","routeId":"wan-2-7-video-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-04-02","displayName":"Wan 2.7 Edit","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.7-edit","outputPriceLabel":"Varies","shortDescription":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This editing variant takes an…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This editing variant takes an existing video and a natural-language instruction and returns an edited clip of up to 10 seconds."},{"id":"alibaba/wan-2.7-enhanced-i2v","routeId":"wan-2-7-enhanced-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-05-09","displayName":"Wan 2.7 Enhanced","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.7-enhanced-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.7 Enhanced is a variant listed under Wan 2.7, Alibaba's Wan video generation family. This image-to-video version animates a still image, guided by a text prompt, into a short clip at 720p or…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.7 Enhanced is a variant listed under Wan 2.7, Alibaba's Wan video generation family. This image-to-video version animates a still image, guided by a text prompt, into a short clip at 720p or 1080p."},{"id":"alibaba/wan-2.7-enhanced-t2v","routeId":"wan-2-7-enhanced-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-06-03","displayName":"Wan 2.7 Enhanced","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.7-enhanced-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.7 Enhanced is a variant listed under Wan 2.7, Alibaba's Wan video generation family. This text-to-video version generates a short clip at 720p or 1080p from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.7 Enhanced is a variant listed under Wan 2.7, Alibaba's Wan video generation family. This text-to-video version generates a short clip at 720p or 1080p from a text prompt."},{"id":"alibaba/wan-2.7-i2v","routeId":"wan-2-7-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-04-02","displayName":"Wan 2.7","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.7-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This image-to-video variant animates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This image-to-video variant animates a first frame, or a first and last frame, into a clip of 2 to 15 seconds, and can also continue an existing clip."},{"id":"alibaba/wan-2.7-pro-edit","routeId":"wan-2-7-pro-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-04-23","displayName":"Wan 2.7 Pro Edit","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"alibaba/wan-2.7-pro-edit","outputPriceLabel":"$0.09/edit","shortDescription":"Wan 2.7 Pro is the high-fidelity tier of Wan 2.7, Alibaba's unified image generation and editing model family, with a focus on text rendering, brand colors and consistent multi-image output. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.7 Pro is the high-fidelity tier of Wan 2.7, Alibaba's unified image generation and editing model family, with a focus on text rendering, brand colors and consistent multi-image output. This variant edits an input image from a text instruction."},{"id":"alibaba/wan-2.7-reference","routeId":"wan-2-7-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-04-02","displayName":"Wan 2.7 Reference","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.7-reference","outputPriceLabel":"Varies","shortDescription":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This reference-to-video variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This reference-to-video variant combines up to five reference images or video clips, plus an optional voice sample for timbre cloning, into a new clip of 2 to 10 seconds."},{"id":"alibaba/wan-2.7-t2v","routeId":"wan-2-7-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-04-02","displayName":"Wan 2.7","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-2.7-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This text-to-video variant generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 2.7 is Alibaba's Wan video generation family covering text-to-video, image-to-video, reference-to-video and instruction-based video editing at 720p or 1080p. This text-to-video variant generates a clip of 2 to 15 seconds with synchronized audio from a text prompt."},{"id":"alibaba/wan-3.0-i2v","routeId":"wan-3-0-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-01","displayName":"Wan 3.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 is Alibaba's all-in-one Wan video generation model, producing single-shot or multi-shot clips of up to 30 seconds at up to 1080p with natively generated dialogue, sound effects and music.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 is Alibaba's all-in-one Wan video generation model, producing single-shot or multi-shot clips of up to 30 seconds at up to 1080p with natively generated dialogue, sound effects and music. This image-to-video variant animates a first frame, or a first and last frame, guided by a text prompt."},{"id":"alibaba/wan-3.0-prime-i2v","routeId":"wan-3-0-prime-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-24","displayName":"Wan 3.0 Prime","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-prime-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Prime is the speed-optimized version of Wan 3.0, Alibaba's all-in-one video generation model, producing clips of up to 30 seconds at up to 1080p with native audio. This image-to-video variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Prime is the speed-optimized version of Wan 3.0, Alibaba's all-in-one video generation model, producing clips of up to 30 seconds at up to 1080p with native audio. This image-to-video variant animates a first frame, or a first and last frame, guided by a text prompt."},{"id":"alibaba/wan-3.0-prime-pro-i2v","routeId":"wan-3-0-prime-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-09-08","displayName":"Wan 3.0 Prime Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-prime-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Prime Pro is a tier listed under Wan 3.0 Prime, the speed-optimized version of Alibaba's all-in-one Wan 3.0 video model, which produces clips of up to 30 seconds with native audio. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Prime Pro is a tier listed under Wan 3.0 Prime, the speed-optimized version of Alibaba's all-in-one Wan 3.0 video model, which produces clips of up to 30 seconds with native audio. This image-to-video variant animates a first frame, or a first and last frame, guided by a text prompt."},{"id":"alibaba/wan-3.0-prime-pro-reference","routeId":"wan-3-0-prime-pro-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-09-08","displayName":"Wan 3.0 Prime Pro Reference","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-prime-pro-reference","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Prime Pro is a tier listed under Wan 3.0 Prime, the speed-optimized version of Alibaba's all-in-one Wan 3.0 video model, which produces clips of up to 30 seconds with native audio. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Prime Pro is a tier listed under Wan 3.0 Prime, the speed-optimized version of Alibaba's all-in-one Wan 3.0 video model, which produces clips of up to 30 seconds with native audio. This reference variant builds a video from reference images, video clips and audio, keeping characters, props and voices consistent."},{"id":"alibaba/wan-3.0-prime-pro-t2v","routeId":"wan-3-0-prime-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-09-08","displayName":"Wan 3.0 Prime Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-prime-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Prime Pro is a tier listed under Wan 3.0 Prime, the speed-optimized version of Alibaba's all-in-one Wan 3.0 video model, which produces clips of up to 30 seconds with native audio. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Prime Pro is a tier listed under Wan 3.0 Prime, the speed-optimized version of Alibaba's all-in-one Wan 3.0 video model, which produces clips of up to 30 seconds with native audio. This text-to-video variant generates a video from a text prompt."},{"id":"alibaba/wan-3.0-prime-reference","routeId":"wan-3-0-prime-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-24","displayName":"Wan 3.0 Prime Reference","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-prime-reference","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Prime is the speed-optimized version of Wan 3.0, Alibaba's all-in-one video generation model, producing clips of up to 30 seconds at up to 1080p with native audio. This reference variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Prime is the speed-optimized version of Wan 3.0, Alibaba's all-in-one video generation model, producing clips of up to 30 seconds at up to 1080p with native audio. This reference variant builds a video from reference images, video clips and audio, keeping characters, props and voices consistent."},{"id":"alibaba/wan-3.0-prime-t2v","routeId":"wan-3-0-prime-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-08-24","displayName":"Wan 3.0 Prime","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-prime-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Prime is the speed-optimized version of Wan 3.0, Alibaba's all-in-one video generation model, producing clips of up to 30 seconds at up to 1080p with native audio. This text-to-video variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Prime is the speed-optimized version of Wan 3.0, Alibaba's all-in-one video generation model, producing clips of up to 30 seconds at up to 1080p with native audio. This text-to-video variant generates a video from a text prompt."},{"id":"alibaba/wan-3.0-pro-i2v","routeId":"wan-3-0-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-09-08","displayName":"Wan 3.0 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Pro is a tier listed under Wan 3.0, Alibaba's all-in-one video generation model that produces clips of up to 30 seconds with native audio. This image-to-video variant animates a first frame,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Pro is a tier listed under Wan 3.0, Alibaba's all-in-one video generation model that produces clips of up to 30 seconds with native audio. This image-to-video variant animates a first frame, or a first and last frame, guided by a text prompt."},{"id":"alibaba/wan-3.0-pro-reference","routeId":"wan-3-0-pro-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-09-08","displayName":"Wan 3.0 Pro Reference","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-pro-reference","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Pro is a tier listed under Wan 3.0, Alibaba's all-in-one video generation model that produces clips of up to 30 seconds with native audio. This reference variant builds a video from reference…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Pro is a tier listed under Wan 3.0, Alibaba's all-in-one video generation model that produces clips of up to 30 seconds with native audio. This reference variant builds a video from reference images, video clips and audio, keeping characters, props and voices consistent."},{"id":"alibaba/wan-3.0-pro-t2v","routeId":"wan-3-0-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-09-08","displayName":"Wan 3.0 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 Pro is a tier listed under Wan 3.0, Alibaba's all-in-one video generation model that produces clips of up to 30 seconds with native audio. This text-to-video variant generates a video from a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 Pro is a tier listed under Wan 3.0, Alibaba's all-in-one video generation model that produces clips of up to 30 seconds with native audio. This text-to-video variant generates a video from a text prompt."},{"id":"alibaba/wan-3.0-reference","routeId":"wan-3-0-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-01","displayName":"Wan 3.0 Reference","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-reference","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 is Alibaba's all-in-one Wan video generation model, producing single-shot or multi-shot clips of up to 30 seconds at up to 1080p with natively generated dialogue, sound effects and music.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 is Alibaba's all-in-one Wan video generation model, producing single-shot or multi-shot clips of up to 30 seconds at up to 1080p with natively generated dialogue, sound effects and music. This reference variant builds a video from reference images, video clips and audio, keeping characters, props and voices consistent."},{"id":"alibaba/wan-3.0-t2v","routeId":"wan-3-0-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-08-01","displayName":"Wan 3.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"alibaba/wan-3.0-t2v","outputPriceLabel":"Varies","shortDescription":"Wan 3.0 is Alibaba's all-in-one Wan video generation model, producing single-shot or multi-shot clips of up to 30 seconds at up to 1080p with natively generated dialogue, sound effects and music.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Wan 3.0 is Alibaba's all-in-one Wan video generation model, producing single-shot or multi-shot clips of up to 30 seconds at up to 1080p with natively generated dialogue, sound effects and music. This text-to-video variant generates a video from a text prompt."},{"id":"black-forest-labs/flux-2-max-edit","routeId":"flux-2-max-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-01-05","displayName":"FLUX.2 Max","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"black-forest-labs/flux-2-max-edit","outputPriceLabel":"$0.12/edit","shortDescription":"FLUX.2 [max] is the top tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"FLUX.2 [max] is the top tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one architecture. This variant edits an existing image from a text instruction and can combine multiple reference images while keeping characters, products and style consistent."},{"id":"black-forest-labs/flux-3","routeId":"flux-3-image","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-10-01","displayName":"FLUX 3 Image","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"black-forest-labs/flux-3","outputPriceLabel":"from $0.12/image","shortDescription":"FLUX 3 is Black Forest Labs' multimodal flow matching foundation model, trained jointly on images, video and audio. FLUX 3 Image synthesizes and edits images in a wide range of styles, aspect ratios…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"FLUX 3 is Black Forest Labs' multimodal flow matching foundation model, trained jointly on images, video and audio. FLUX 3 Image synthesizes and edits images in a wide range of styles, aspect ratios and resolutions, with multilingual text rendering. This variant generates images from a text prompt."},{"id":"black-forest-labs/flux-3-edit","routeId":"flux-3-image-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-10-01","displayName":"FLUX 3 Image","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"black-forest-labs/flux-3-edit","outputPriceLabel":"from $0.12/edit","shortDescription":"FLUX 3 is Black Forest Labs' multimodal flow matching foundation model, trained jointly on images, video and audio. FLUX 3 Image synthesizes and edits images in a wide range of styles, aspect ratios…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"FLUX 3 is Black Forest Labs' multimodal flow matching foundation model, trained jointly on images, video and audio. FLUX 3 Image synthesizes and edits images in a wide range of styles, aspect ratios and resolutions, with multilingual text rendering. This variant edits an existing image from a text instruction, optionally guided by reference images."},{"id":"black-forest-labs/flux-3-extend","routeId":"flux-3-extend-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-08-04","displayName":"Flux 3 Extend","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"black-forest-labs/flux-3-extend","outputPriceLabel":"Varies","shortDescription":"Flux 3 Extend is a video generation model. Photorealistic, high-detail output with excellent typography and layout.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Flux 3 Extend is a video generation model. Photorealistic, high-detail output with excellent typography and layout."},{"id":"black-forest-labs/flux-3-first-last-frame","routeId":"flux-3-first-last-frame-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-04","displayName":"FLUX 3 Video First-Last Frame","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"black-forest-labs/flux-3-first-last-frame","outputPriceLabel":"Varies","shortDescription":"FLUX 3 Video is the video model in Black Forest Labs' natively multimodal FLUX 3 family, generating clips of up to 20 seconds with native audio. Audio includes dialogue, sound effects and ambient…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"FLUX 3 Video is the video model in Black Forest Labs' natively multimodal FLUX 3 family, generating clips of up to 20 seconds with native audio. Audio includes dialogue, sound effects and ambient sound. This variant generates the motion between a supplied first frame and last frame, guided by a text prompt."},{"id":"black-forest-labs/flux-3-i2v","routeId":"flux-3-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-04","displayName":"FLUX 3 Video","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"black-forest-labs/flux-3-i2v","outputPriceLabel":"Varies","shortDescription":"FLUX 3 Video is the video model in Black Forest Labs' natively multimodal FLUX 3 family, generating clips of up to 20 seconds with native audio. Audio includes dialogue, sound effects and ambient…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"FLUX 3 Video is the video model in Black Forest Labs' natively multimodal FLUX 3 family, generating clips of up to 20 seconds with native audio. Audio includes dialogue, sound effects and ambient sound. This variant animates a starting image guided by a text prompt."},{"id":"black-forest-labs/flux-3-t2v","routeId":"flux-3-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-08-04","displayName":"FLUX 3 Video","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"black-forest-labs/flux-3-t2v","outputPriceLabel":"Varies","shortDescription":"FLUX 3 Video is the video model in Black Forest Labs' natively multimodal FLUX 3 family, generating clips of up to 20 seconds with native audio. Audio includes dialogue, sound effects and ambient…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"FLUX 3 Video is the video model in Black Forest Labs' natively multimodal FLUX 3 family, generating clips of up to 20 seconds with native audio. Audio includes dialogue, sound effects and ambient sound. This variant generates video from a text prompt."},{"id":"bytedance/seed-audio-1.0","routeId":"seed-audio-1-0","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-06-29","displayName":"Seed Audio 1.0","pricingNote":"Priced per second of generated audio.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"venice/seed-audio-1.0","outputPriceLabel":"$0.17/min","shortDescription":"Seed Audio 1.0 is ByteDance Seed's audio creation model that generates speech, sound effects and ambience from a text prompt in one unified framework. It supports more than 20 languages, can follow a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seed Audio 1.0 is ByteDance Seed's audio creation model that generates speech, sound effects and ambience from a text prompt in one unified framework. It supports more than 20 languages, can follow a voice description or an authorized reference sample, controls dialogue timing at 100 ms precision, and produces up to two minutes of audio per pass."},{"id":"bytedance/seedance-1.5-pro-i2v","routeId":"seedance-1-5-pro-image-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-03-20","statusNote":"Venice removes this route on 2026-11-10; replacement: seedance-2-0-mini-image-to-video-basic.","displayName":"Seedance 1.5 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"deprecated","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-1.5-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Seedance 1.5 Pro is ByteDance Seed's joint audio-video generation model, producing video with synchronized voices, spatial sound effects and lip-sync from complex instructions. This variant animates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 1.5 Pro is ByteDance Seed's joint audio-video generation model, producing video with synchronized voices, spatial sound effects and lip-sync from complex instructions. This variant animates a still image guided by a text prompt."},{"id":"bytedance/seedance-1.5-pro-t2v","routeId":"seedance-1-5-pro-text-to-video-basic","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-03-20","statusNote":"Venice removes this route on 2026-11-10; replacement: seedance-2-0-mini-text-to-video-basic.","displayName":"Seedance 1.5 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"deprecated","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-1.5-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Seedance 1.5 Pro is ByteDance Seed's joint audio-video generation model, producing video with synchronized voices, spatial sound effects and lip-sync from complex instructions. This variant generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 1.5 Pro is ByteDance Seed's joint audio-video generation model, producing video with synchronized voices, spatial sound effects and lip-sync from complex instructions. This variant generates video with audio from a text prompt."},{"id":"bytedance/seedance-2.0-fast-i2v","routeId":"seedance-2-0-fast-image-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-01","displayName":"Seedance 2.0 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-fast-i2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0 that keeps its core features, including joint audio-video generation guided by text, image, audio and video inputs. This variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0 that keeps its core features, including joint audio-video generation guided by text, image, audio and video inputs. This variant animates a still image guided by a text prompt."},{"id":"bytedance/seedance-2.0-fast-r2v","routeId":"seedance-2-0-fast-reference-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-01","displayName":"Seedance 2.0 Fast R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-fast-r2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0 that keeps its core features, including joint audio-video generation guided by text, image, audio and video inputs. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0 that keeps its core features, including joint audio-video generation guided by text, image, audio and video inputs. This reference-to-video variant uses images, video clips and audio as references to guide performance, lighting and camera movement in a new clip."},{"id":"bytedance/seedance-2.0-fast-t2v","routeId":"seedance-2-0-fast-text-to-video-basic","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-01","displayName":"Seedance 2.0 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-fast-t2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0 that keeps its core features, including joint audio-video generation guided by text, image, audio and video inputs. This variant…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0 that keeps its core features, including joint audio-video generation guided by text, image, audio and video inputs. This variant generates video with audio from a text prompt."},{"id":"bytedance/seedance-2.0-i2v","routeId":"seedance-2-0-image-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-03-31","displayName":"Seedance 2.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-i2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 is ByteDance Seed's multimodal video model with a unified audio-video joint generation architecture that accepts text, image, audio and video inputs. This variant animates a still image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 is ByteDance Seed's multimodal video model with a unified audio-video joint generation architecture that accepts text, image, audio and video inputs. This variant animates a still image guided by a text prompt."},{"id":"bytedance/seedance-2.0-mini-i2v","routeId":"seedance-2-0-mini-image-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-25","displayName":"Seedance 2.0 Mini","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-mini-i2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 Mini is a lighter tier of ByteDance Seed's Seedance 2.0, a multimodal video model that generates video with audio from text, image, audio and video inputs. This variant animates a still…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 Mini is a lighter tier of ByteDance Seed's Seedance 2.0, a multimodal video model that generates video with audio from text, image, audio and video inputs. This variant animates a still image guided by a text prompt."},{"id":"bytedance/seedance-2.0-mini-r2v","routeId":"seedance-2-0-mini-reference-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-25","displayName":"Seedance 2.0 Mini R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-mini-r2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 Mini is a lighter tier of ByteDance Seed's Seedance 2.0, a multimodal video model that generates video with audio from text, image, audio and video inputs. This reference-to-video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 Mini is a lighter tier of ByteDance Seed's Seedance 2.0, a multimodal video model that generates video with audio from text, image, audio and video inputs. This reference-to-video variant uses images, video clips and audio as references to guide performance, lighting and camera movement in a new clip."},{"id":"bytedance/seedance-2.0-mini-t2v","routeId":"seedance-2-0-mini-text-to-video-basic","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-06-25","displayName":"Seedance 2.0 Mini","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-mini-t2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 Mini is a lighter tier of ByteDance Seed's Seedance 2.0, a multimodal video model that generates video with audio from text, image, audio and video inputs. This variant generates video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 Mini is a lighter tier of ByteDance Seed's Seedance 2.0, a multimodal video model that generates video with audio from text, image, audio and video inputs. This variant generates video with audio from a text prompt."},{"id":"bytedance/seedance-2.0-r2v","routeId":"seedance-2-0-reference-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-03-31","displayName":"Seedance 2.0 R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-r2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 is ByteDance Seed's multimodal video model with a unified audio-video joint generation architecture that accepts text, image, audio and video inputs. This reference-to-video variant uses…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 is ByteDance Seed's multimodal video model with a unified audio-video joint generation architecture that accepts text, image, audio and video inputs. This reference-to-video variant uses images, video clips and audio as references to guide performance, lighting and camera movement in a new clip."},{"id":"bytedance/seedance-2.0-t2v","routeId":"seedance-2-0-text-to-video-basic","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-03-31","displayName":"Seedance 2.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.0-t2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.0 is ByteDance Seed's multimodal video model with a unified audio-video joint generation architecture that accepts text, image, audio and video inputs. This variant generates video with…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.0 is ByteDance Seed's multimodal video model with a unified audio-video joint generation architecture that accepts text, image, audio and video inputs. This variant generates video with audio from a text prompt."},{"id":"bytedance/seedance-2.5-i2v","routeId":"seedance-2-5-image-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-07","displayName":"Seedance 2.5","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.5-i2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.5 is ByteDance Seed's audio-video joint generation model, producing up to 30 seconds of video with synchronized audio in one generation and supporting extension for longer stories. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.5 is ByteDance Seed's audio-video joint generation model, producing up to 30 seconds of video with synchronized audio in one generation and supporting extension for longer stories. This variant animates a still image guided by a text prompt."},{"id":"bytedance/seedance-2.5-r2v","routeId":"seedance-2-5-reference-to-video-basic","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-07","displayName":"Seedance 2.5 R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.5-r2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.5 is ByteDance Seed's audio-video joint generation model, producing up to 30 seconds of video with synchronized audio in one generation and supporting extension for longer stories. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.5 is ByteDance Seed's audio-video joint generation model, producing up to 30 seconds of video with synchronized audio in one generation and supporting extension for longer stories. This reference-to-video variant uses reference images, video clips and audio to carry characters, framing and camera language into a new clip."},{"id":"bytedance/seedance-2.5-t2v","routeId":"seedance-2-5-text-to-video-basic","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-08-07","displayName":"Seedance 2.5","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"bytedance/seedance-2.5-t2v","outputPriceLabel":"Varies","shortDescription":"Seedance 2.5 is ByteDance Seed's audio-video joint generation model, producing up to 30 seconds of video with synchronized audio in one generation and supporting extension for longer stories. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedance 2.5 is ByteDance Seed's audio-video joint generation model, producing up to 30 seconds of video with synchronized audio in one generation and supporting extension for longer stories. This variant generates video with audio from a text prompt."},{"id":"bytedance/seedream-v4.5-edit","routeId":"seedream-v4-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-01-04","displayName":"Seedream 4.5","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"bytedance/seedream-v4.5-edit","outputPriceLabel":"$0.05/edit","shortDescription":"Seedream 4.5 is ByteDance Seed's image generation and editing model, scaled up from Seedream 4.0 with stronger typography, dense text rendering and closer preservation of reference details. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedream 4.5 is ByteDance Seed's image generation and editing model, scaled up from Seedream 4.0 with stronger typography, dense text rendering and closer preservation of reference details. This variant edits images from a text instruction, including multi-image edits that keep the main subjects of the reference images."},{"id":"bytedance/seedream-v5-lite-edit","routeId":"seedream-v5-lite-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-02-23","displayName":"Seedream 5.0 Lite","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"bytedance/seedream-v5-lite-edit","outputPriceLabel":"$0.05/edit","shortDescription":"Seedream 5.0 Lite is ByteDance Seed's unified multimodal image generation model with deep thinking and online search, which it uses to interpret the intent behind a prompt and depict current topics.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedream 5.0 Lite is ByteDance Seed's unified multimodal image generation model with deep thinking and online search, which it uses to interpret the intent behind a prompt and depict current topics. This variant edits an existing image from a text instruction."},{"id":"bytedance/seedream-v5-pro","routeId":"seedream-v5-pro","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-07-08","displayName":"Seedream 5.0 Pro","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"bytedance/seedream-v5-pro","outputPriceLabel":"from $0.06/image","shortDescription":"Seedream 5.0 Pro is ByteDance Seed's multimodal image generation model for reasoning-heavy work such as infographics and text-rich images. It offers photographic realism and native support for about…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedream 5.0 Pro is ByteDance Seed's multimodal image generation model for reasoning-heavy work such as infographics and text-rich images. It offers photographic realism and native support for about a dozen languages. This variant generates images from a text prompt."},{"id":"bytedance/seedream-v5-pro-edit","routeId":"seedream-v5-pro-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-07-08","displayName":"Seedream 5.0 Pro","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"bytedance/seedream-v5-pro-edit","outputPriceLabel":"from $0.06/edit","shortDescription":"Seedream 5.0 Pro is ByteDance Seed's multimodal image generation model for reasoning-heavy work such as infographics and text-rich images. It offers photographic realism and native support for about…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Seedream 5.0 Pro is ByteDance Seed's multimodal image generation model for reasoning-heavy work such as infographics and text-rich images. It offers photographic realism and native support for about a dozen languages. This variant edits images from a text instruction and supports spatial annotations, sketch guidance and layer separation."},{"id":"elevenlabs/elevenlabs-multilingual-v2","routeId":"elevenlabs-tts-multilingual-v2","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-28","displayName":"ElevenLabs Multilingual v2","pricingNote":"Priced per 1K input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-multilingual-v2","outputPriceLabel":"$0.12/1K chars","shortDescription":"Multilingual text-to-speech using ElevenLabs. Supports 29 languages with high-quality natural-sounding voices, configurable speed, and accent accuracy.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Multilingual text-to-speech using ElevenLabs. Supports 29 languages with high-quality natural-sounding voices, configurable speed, and accent accuracy."},{"id":"elevenlabs/elevenlabs-music","routeId":"elevenlabs-music","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-22","displayName":"ElevenLabs Music","pricingNote":"Price scales with track duration.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-music","outputPriceLabel":"from $0.69/track","shortDescription":"High-quality instrumental music generation with configurable duration. Best for polished, production-ready tracks across a wide range of genres.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"High-quality instrumental music generation with configurable duration. Best for polished, production-ready tracks across a wide range of genres."},{"id":"elevenlabs/elevenlabs-music-v2","routeId":"elevenlabs-music-v2","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-09-15","displayName":"ElevenLabs Music v2","pricingNote":"Price scales with track duration.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-music-v2","outputPriceLabel":"from $0.69/track","shortDescription":"High-quality realistic music generation with optional vocals and configurable duration. Best for polished, production-ready tracks across a wide range of genres.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"High-quality realistic music generation with optional vocals and configurable duration. Best for polished, production-ready tracks across a wide range of genres."},{"id":"elevenlabs/elevenlabs-music-v2.5","routeId":"elevenlabs-music-v2-5","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-09-15","displayName":"ElevenLabs Music v2.5","pricingNote":"Price scales with track duration.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-music-v2.5","outputPriceLabel":"from $0.69/track","shortDescription":"Eleven Music v2.5 is ElevenLabs' music generation model, an update to Music v2 with improved audio quality and prompt adherence. It generates songs with vocals or instrumental-only tracks from a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Eleven Music v2.5 is ElevenLabs' music generation model, an update to Music v2 with improved audio quality and prompt adherence. It generates songs with vocals or instrumental-only tracks from a text prompt, in multiple languages and from 3 seconds to 5 minutes long, and supports composition plans, audio reference and inpainting."},{"id":"elevenlabs/elevenlabs-scribe-v2","routeId":"elevenlabs/scribe-v2","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-17","displayName":"ElevenLabs Scribe v2","pricingNote":"Priced at $0.000167 per second of input audio.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$0.01/min","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-scribe-v2","outputPriceLabel":"–","shortDescription":"Scribe v2 is ElevenLabs' speech-to-text model for transcribing recorded audio in more than 90 languages. It returns word-level timestamps and supports speaker diarization for up to 32 speakers,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Scribe v2 is ElevenLabs' speech-to-text model for transcribing recorded audio in more than 90 languages. It returns word-level timestamps and supports speaker diarization for up to 32 speakers, keyterm prompting, entity detection and tagging of non-speech audio events such as laughter or applause."},{"id":"elevenlabs/elevenlabs-sound-effects","routeId":"elevenlabs-sound-effects-v2","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-28","displayName":"ElevenLabs Sound Effects","pricingNote":"Priced per second of generated audio.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-sound-effects","outputPriceLabel":"$0.14/min","shortDescription":"Generate high-quality sound effects from text descriptions using ElevenLabs. Ideal for films, games, and digital content with configurable duration.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Generate high-quality sound effects from text descriptions using ElevenLabs. Ideal for films, games, and digital content with configurable duration."},{"id":"elevenlabs/elevenlabs-tts-v3","routeId":"elevenlabs-tts-v3","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-28","displayName":"ElevenLabs TTS v3","pricingNote":"Priced per 1K input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-tts-v3","outputPriceLabel":"$0.12/1K chars","shortDescription":"Generate natural text-to-speech audio using ElevenLabs Eleven-v3. High-quality voices with stability control and automatic text normalization.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Generate natural text-to-speech audio using ElevenLabs Eleven-v3. High-quality voices with stability control and automatic text normalization."},{"id":"elevenlabs/elevenlabs-tts-v4","routeId":"elevenlabs-tts-v4","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-09-29","displayName":"ElevenLabs TTS v4","pricingNote":"Priced per 1K input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-tts-v4","outputPriceLabel":"$0.09/1K chars","shortDescription":"Generate expressive text-to-speech audio using ElevenLabs Eleven-v4. High-quality voices with audio tag support and automatic text normalization.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Generate expressive text-to-speech audio using ElevenLabs Eleven-v4. High-quality voices with audio tag support and automatic text normalization."},{"id":"elevenlabs/elevenlabs-tts-v4-turbo","routeId":"elevenlabs-tts-v4-turbo","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-09-29","displayName":"ElevenLabs TTS v4 Turbo","pricingNote":"Priced per 1K input characters.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-tts-v4-turbo","outputPriceLabel":"$0.05/1K chars","shortDescription":"Generate fast text-to-speech audio using ElevenLabs Eleven-v4 Turbo. High-quality low-latency voices with audio tag support and automatic text normalization.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Generate fast text-to-speech audio using ElevenLabs Eleven-v4 Turbo. High-quality low-latency voices with audio tag support and automatic text normalization."},{"id":"elevenlabs/elevenlabs-voice-changer","routeId":"elevenlabs-voice-changer","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-07-27","displayName":"ElevenLabs Voice Changer","pricingNote":"Price scales with track duration.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"elevenlabs/elevenlabs-voice-changer","outputPriceLabel":"from $0.35/track","shortDescription":"Re-record any speech in a different voice with ElevenLabs Voice Changer. Keeps the original delivery, pacing and emotion.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Re-record any speech in a different voice with ElevenLabs Voice Changer. Keeps the original delivery, pacing and emotion."},{"id":"google/gemini-omni-flash-1.1-edit","routeId":"gemini-omni-flash-1-1-video-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-08-27","displayName":"Gemini Omni 1.1 Flash Edit","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/gemini-omni-flash-1.1-edit","outputPriceLabel":"Varies","shortDescription":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video references and 360p drafts. This editing variant takes a video of up to 10 seconds and a text instruction and returns an edited clip, with support for multi-turn conversational edits."},{"id":"google/gemini-omni-flash-1.1-i2v","routeId":"gemini-omni-flash-1-1-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-27","displayName":"Gemini Omni 1.1 Flash","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/gemini-omni-flash-1.1-i2v","outputPriceLabel":"Varies","shortDescription":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video references and 360p drafts. This variant animates a reference image, or generates the motion between a first and last frame."},{"id":"google/gemini-omni-flash-1.1-r2v","routeId":"gemini-omni-flash-1-1-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-27","displayName":"Gemini Omni 1.1 Flash R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/gemini-omni-flash-1.1-r2v","outputPriceLabel":"Varies","shortDescription":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video references and 360p drafts. This reference-to-video variant uses reference images and up to three video clips of up to three seconds each to keep subjects consistent in a new scene."},{"id":"google/gemini-omni-flash-1.1-t2v","routeId":"gemini-omni-flash-1-1-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-08-27","displayName":"Gemini Omni 1.1 Flash","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/gemini-omni-flash-1.1-t2v","outputPriceLabel":"Varies","shortDescription":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Gemini Omni 1.1 Flash is an update to Google DeepMind's Gemini Omni Flash video model. It adds first and last frame control, scene extension from up to 10 seconds of prior context, short video references and 360p drafts. This variant generates a video with audio from a text prompt."},{"id":"google/gemini-omni-flash-i2v","routeId":"gemini-omni-flash-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-30","displayName":"Gemini Omni Flash","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/gemini-omni-flash-i2v","outputPriceLabel":"Varies","shortDescription":"Gemini Omni Flash is Google DeepMind's multimodal model for generating and conversationally editing video with audio, drawing on Gemini's world knowledge. It accepts text, image, video and voice…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Gemini Omni Flash is Google DeepMind's multimodal model for generating and conversationally editing video with audio, drawing on Gemini's world knowledge. It accepts text, image, video and voice references. This variant animates a still image guided by a text prompt."},{"id":"google/gemini-omni-flash-r2v","routeId":"gemini-omni-flash-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-30","displayName":"Gemini Omni Flash R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/gemini-omni-flash-r2v","outputPriceLabel":"Varies","shortDescription":"Gemini Omni Flash is Google DeepMind's multimodal model for generating and conversationally editing video with audio, drawing on Gemini's world knowledge. It accepts text, image, video and voice…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Gemini Omni Flash is Google DeepMind's multimodal model for generating and conversationally editing video with audio, drawing on Gemini's world knowledge. It accepts text, image, video and voice references. This reference-to-video variant places subjects from reference images into a new scene while keeping their identity consistent."},{"id":"google/gemini-omni-flash-t2v","routeId":"gemini-omni-flash-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-06-30","displayName":"Gemini Omni Flash","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/gemini-omni-flash-t2v","outputPriceLabel":"Varies","shortDescription":"Gemini Omni Flash is Google DeepMind's multimodal model for generating and conversationally editing video with audio, drawing on Gemini's world knowledge. It accepts text, image, video and voice…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Gemini Omni Flash is Google DeepMind's multimodal model for generating and conversationally editing video with audio, drawing on Gemini's world knowledge. It accepts text, image, video and voice references. This variant generates a video from a text prompt."},{"id":"google/lyria-3-pro","routeId":"lyria-3-pro","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-05-22","displayName":"Lyria 3 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"google/lyria-3-pro","outputPriceLabel":"$0.10/track","shortDescription":"Google's Lyria 3 Pro generates full-length, structured songs up to 3 minutes long from a single text prompt. Supports vocals, lyrics, and multi-language generation across genres.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Google's Lyria 3 Pro generates full-length, structured songs up to 3 minutes long from a single text prompt. Supports vocals, lyrics, and multi-language generation across genres."},{"id":"google/nano-banana-2","routeId":"nano-banana-2","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-02-26","displayName":"Nano Banana 2","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-2","outputPriceLabel":"from $0.10/image","shortDescription":"Nano Banana 2 (Gemini 3.1 Flash Image) is Google DeepMind's image generation and editing model that brings Nano Banana Pro's world knowledge and reasoning to Flash speed. It renders legible in-image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Nano Banana 2 (Gemini 3.1 Flash Image) is Google DeepMind's image generation and editing model that brings Nano Banana Pro's world knowledge and reasoning to Flash speed. It renders legible in-image text and outputs from 512px to 4K. This variant generates images from a text prompt."},{"id":"google/nano-banana-2-edit","routeId":"nano-banana-2-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-02-26","displayName":"Nano Banana 2","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-2-edit","outputPriceLabel":"from $0.10/edit","shortDescription":"Nano Banana 2 (Gemini 3.1 Flash Image) is Google DeepMind's image generation and editing model that brings Nano Banana Pro's world knowledge and reasoning to Flash speed. It renders legible in-image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Nano Banana 2 (Gemini 3.1 Flash Image) is Google DeepMind's image generation and editing model that brings Nano Banana Pro's world knowledge and reasoning to Flash speed. It renders legible in-image text and outputs from 512px to 4K. This variant edits images from a text instruction and can keep up to five characters and 14 objects consistent."},{"id":"google/nano-banana-2-lite-edit","routeId":"nano-banana-2-lite-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-30","displayName":"Nano Banana 2 Lite","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-2-lite-edit","outputPriceLabel":"$0.06/edit","shortDescription":"Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is the speed- and cost-focused model in Google DeepMind's Nano Banana image family, built for high-volume generation and editing. This variant edits…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is the speed- and cost-focused model in Google DeepMind's Nano Banana image family, built for high-volume generation and editing. This variant edits an existing image from a text instruction."},{"id":"google/nano-banana-2.1","routeId":"nano-banana-2-1","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-10-06","displayName":"Nano Banana 2.1","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-2.1","outputPriceLabel":"from $0.10/image","shortDescription":"Nano Banana 2.1 is Google DeepMind's update to Nano Banana 2 (Gemini 3.1 Flash Image), with improved realism, text rendering and infographic layout. It offers configurable thinking levels and output…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Nano Banana 2.1 is Google DeepMind's update to Nano Banana 2 (Gemini 3.1 Flash Image), with improved realism, text rendering and infographic layout. It offers configurable thinking levels and output at 1K, 2K or 4K. This variant generates images from a text prompt, with optional grounding in web and image search."},{"id":"google/nano-banana-2.1-edit","routeId":"nano-banana-2-1-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-10-06","displayName":"Nano Banana 2.1","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-2.1-edit","outputPriceLabel":"from $0.10/edit","shortDescription":"Nano Banana 2.1 is Google DeepMind's update to Nano Banana 2 (Gemini 3.1 Flash Image), with improved realism, text rendering and infographic layout. It offers configurable thinking levels and output…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Nano Banana 2.1 is Google DeepMind's update to Nano Banana 2 (Gemini 3.1 Flash Image), with improved realism, text rendering and infographic layout. It offers configurable thinking levels and output at 1K, 2K or 4K. This variant edits images from a text instruction and can fuse up to 14 reference images."},{"id":"google/nano-banana-pro","routeId":"nano-banana-pro","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-11-20","displayName":"Nano Banana Pro","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-pro","outputPriceLabel":"from $0.18/image","shortDescription":"Nano Banana Pro (Gemini 3 Pro Image) is Google DeepMind's image generation and editing model built on Gemini 3 Pro. It uses Gemini's reasoning and world knowledge for legible multilingual text and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Nano Banana Pro (Gemini 3 Pro Image) is Google DeepMind's image generation and editing model built on Gemini 3 Pro. It uses Gemini's reasoning and world knowledge for legible multilingual text and information graphics at up to 4K. This variant generates images from a text prompt."},{"id":"google/nano-banana-pro-edit","routeId":"nano-banana-pro-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2025-12-13","displayName":"Nano Banana Pro","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"google/nano-banana-pro-edit","outputPriceLabel":"from $0.18/edit","shortDescription":"Nano Banana Pro (Gemini 3 Pro Image) is Google DeepMind's image generation and editing model built on Gemini 3 Pro. It uses Gemini's reasoning and world knowledge for legible multilingual text and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Nano Banana Pro (Gemini 3 Pro Image) is Google DeepMind's image generation and editing model built on Gemini 3 Pro. It uses Gemini's reasoning and world knowledge for legible multilingual text and information graphics at up to 4K. This variant edits images with control over regions, camera angle and lighting, and can blend up to 14 reference images."},{"id":"google/veo-3.1-fast-i2v","routeId":"veo3.1-fast-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2024-10-15","displayName":"Veo 3.1 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/veo-3.1-fast-i2v","outputPriceLabel":"Varies","shortDescription":"Veo 3.1 Fast is the speed-optimized version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better image-to-video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Veo 3.1 Fast is the speed-optimized version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better image-to-video consistency. This variant animates a starting image, or a first and last frame, guided by a text prompt."},{"id":"google/veo-3.1-fast-t2v","routeId":"veo3.1-fast-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2024-10-15","displayName":"Veo 3.1 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/veo-3.1-fast-t2v","outputPriceLabel":"Varies","shortDescription":"Veo 3.1 Fast is the speed-optimized version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better image-to-video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Veo 3.1 Fast is the speed-optimized version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better image-to-video consistency. This variant generates video from a text prompt."},{"id":"google/veo-3.1-full-quality-i2v","routeId":"veo3.1-full-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2024-10-15","displayName":"Veo 3.1 Full Quality","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/veo-3.1-full-quality-i2v","outputPriceLabel":"Varies","shortDescription":"Veo 3.1 Full Quality is the standard, non-Fast version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Veo 3.1 Full Quality is the standard, non-Fast version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better image-to-video consistency. This variant animates a starting image, or a first and last frame, guided by a text prompt."},{"id":"google/veo-3.1-full-quality-t2v","routeId":"veo3.1-full-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2024-10-15","displayName":"Veo 3.1 Full Quality","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"google/veo-3.1-full-quality-t2v","outputPriceLabel":"Varies","shortDescription":"Veo 3.1 Full Quality is the standard, non-Fast version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Veo 3.1 Full Quality is the standard, non-Fast version of Veo 3.1, Google DeepMind's video model with native audio. Over Veo 3 it adds richer audio, stronger narrative control and better image-to-video consistency. This variant generates video from a text prompt."},{"id":"hkchengrex/mmaudio-v2","routeId":"mmaudio-v2-text-to-audio","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-28","displayName":"MMAudio V2","pricingNote":"Priced per second of generated audio.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"venice/mmaudio-v2","outputPriceLabel":"$0.06/min","shortDescription":"Generate synchronized audio and sound effects from text prompts with MMAudio V2.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Generate synchronized audio and sound effects from text prompts with MMAudio V2."},{"id":"ideogram/ideogram-v4.5-edit","routeId":"ideogram-v4-5-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-30","displayName":"Ideogram 4.5 Edit","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"ideogram/ideogram-v4.5-edit","outputPriceLabel":"$0.26/edit","shortDescription":"Ideogram 4.5 is Ideogram's image generation and editing model, built for precise multi-turn edits that change part of an image while leaving the rest untouched. This variant edits an input image from…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Ideogram 4.5 is Ideogram's image generation and editing model, built for precise multi-turn edits that change part of an image while leaving the rest untouched. This variant edits an input image from a text instruction."},{"id":"kuaishou/kling-2.5-turbo-pro-i2v","routeId":"kling-2.5-turbo-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2025-09-25","displayName":"Kling 2.5 Turbo Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-2.5-turbo-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Kling 2.5 Turbo Pro is the Pro mode of Kling 2.5 Turbo, a Kling AI video model from Kuaishou. It was trained with reinforcement learning for stronger prompt adherence, multi-step instructions and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling 2.5 Turbo Pro is the Pro mode of Kling 2.5 Turbo, a Kling AI video model from Kuaishou. It was trained with reinforcement learning for stronger prompt adherence, multi-step instructions and stable fast motion. This variant animates a still image guided by a text prompt, with optional first and last frames."},{"id":"kuaishou/kling-2.5-turbo-pro-t2v","routeId":"kling-2.5-turbo-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2025-09-25","displayName":"Kling 2.5 Turbo Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-2.5-turbo-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Kling 2.5 Turbo Pro is the Pro mode of Kling 2.5 Turbo, a Kling AI video model from Kuaishou. It was trained with reinforcement learning for stronger prompt adherence, multi-step instructions and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling 2.5 Turbo Pro is the Pro mode of Kling 2.5 Turbo, a Kling AI video model from Kuaishou. It was trained with reinforcement learning for stronger prompt adherence, multi-step instructions and stable fast motion. This variant generates video from a text prompt."},{"id":"kuaishou/kling-2.6-pro-i2v","routeId":"kling-2.6-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2024-12-03","displayName":"Kling 2.6 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-2.6-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Kling 2.6 Pro is the Pro mode of Kling 2.6, Kuaishou's Kling AI video model that generates video and audio in a single pass. Audio includes dialogue, singing, sound effects and ambient sound…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling 2.6 Pro is the Pro mode of Kling 2.6, Kuaishou's Kling AI video model that generates video and audio in a single pass. Audio includes dialogue, singing, sound effects and ambient sound synchronized with the action. This variant animates a still image guided by a text prompt."},{"id":"kuaishou/kling-2.6-pro-t2v","routeId":"kling-2.6-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2024-12-03","displayName":"Kling 2.6 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-2.6-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Kling 2.6 Pro is the Pro mode of Kling 2.6, Kuaishou's Kling AI video model that generates video and audio in a single pass. Audio includes dialogue, singing, sound effects and ambient sound…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling 2.6 Pro is the Pro mode of Kling 2.6, Kuaishou's Kling AI video model that generates video and audio in a single pass. Audio includes dialogue, singing, sound effects and ambient sound synchronized with the action. This variant generates video from a text prompt."},{"id":"kuaishou/kling-4.0-i2v","routeId":"kling-v4-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-10-24","displayName":"Kling 4.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-4.0-i2v","outputPriceLabel":"Varies","shortDescription":"Kling 4.0 is a video generation model. Smooth motion with strong scene and subject consistency.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling 4.0 is a video generation model. Smooth motion with strong scene and subject consistency."},{"id":"kuaishou/kling-4.0-r2v","routeId":"kling-v4-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-10-24","displayName":"Kling 4.0 R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-4.0-r2v","outputPriceLabel":"Varies","shortDescription":"Kling 4.0 R2V is a video generation model. Smooth motion with strong scene and subject consistency.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling 4.0 R2V is a video generation model. Smooth motion with strong scene and subject consistency."},{"id":"kuaishou/kling-4.0-t2v","routeId":"kling-v4-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-10-24","displayName":"Kling 4.0","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-4.0-t2v","outputPriceLabel":"Varies","shortDescription":"Kling 4.0 is a video generation model. Smooth motion with strong scene and subject consistency.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling 4.0 is a video generation model. Smooth motion with strong scene and subject consistency."},{"id":"kuaishou/kling-o3-4k-i2v","routeId":"kling-o3-4k-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-22","displayName":"Kling O3 4K","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-4k-i2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This variant renders native 4K (3840x2160) video from a start image guided by a text prompt."},{"id":"kuaishou/kling-o3-4k-r2v","routeId":"kling-o3-4k-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-22","displayName":"Kling O3 4K R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-4k-r2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This variant renders native 4K (3840x2160) video guided by reference images, elements or video and a text prompt."},{"id":"kuaishou/kling-o3-4k-t2v","routeId":"kling-o3-4k-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-22","displayName":"Kling O3 4K","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-4k-t2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This variant renders native 4K (3840x2160) video from a text prompt."},{"id":"kuaishou/kling-o3-pro-i2v","routeId":"kling-o3-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling O3 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This Pro tier variant animates a start image, or start and end frames, guided by a text prompt."},{"id":"kuaishou/kling-o3-pro-r2v","routeId":"kling-o3-pro-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-03-09","displayName":"Kling O3 Pro R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-pro-r2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This Pro tier reference-to-video variant uses up to seven reference images or elements, or a reference video, to keep characters and objects consistent, and can bind a voice to a character."},{"id":"kuaishou/kling-o3-pro-t2v","routeId":"kling-o3-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling O3 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This Pro tier variant generates video from a text prompt."},{"id":"kuaishou/kling-o3-standard-i2v","routeId":"kling-o3-standard-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling O3 Standard","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-standard-i2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This Standard tier variant animates a start image, or start and end frames, guided by a text prompt."},{"id":"kuaishou/kling-o3-standard-r2v","routeId":"kling-o3-standard-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-03-10","displayName":"Kling O3 Standard R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-standard-r2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This Standard tier reference-to-video variant uses up to seven reference images or elements, or a reference video, to keep characters and objects consistent, and can bind a voice to a character."},{"id":"kuaishou/kling-o3-standard-t2v","routeId":"kling-o3-standard-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling O3 Standard","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-o3-standard-t2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Omni is Kuaishou's unified multimodal Kling AI video model that treats text, images, elements and video as prompts. It generates clips of up to 15 seconds with native audio and custom multi-shot storyboards. This Standard tier variant generates video from a text prompt."},{"id":"kuaishou/kling-v3-4k","routeId":"kling-v3-4k-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-22","displayName":"Kling V3 4K","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-4k","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot storyboards. This variant renders native 4K (3840x2160) video from a text prompt."},{"id":"kuaishou/kling-v3-4k-r2v","routeId":"kling-v3-4k-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-22","displayName":"Kling V3 4K R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-4k-r2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot storyboards. This variant renders native 4K (3840x2160) video guided by reference elements, such as characters or objects from images or video, and a text prompt."},{"id":"kuaishou/kling-v3-pro-i2v","routeId":"kling-v3-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling V3 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot storyboards. This Pro tier variant animates a start image, or start and end frames, guided by a text prompt."},{"id":"kuaishou/kling-v3-pro-motion-control","routeId":"kling-v3-pro-motion-control","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-05-25","displayName":"Kling V3 Pro Motion Control","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-pro-motion-control","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Motion Control is Kuaishou's Kling AI model that transfers the movements and facial expressions from a reference video onto a character in a still image. It keeps facial features…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Motion Control is Kuaishou's Kling AI model that transfers the movements and facial expressions from a reference video onto a character in a still image. It keeps facial features stable through complex, multi-angle motion. This is the Pro tier."},{"id":"kuaishou/kling-v3-pro-t2v","routeId":"kling-v3-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling V3 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot storyboards. This Pro tier variant generates video from a text prompt."},{"id":"kuaishou/kling-v3-standard-i2v","routeId":"kling-v3-standard-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling V3 Standard","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-standard-i2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot storyboards. This Standard tier variant animates a start image, or start and end frames, guided by a text prompt."},{"id":"kuaishou/kling-v3-standard-motion-control","routeId":"kling-v3-standard-motion-control","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-05-25","displayName":"Kling V3 Standard Motion Control","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-standard-motion-control","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Motion Control is Kuaishou's Kling AI model that transfers the movements and facial expressions from a reference video onto a character in a still image. It keeps facial features…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Motion Control is Kuaishou's Kling AI model that transfers the movements and facial expressions from a reference video onto a character in a still image. It keeps facial features stable through complex, multi-angle motion. This is the Standard tier."},{"id":"kuaishou/kling-v3-standard-t2v","routeId":"kling-v3-standard-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-02-03","displayName":"Kling V3 Standard","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-standard-t2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 is Kuaishou's Kling AI video model that generates clips of 3 to 15 seconds with native audio and character-level lip-sync in five languages. It supports automatic or custom multi-shot storyboards. This Standard tier variant generates video from a text prompt."},{"id":"kuaishou/kling-v3-turbo-pro-i2v","routeId":"kling-v3-turbo-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Kling V3 Turbo Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-turbo-pro-i2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Pro tier variant animates a still image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Pro tier variant animates a still image guided by a text prompt."},{"id":"kuaishou/kling-v3-turbo-pro-t2v","routeId":"kling-v3-turbo-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Kling V3 Turbo Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-turbo-pro-t2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Pro tier variant generates video from a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Pro tier variant generates video from a text prompt."},{"id":"kuaishou/kling-v3-turbo-standard-i2v","routeId":"kling-v3-turbo-standard-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Kling V3 Turbo Standard","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-turbo-standard-i2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Standard tier variant animates a still…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Standard tier variant animates a still image guided by a text prompt."},{"id":"kuaishou/kling-v3-turbo-standard-t2v","routeId":"kling-v3-turbo-standard-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Kling V3 Turbo Standard","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"kuaishou/kling-v3-turbo-standard-t2v","outputPriceLabel":"Varies","shortDescription":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Standard tier variant generates video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Kling VIDEO 3.0 Turbo is a faster version of Kuaishou's Kling VIDEO 3.0 video model that generates video with native audio and synchronized lip movement. This Standard tier variant generates video from a text prompt."},{"id":"lightricks/ltx-video-2.3-fast-i2v","routeId":"ltx-2-v2-3-fast-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-03-05","displayName":"LTX-2.3 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.3-fast-i2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.3 Fast is the speed-focused tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant animates a source image into a video…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.3","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.3 Fast is the speed-focused tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant animates a source image into a video guided by a text prompt, at up to 4K resolution."},{"id":"lightricks/ltx-video-2.3-fast-t2v","routeId":"ltx-2-v2-3-fast-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-03-05","displayName":"LTX-2.3 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.3-fast-t2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.3 Fast is the speed-focused tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant generates video with audio from a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.3","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.3 Fast is the speed-focused tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant generates video with audio from a text prompt, at up to 4K resolution."},{"id":"lightricks/ltx-video-2.3-full-quality-i2v","routeId":"ltx-2-v2-3-full-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-03-05","displayName":"LTX-2.3 Full Quality","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.3-full-quality-i2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.3 Full Quality is the higher-fidelity tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant animates a source image…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.3","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.3 Full Quality is the higher-fidelity tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant animates a source image into a video guided by a text prompt."},{"id":"lightricks/ltx-video-2.3-full-quality-t2v","routeId":"ltx-2-v2-3-full-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-03-05","displayName":"LTX-2.3 Full Quality","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.3-full-quality-t2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.3 Full Quality is the higher-fidelity tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant generates video with audio…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.3","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.3 Full Quality is the higher-fidelity tier of Lightricks' LTX-2.3, an open-weight 22B diffusion transformer that generates synchronized video and audio. This variant generates video with audio from a text prompt."},{"id":"lightricks/ltx-video-2.5-fast-i2v","routeId":"ltx-2-5-fast-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-11","displayName":"LTX-2.5 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.5-fast-i2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.5 Fast is the speed-focused tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.5","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.5 Fast is the speed-focused tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts. This variant animates a source image into a video with audio guided by a text prompt, at up to 4K resolution."},{"id":"lightricks/ltx-video-2.5-fast-t2v","routeId":"ltx-2-5-fast-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-08-11","displayName":"LTX-2.5 Fast","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.5-fast-t2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.5 Fast is the speed-focused tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.5","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.5 Fast is the speed-focused tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts. This variant generates video with audio from a text prompt, at up to 4K resolution."},{"id":"lightricks/ltx-video-2.5-pro-i2v","routeId":"ltx-2-5-pro-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-08-11","displayName":"LTX-2.5 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.5-pro-i2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.5 Pro is the higher-fidelity tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.5","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.5 Pro is the higher-fidelity tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts. This variant animates a source image into a video with audio guided by a text prompt, at up to 4K resolution."},{"id":"lightricks/ltx-video-2.5-pro-t2v","routeId":"ltx-2-5-pro-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-08-11","displayName":"LTX-2.5 Pro","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"lightricks/ltx-video-2.5-pro-t2v","outputPriceLabel":"Varies","shortDescription":"LTX-2.5 Pro is the higher-fidelity tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts.…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Lightricks/LTX-2.5","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"LTX-2.5 Pro is the higher-fidelity tier of Lightricks' LTX-2.5, an open-weight audio-video model with native multi-shot generation that keeps characters, lighting and voice consistent across cuts. This variant generates video with audio from a text prompt, at up to 4K resolution."},{"id":"luma/luma-uni-1-edit","routeId":"luma-uni-1-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Luma Uni-1","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"luma/luma-uni-1-edit","outputPriceLabel":"$0.06/edit","shortDescription":"Uni-1 is Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant edits an…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Uni-1 is Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant edits an existing image from natural-language instructions, such as changes to background, lighting or local details."},{"id":"luma/luma-uni-1-max-edit","routeId":"luma-uni-1-max-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-06-17","displayName":"Luma Uni-1 Max","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"luma/luma-uni-1-max-edit","outputPriceLabel":"$0.13/edit","shortDescription":"Uni-1 Max is the higher-quality tier of Uni-1, Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Uni-1 Max is the higher-quality tier of Uni-1, Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant edits an existing image from natural-language instructions, such as changes to background, lighting or local details."},{"id":"meta/muse-image-edit","routeId":"muse-image-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-03","displayName":"Muse Image","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"venice/muse-image-edit","outputPriceLabel":"$0.02/edit","shortDescription":"Muse Image is Meta's image generation and editing model, the first from Meta Superintelligence Labs. It works with Meta's Muse Spark reasoning model to plan layouts, draw on web context and combine…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Muse Image is Meta's image generation and editing model, the first from Meta Superintelligence Labs. It works with Meta's Muse Spark reasoning model to plan layouts, draw on web context and combine multiple references, and renders legible in-image text. This variant edits an existing image from a text instruction or marked-up regions."},{"id":"minimax/minimax-h3-enhanced","routeId":"minimax-h3-enhanced-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-08-05","displayName":"MiniMax H3 Enhanced","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-enhanced","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 Enhanced is an enhanced-output variant of MiniMax's open-weight H3 omni-modal video model, which generates clips with native stereo audio. This variant generates video with audio from a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 Enhanced is an enhanced-output variant of MiniMax's open-weight H3 omni-modal video model, which generates clips with native stereo audio. This variant generates video with audio from a text prompt."},{"id":"minimax/minimax-h3-i2v","routeId":"minimax-h3-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-07-30","displayName":"MiniMax H3","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-i2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 is MiniMax's open-weight omni-modal video model, a 33B-parameter transformer that generates 4 to 15 second clips with native stereo audio from text, image, video and audio inputs. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 is MiniMax's open-weight omni-modal video model, a 33B-parameter transformer that generates 4 to 15 second clips with native stereo audio from text, image, video and audio inputs. This variant animates a first-frame image, optionally with a last frame, guided by a text prompt."},{"id":"minimax/minimax-h3-r2v","routeId":"minimax-h3-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-07-30","displayName":"MiniMax H3 R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-r2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 is MiniMax's open-weight omni-modal video model, a 33B-parameter transformer that generates 4 to 15 second clips with native stereo audio from text, image, video and audio inputs. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 is MiniMax's open-weight omni-modal video model, a 33B-parameter transformer that generates 4 to 15 second clips with native stereo audio from text, image, video and audio inputs. This variant generates video from up to 9 reference images, 3 video clips and 3 audio clips plus a text prompt, keeping subjects and voices consistent."},{"id":"minimax/minimax-h3-r2v-enhanced","routeId":"minimax-h3-enhanced-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"uncensored","releasedAt":"2026-08-05","displayName":"MiniMax H3 R2V Enhanced","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-r2v-enhanced","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 R2V Enhanced is an enhanced-output variant of MiniMax's open-weight H3 omni-modal video model, which generates clips with native stereo audio. This variant generates video from reference…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 R2V Enhanced is an enhanced-output variant of MiniMax's open-weight H3 omni-modal video model, which generates clips with native stereo audio. This variant generates video from reference images, video and audio clips plus a text prompt."},{"id":"minimax/minimax-h3-t2v","routeId":"minimax-h3-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"uncensored","releasedAt":"2026-07-30","displayName":"MiniMax H3","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"minimax/minimax-h3-t2v","outputPriceLabel":"Varies","shortDescription":"MiniMax H3 is MiniMax's open-weight omni-modal video model, a 33B-parameter transformer that generates 4 to 15 second clips with native stereo audio from text, image, video and audio inputs. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax H3 is MiniMax's open-weight omni-modal video model, a 33B-parameter transformer that generates 4 to 15 second clips with native stereo audio from text, image, video and audio inputs. This variant generates video with audio from a text prompt."},{"id":"minimax/minimax-music-2.0","routeId":"minimax-music-v2","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-22","displayName":"MiniMax Music 2.0","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"minimax/minimax-music-2.0","outputPriceLabel":"$0.04/track","shortDescription":"Full song generation with vocals and lyrics. Provide your own lyrics with verse/chorus structure for complete songs with singing.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Full song generation with vocals and lyrics. Provide your own lyrics with verse/chorus structure for complete songs with singing."},{"id":"minimax/minimax-music-2.5","routeId":"minimax-music-v25","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-12","displayName":"MiniMax Music 2.5","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"minimax/minimax-music-2.5","outputPriceLabel":"$0.18/track","shortDescription":"Advanced song generation with vocals, lyrics optimizer, and instrumental mode. Supports structure tags and up to 3500 character lyrics.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Advanced song generation with vocals, lyrics optimizer, and instrumental mode. Supports structure tags and up to 3500 character lyrics."},{"id":"minimax/minimax-music-2.6","routeId":"minimax-music-v26","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-12","displayName":"MiniMax Music 2.6","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"minimax/minimax-music-2.6","outputPriceLabel":"$0.18/track","shortDescription":"MiniMax Music 2.6 is MiniMax's song generation model. It generates songs with vocals or instrumental-only tracks from a text prompt and lyrics, and follows prompt instructions for BPM, key, song…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"MiniMax Music 2.6 is MiniMax's song generation model. It generates songs with vocals or instrumental-only tracks from a text prompt and lyrics, and follows prompt instructions for BPM, key, song structure and emotional arc."},{"id":"openai/gpt-5.6-luna-pro","routeId":"openai-gpt-56-luna-pro","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"medium","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-07-09","displayName":"GPT-5.6 Luna Pro","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-5.6-luna-pro","shortDescription":"GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-5.6-luna","label":"Model source"}],"inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":0.25,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks."},{"id":"openai/gpt-6.1-terra","routeId":"openai-gpt-61-terra","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","medium","high","xhigh","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-26","displayName":"GPT-6.1 Terra","pricingNote":"USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1050000,"privacySummary":"Venice Anonymous routing","maxOutputTokens":128000,"primaryModality":"text","providerRouteId":"openai/gpt-6.1-terra","shortDescription":"GPT-6.1 Terra is a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. It has a 1.05M token context window (922K input, 128K output), support for text and…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://developers.openai.com/api/docs/models/gpt-6.1-terra","label":"Model source"}],"inputPriceUsdPerMillion":1,"outputPriceUsdPerMillion":5,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":1.25,"priceTiers":[{"aboveInputTokens":272000,"inputPriceUsdPerMillion":2,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":2.5}],"priceTiersInEffect":false,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT-6.1 Terra is a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max."},{"id":"openai/gpt-image-1.5-edit","routeId":"gpt-image-1-5-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-01-04","displayName":"GPT Image 1.5","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-1.5-edit","outputPriceLabel":"$0.31/edit","shortDescription":"GPT Image 1.5 is OpenAI's image generation model that takes text and image input, with improved instruction following and prompt adherence over earlier GPT Image models. This variant edits an…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT Image 1.5 is OpenAI's image generation model that takes text and image input, with improved instruction following and prompt adherence over earlier GPT Image models. This variant edits an existing image from a text instruction, including inpainting with a mask."},{"id":"openai/gpt-image-2","routeId":"gpt-image-2","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-04-21","displayName":"GPT Image 2","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-2","outputPriceLabel":"from $0.27/image","shortDescription":"GPT Image 2 is OpenAI's image generation and editing model for fast, high-quality output, taking text and image input with flexible output sizes. This variant generates images from a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT Image 2 is OpenAI's image generation and editing model for fast, high-quality output, taking text and image input with flexible output sizes. This variant generates images from a text prompt."},{"id":"openai/gpt-image-2-edit","routeId":"gpt-image-2-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-04-21","displayName":"GPT Image 2","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-2-edit","outputPriceLabel":"from $0.34/edit","shortDescription":"GPT Image 2 is OpenAI's image generation and editing model for fast, high-quality output, taking text and image input with flexible output sizes. This variant edits an existing image from a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT Image 2 is OpenAI's image generation and editing model for fast, high-quality output, taking text and image input with flexible output sizes. This variant edits an existing image from a text instruction, with high-fidelity image inputs and inpainting."},{"id":"openai/gpt-image-2.5-flare","routeId":"gpt-image-2-5-flare","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-08","displayName":"GPT Image 2.5 Flare","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-2.5-flare","outputPriceLabel":"from $0.07/image","shortDescription":"GPT Image 2.5 Flare is the speed-focused model in OpenAI's GPT Image 2.5 release, built for high-quality everyday image generation from text and image input. This variant generates images from a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT Image 2.5 Flare is the speed-focused model in OpenAI's GPT Image 2.5 release, built for high-quality everyday image generation from text and image input. This variant generates images from a text prompt."},{"id":"openai/gpt-image-2.5-flare-edit","routeId":"gpt-image-2-5-flare-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-08","displayName":"GPT Image 2.5 Flare","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-2.5-flare-edit","outputPriceLabel":"from $0.08/edit","shortDescription":"GPT Image 2.5 Flare is the speed-focused model in OpenAI's GPT Image 2.5 release, built for high-quality everyday image generation from text and image input. This variant edits an existing image from…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT Image 2.5 Flare is the speed-focused model in OpenAI's GPT Image 2.5 release, built for high-quality everyday image generation from text and image input. This variant edits an existing image from a text instruction, including inpainting."},{"id":"openai/gpt-image-2.5-sunburst","routeId":"gpt-image-2-5-sunburst","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-08","displayName":"GPT Image 2.5 Sunburst","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-2.5-sunburst","outputPriceLabel":"from $0.07/image","shortDescription":"GPT Image 2.5 Sunburst is the detail-focused model in OpenAI's GPT Image 2.5 release, aimed at image generation and editing work where editing precision matters, from text and image input. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT Image 2.5 Sunburst is the detail-focused model in OpenAI's GPT Image 2.5 release, aimed at image generation and editing work where editing precision matters, from text and image input. This variant generates images from a text prompt."},{"id":"openai/gpt-image-2.5-sunburst-edit","routeId":"gpt-image-2-5-sunburst-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-08","displayName":"GPT Image 2.5 Sunburst","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"openai/gpt-image-2.5-sunburst-edit","outputPriceLabel":"from $0.08/edit","shortDescription":"GPT Image 2.5 Sunburst is the detail-focused model in OpenAI's GPT Image 2.5 release, aimed at image generation and editing work where editing precision matters, from text and image input. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"GPT Image 2.5 Sunburst is the detail-focused model in OpenAI's GPT Image 2.5 release, aimed at image generation and editing work where editing precision matters, from text and image input. This variant edits an existing image from a text instruction, including inpainting."},{"id":"pixverse/pixverse-c1-i2v","routeId":"pixverse-c1-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-11","displayName":"PixVerse C1","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"pixverse/pixverse-c1-i2v","outputPriceLabel":"Varies","shortDescription":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant animates a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant animates a source image guided by a text prompt."},{"id":"pixverse/pixverse-c1-r2v","routeId":"pixverse-c1-reference-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-11","displayName":"PixVerse C1 R2V","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"pixverse/pixverse-c1-r2v","outputPriceLabel":"Varies","shortDescription":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant uses…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant uses reference images and a text prompt to keep characters and scenes consistent across shots."},{"id":"pixverse/pixverse-c1-t2v","routeId":"pixverse-c1-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-11","displayName":"PixVerse C1","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"pixverse/pixverse-c1-t2v","outputPriceLabel":"Varies","shortDescription":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant generates video from a text prompt."},{"id":"pixverse/pixverse-c1-transition","routeId":"pixverse-c1-transition","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-11","displayName":"PixVerse C1 Transition","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"pixverse/pixverse-c1-transition","outputPriceLabel":"Varies","shortDescription":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant generates…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"PixVerse C1 is PixVerse's video model built for film production, with action and visual-effects rendering, storyboard-to-video and native audio, at up to 1080p and 15 seconds. This variant generates a video that moves from a first-frame image to a last-frame image, guided by a text prompt."},{"id":"pixverse/pixverse-v5.6-i2v","routeId":"pixverse-v5.6-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-01-27","displayName":"PixVerse V5.6","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"pixverse/pixverse-v5.6-i2v","outputPriceLabel":"Varies","shortDescription":"PixVerse V5.6 is a PixVerse video generation model, released in January 2026, that can generate audio and multiple shots within one clip at up to 1080p. This variant animates a source image guided by…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"PixVerse V5.6 is a PixVerse video generation model, released in January 2026, that can generate audio and multiple shots within one clip at up to 1080p. This variant animates a source image guided by a text prompt."},{"id":"pixverse/pixverse-v5.6-t2v","routeId":"pixverse-v5.6-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-01-27","displayName":"PixVerse V5.6","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"pixverse/pixverse-v5.6-t2v","outputPriceLabel":"Varies","shortDescription":"PixVerse V5.6 is a PixVerse video generation model, released in January 2026, that can generate audio and multiple shots within one clip at up to 1080p. This variant generates video from a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"PixVerse V5.6 is a PixVerse video generation model, released in January 2026, that can generate audio and multiple shots within one clip at up to 1080p. This variant generates video from a text prompt."},{"id":"pixverse/pixverse-v5.6-transition","routeId":"pixverse-v5.6-transition","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-01-27","displayName":"PixVerse V5.6 Transition","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"pixverse/pixverse-v5.6-transition","outputPriceLabel":"Varies","shortDescription":"PixVerse V5.6 is a PixVerse video generation model, released in January 2026, that can generate audio and multiple shots within one clip at up to 1080p. This variant generates a video that moves from…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"PixVerse V5.6 is a PixVerse video generation model, released in January 2026, that can generate audio and multiple shots within one clip at up to 1080p. This variant generates a video that moves from a first-frame image to a last-frame image, guided by a text prompt."},{"id":"qwen/qwen-image-2-edit","routeId":"qwen-image-2-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-03-04","displayName":"Qwen Image 2.0","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2-edit","outputPriceLabel":"$0.05/edit","shortDescription":"Qwen-Image-2.0 is an image model from Alibaba's Qwen team that unifies generation and editing in one smaller, faster model, with instructions up to 1K tokens for infographics and native 2K…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen-Image-2.0 is an image model from Alibaba's Qwen team that unifies generation and editing in one smaller, faster model, with instructions up to 1K tokens for infographics and native 2K resolution. This variant edits images from a text instruction, including in-image text edits, object changes, style transfer and multi-image fusion."},{"id":"qwen/qwen-image-2-pro-edit","routeId":"qwen-image-2-pro-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-03-04","displayName":"Qwen Image 2.0 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2-pro-edit","outputPriceLabel":"$0.10/edit","shortDescription":"Qwen-Image-2.0 Pro is the Pro tier of Qwen-Image-2.0, an image model from Alibaba's Qwen team that unifies generation and editing at native 2K resolution. This variant edits images from a text…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen-Image-2.0 Pro is the Pro tier of Qwen-Image-2.0, an image model from Alibaba's Qwen team that unifies generation and editing at native 2K resolution. This variant edits images from a text instruction, including in-image text edits, object changes, style transfer and multi-image fusion."},{"id":"qwen/qwen-image-2.1-pro-edit","routeId":"qwen-image-2-1-pro-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-09-20","displayName":"Qwen Image 2.1 Pro","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2.1-pro-edit","outputPriceLabel":"$0.05/edit","shortDescription":"Qwen-Image-2.1 Pro is the Pro tier of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen-Image-2.1 Pro is the Pro tier of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant edits images from a text instruction, with local edits guided by masks or painted annotations."},{"id":"qwen/qwen-image-2.1-turbo-edit","routeId":"qwen-image-2-1-turbo-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-10-09","displayName":"Qwen Image 2.1 Turbo","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-2.1-turbo-edit","outputPriceLabel":"$0.02/edit","shortDescription":"Qwen-Image-2.1 Turbo is an accelerated 8-step checkpoint of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen-Image-2.1 Turbo is an accelerated 8-step checkpoint of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant edits an existing image from a text instruction, including multi-reference composition."},{"id":"qwen/qwen-image-3-edit","routeId":"qwen-image-3-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-08-05","displayName":"Qwen Image 3.0","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-3-edit","outputPriceLabel":"$0.04/edit","shortDescription":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders text as small as 10px, with native text in 12 languages. This standard tier is a faster version of Qwen-Image-3.0 Pro. This variant edits an existing image from a text instruction."},{"id":"qwen/qwen-image-3-pro","routeId":"qwen-image-3-pro","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-07-16","displayName":"Qwen Image 3.0 Pro","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-3-pro","outputPriceLabel":"from $0.05/image","shortDescription":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders text as small as 10px, with native text in 12 languages. This variant is the Pro tier and generates images from a text prompt."},{"id":"qwen/qwen-image-3-pro-edit","routeId":"qwen-image-3-pro-edit","features":[],"provider":"venice","modalities":["image"],"moderation":"unknown","releasedAt":"2026-07-16","displayName":"Qwen Image 3.0 Pro","pricingNote":"Price varies by resolution or quality tier.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"image","providerRouteId":"qwen/qwen-image-3-pro-edit","outputPriceLabel":"from $0.05/edit","shortDescription":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://www.alibabacloud.com/help/en/model-studio/models","label":"Model source"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders text as small as 10px, with native text in 12 languages. This variant is the Pro tier and edits an existing image from a text instruction."},{"id":"runway/runway-gen-4-turbo","routeId":"runway-gen4-turbo","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-01-22","displayName":"Runway Gen-4 Turbo","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"runway/runway-gen-4-turbo","outputPriceLabel":"Varies","shortDescription":"Runway Gen-4 Turbo is Runway's faster version of its Gen-4 video model. It animates a starting image, used as the first frame, into a 2 to 10 second video guided by a text prompt.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Runway Gen-4 Turbo is Runway's faster version of its Gen-4 video model. It animates a starting image, used as the first frame, into a 2 to 10 second video guided by a text prompt."},{"id":"runway/runway-gen-4.5-i2v","routeId":"runway-gen4-5","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-04-12","displayName":"Runway Gen-4.5","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"runway/runway-gen-4.5","outputPriceLabel":"Varies","shortDescription":"Runway Gen-4.5 is Runway's video generation model, released in December 2025, built for prompt adherence, physical accuracy and visual styles from photorealistic to stylized. This variant animates a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Runway Gen-4.5 is Runway's video generation model, released in December 2025, built for prompt adherence, physical accuracy and visual styles from photorealistic to stylized. This variant animates a source image, used as the first frame, into a 2 to 10 second video guided by a text prompt."},{"id":"runway/runway-gen-4.5-t2v","routeId":"runway-gen4-5-text","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-12","displayName":"Runway Gen-4.5","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"runway/runway-gen-4.5-ay-gen4-5-text-2","outputPriceLabel":"Varies","shortDescription":"Runway Gen-4.5 is Runway's video generation model, released in December 2025, built for prompt adherence, physical accuracy and visual styles from photorealistic to stylized. This variant generates a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Runway Gen-4.5 is Runway's video generation model, released in December 2025, built for prompt adherence, physical accuracy and visual styles from photorealistic to stylized. This variant generates a 2 to 10 second video from a text prompt alone."},{"id":"sonilo/sonilo-v1.1-music","routeId":"sonilo-v1-1-music","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-07-21","displayName":"Sonilo V1.1 Music","pricingNote":"Priced per second of generated audio.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"venice/sonilo-v1.1-music","outputPriceLabel":"$0.17/min","shortDescription":"Generate licensed, commercial-use-safe music with precise control over style, mood, instrumentation, and duration.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Generate licensed, commercial-use-safe music with precise control over style, mood, instrumentation, and duration."},{"id":"sonilo/sonilo-v1.1-sound-effects","routeId":"sonilo-v1-1-sound-effects","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-07-21","displayName":"Sonilo V1.1 Sound Effects","pricingNote":"Priced per second of generated audio.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"venice/sonilo-v1.1-sound-effects","outputPriceLabel":"$0.12/min","shortDescription":"Generate licensed, commercial-use-safe sound effects with precise control over type, texture, intensity, and duration.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Generate licensed, commercial-use-safe sound effects with precise control over type, texture, intensity, and duration."},{"id":"stabilityai/stable-audio-2.5","routeId":"stable-audio-25","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-02-22","displayName":"Stable Audio 2.5","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"audio","providerRouteId":"stabilityai/stable-audio-2.5","outputPriceLabel":"$0.19/track","shortDescription":"Fast, lightweight audio generation for sound effects, ambient textures, and short musical clips. Flexible duration from 5 seconds to over 3 minutes.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Fast, lightweight audio generation for sound effects, ambient textures, and short musical clips. Flexible duration from 5 seconds to over 3 minutes."},{"id":"topaz-labs/topaz-video-upscale","routeId":"topaz-video-upscale","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-04-03","displayName":"Topaz Video Upscale","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"venice/topaz-video-upscale","outputPriceLabel":"Varies","shortDescription":"Topaz Video Upscale is a video enhancement model from Topaz Labs that upscales an existing video to a higher resolution, up to 4K, while reducing noise and sharpening detail.","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Topaz Video Upscale is a video enhancement model from Topaz Labs that upscales an existing video to a higher resolution, up to 4K, while reducing noise and sharpening detail."},{"id":"typesafe-ai/jev-system-one","routeId":"jev-latest","features":[],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2026-09-18","statusNote":"Beta","displayName":"Jev (System One)","availability":"preview","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","primaryModality":"text","providerRouteId":"venice/jev-system-one","shortDescription":"Jev (System One) is a decision model from TypeSafe AI that answers typed questions about a text state with calibrated probabilities. It returns structured choices, scores or yes/no probabilities…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Jev (System One) is a decision model from TypeSafe AI that answers typed questions about a text state with calibrated probabilities. It returns structured choices, scores or yes/no probabilities rather than generating chat, prose or code."},{"id":"vidu/vidu-q3-i2v","routeId":"vidu-q3-image-to-video","features":[],"provider":"venice","modalities":["image","video"],"moderation":"unknown","releasedAt":"2026-01-31","displayName":"Vidu Q3","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"vidu/vidu-q3-i2v","outputPriceLabel":"Varies","shortDescription":"Vidu Q3 is ShengShu Technology's video model that generates video and synchronized audio, including dialogue and sound effects, in one pass, with clips of up to 16 seconds at up to 1080p. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Vidu Q3 is ShengShu Technology's video model that generates video and synchronized audio, including dialogue and sound effects, in one pass, with clips of up to 16 seconds at up to 1080p. This variant animates a source image guided by a text prompt."},{"id":"vidu/vidu-q3-t2v","routeId":"vidu-q3-text-to-video","features":[],"provider":"venice","modalities":["video"],"moderation":"unknown","releasedAt":"2026-01-31","displayName":"Vidu Q3","pricingNote":"Video generation is priced per request by resolution and duration; see Venice pricing docs.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"–","primaryModality":"video","providerRouteId":"vidu/vidu-q3-t2v","outputPriceLabel":"Varies","shortDescription":"Vidu Q3 is ShengShu Technology's video model that generates video and synchronized audio, including dialogue and sound effects, in one pass, with clips of up to 16 seconds at up to 1080p. This…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Vidu Q3 is ShengShu Technology's video model that generates video and synchronized audio, including dialogue and sound effects, in one pass, with clips of up to 16 seconds at up to 1080p. This variant generates video from a text prompt."},{"id":"x-ai/xai-speech-to-text-v1","routeId":"stt-xai-v1","features":[],"provider":"venice","modalities":["audio"],"moderation":"unknown","releasedAt":"2026-04-18","displayName":"Grok Speech to Text","pricingNote":"Priced at $0.000031 per second of input audio.","availability":"available","privacyLevel":"anonymous","privacyNotes":["Venice obscures the caller's identity from the inference provider.","The inference provider can see prompt content and no provider zero-retention guarantee applies."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":null,"privacySummary":"Venice Anonymous routing","inputPriceLabel":"$0.00186/min","primaryModality":"audio","providerRouteId":"x-ai/xai-speech-to-text-v1","outputPriceLabel":"–","shortDescription":"Grok Speech to Text is xAI's speech recognition model for batch and real-time transcription in more than 25 languages. It returns word-level timestamps and supports speaker diarization, multichannel…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"}],"inputPriceUsdPerMillion":null,"outputPriceUsdPerMillion":null,"cacheReadPriceUsdPerMillion":null,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":false,"operationalAvailability":"temporarily_unavailable","description":"Grok Speech to Text is xAI's speech recognition model for batch and real-time transcription in more than 25 languages. It returns word-level timestamps and supports speaker diarization, multichannel audio, and formatting of numbers, dates and currencies in the transcript."},{"id":"~deepseek/deepseek-flash-latest","routeId":"deepseek-v4-1-flash-1017","features":["streaming","tool-calling","reasoning","vision","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","releasedAt":"2026-10-17","displayName":"DeepSeek Flash Latest","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":131072,"primaryModality":"text","providerRouteId":"deepseek/deepseek-v4.1-flash-1017","shortDescription":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text,…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017","label":"Model source"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.0075,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/deepseek-ai-deepseek-v4-1-flash-1017","routeId":"deepseek-ai/DeepSeek-V4.1-Flash-1017","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.006,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"This DeepInfra route is not in the reviewed endpoint manifest and cannot be enabled.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-1-flash-1017","routeId":"deepseek-ai/DeepSeek-V4.1-Flash-1017","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.2,"outputPriceUsdPerMillion":0.6,"cacheReadPriceUsdPerMillion":0.008,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/deepseek-v4-1-flash-1017","routeId":"DeepSeek-V4.1-Flash-1017","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.13,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.003,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-1-flash-1017","routeId":"deepseek-v4.1-flash-1017","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.075,"outputPriceUsdPerMillion":0.3,"cacheReadPriceUsdPerMillion":0.0015,"cacheWritePriceUsdPerMillion":0.075,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-1-flash-1017","routeId":"deepseek-v4.1-flash-1017","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.42,"cacheReadPriceUsdPerMillion":0.0021,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.","alias":{"id":"~deepseek/deepseek-flash-latest","creator":"deepseek","displayName":"DeepSeek Flash Latest","family":"DeepSeek Flash","targetModelId":"deepseek/deepseek-v4.1-flash-1017","revision":2,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"deepseek/deepseek-v4.1-flash","recordedAt":"2026-10-16","note":"Initial reviewed target"},{"revision":2,"targetModelId":"deepseek/deepseek-v4.1-flash-1017","recordedAt":"2026-10-19","note":"Updated to DeepSeek V4.1 Flash 1017, released October 17."}],"targetModelName":"DeepSeek v4.1 Flash (1017)"}},{"id":"~deepseek/deepseek-pro-latest","routeId":"deepseek-v4-pro-0813","features":["streaming","tool-calling","reasoning","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":false,"supported":true,"canDisable":true,"defaultEffort":"high","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-08-14","displayName":"DeepSeek Pro Latest","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1000000,"privacySummary":"Venice Private routing","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"deepseek/deepseek-v4-pro-0813","shortDescription":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","label":"Model source"}],"inputPriceUsdPerMillion":1.65,"outputPriceUsdPerMillion":4.95,"cacheReadPriceUsdPerMillion":0.165,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":2.6,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (priority 1.5x, flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1.32,"outputPriceUsdPerMillion":3.96,"cacheReadPriceUsdPerMillion":0.132,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.5,"outputPriceUsdPerMillion":2,"cacheReadPriceUsdPerMillion":0.05,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/deepseek-ai-deepseek-v4-pro-0813","routeId":"deepseek-ai/DeepSeek-V4-Pro-0813","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.92,"outputPriceUsdPerMillion":2.77,"cacheReadPriceUsdPerMillion":0.04,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/deepseek-v4-pro-0813","routeId":"deepseek-v4-pro-0813","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.553184,"outputPriceUsdPerMillion":1.659553,"cacheReadPriceUsdPerMillion":0.018439,"cacheWritePriceUsdPerMillion":0.553184,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/deepseek-v4-pro-0813","routeId":"deepseek-v4-pro-0813","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.462,"outputPriceUsdPerMillion":1.386,"cacheReadPriceUsdPerMillion":0.0154,"cacheWritePriceUsdPerMillion":0.462,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.","alias":{"id":"~deepseek/deepseek-pro-latest","creator":"deepseek","displayName":"DeepSeek Pro Latest","family":"DeepSeek Pro","targetModelId":"deepseek/deepseek-v4-pro-0813","revision":1,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"deepseek/deepseek-v4-pro-0813","recordedAt":"2026-10-16","note":"Initial reviewed target"}],"targetModelName":"DeepSeek V4 Pro 0813"}},{"id":"~moonshotai/kimi-latest","routeId":"kimi-k3","features":["streaming","tool-calling","vision","reasoning","confidential-compute"],"provider":"tinfoil","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"max","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text","image"],"moderation":"unknown","displayName":"Kimi Latest","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/kimi-k3","shortDescription":"Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text,…","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"}],"inputPriceUsdPerMillion":4,"outputPriceUsdPerMillion":20,"cacheReadPriceUsdPerMillion":0.8,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"phala-ai","providerName":"Phala AI","providerRouteId":"phala-ai/kimi-k3","routeId":"moonshotai/kimi-k3","privacyLevel":"tee","privacySummary":"Verified gateway and pinned confidential model session","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Phala AI pricing in USD per 1M tokens, converted from its per-token list price.","contextTokens":1048576,"maxOutputTokens":1048576,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.phala.com/phala-cloud/confidential-ai/overview","label":"Phala Confidential AI overview"},{"url":"https://inference.phala.com/v1/models","label":"Phala AI models"},{"url":"https://huggingface.co/moonshotai/Kimi-K3","label":"Creator model card"}]},{"provider":"venice","providerName":"Venice","providerRouteId":"moonshotai/kimi-k3","routeId":"kimi-k3","privacyLevel":"private","privacySummary":"Venice Private routing","inputPriceUsdPerMillion":3.75,"outputPriceUsdPerMillion":18.75,"cacheReadPriceUsdPerMillion":0.375,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/moonshotai/Kimi-K3","label":"Model source"}]},{"provider":"fireworks","providerName":"Fireworks AI","providerRouteId":"fireworks/kimi-k3","routeId":"accounts/fireworks/models/kimi-k3","privacyLevel":"private","privacySummary":"Fireworks zero-data-retention routing","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Fireworks Standard serverless pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.fireworks.ai/serverless/pricing","label":"Fireworks serverless pricing"},{"url":"https://docs.fireworks.ai/guides/security_compliance/data_handling","label":"Fireworks zero data retention"},{"url":"https://docs.fireworks.ai/serverless/overview","label":"Fireworks serverless models"}]},{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/moonshotai-kimi-k3","routeId":"moonshotai/Kimi-K3","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":2.85,"outputPriceUsdPerMillion":14.25,"cacheReadPriceUsdPerMillion":0.285,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Explicit cache-write multipliers (5m 1.25x, 1h 2x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/moonshotai-kimi-k3","routeId":"moonshotai/Kimi-K3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/moonshotai-kimi-k3","routeId":"moonshotai/kimi-k3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":2.4,"outputPriceUsdPerMillion":14,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/moonshotai-kimi-k3","routeId":"moonshotai/Kimi-K3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":12.5,"cacheReadPriceUsdPerMillion":0.25,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/kimi-k3","routeId":"Kimi-K3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":3,"outputPriceUsdPerMillion":15,"cacheReadPriceUsdPerMillion":0.3,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/kimi-k3","routeId":"kimi-k3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.95,"outputPriceUsdPerMillion":9.75,"cacheReadPriceUsdPerMillion":0.195,"cacheWritePriceUsdPerMillion":1.95,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/kimi-k3","routeId":"kimi-k3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.1113,"outputPriceUsdPerMillion":13.125,"cacheReadPriceUsdPerMillion":0.1043,"cacheWritePriceUsdPerMillion":0.1113,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"moonshotai/kimi-k3-e2ee","routeId":"e2ee-kimi-k3-p","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":3.75,"outputPriceUsdPerMillion":18.75,"cacheReadPriceUsdPerMillion":0.375,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/moonshotai/Kimi-K3","label":"Model source"}]}],"description":"Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.","alias":{"id":"~moonshotai/kimi-latest","creator":"moonshotai","displayName":"Kimi Latest","family":"Kimi","targetModelId":"moonshotai/kimi-k3","revision":1,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"moonshotai/kimi-k3","recordedAt":"2026-10-16","note":"Initial reviewed target"}],"targetModelName":"Kimi K3"}},{"id":"~z-ai/glm-latest","routeId":"glm-5-3","features":["streaming","tool-calling","reasoning","code-optimized","confidential-compute"],"provider":"tinfoil","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":"max","supportedEfforts":["low","high","max"],"effortConfigurable":true},"modalities":["text"],"moderation":"unknown","displayName":"GLM Latest","pricingNote":"Tinfoil pricing in USD per 1M tokens.","availability":"available","privacyLevel":"tee","privacyNotes":["Tinfoil's official SDK authenticates the router's signed release and hardware report and confirms that the signed code measurement matches the live router enclave. The router forwards to its verified model enclaves, which use AMD SEV-SNP or Intel TDX. This route is SDK-verified; AnonRouter does not independently verify every serving GPU or model weight.","AnonRouter pins every inference TLS connection's observed certificate key to the public-key fingerprint carried in that verified hardware report. The enclave sees plaintext prompts and generations: this is a TEE guarantee, not end-to-end encryption.","Tinfoil also offers an HPKE (EHBP) body-encryption transport, but its model selector is inside the ciphertext and the documented outer metadata cannot bind it to an AnonRouter ticket and reservation; AnonRouter therefore fails closed and exposes only the standard TEE route."],"providerName":"Tinfoil","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"Tinfoil SDK-verified confidential enclave","maxOutputTokens":32768,"primaryModality":"text","providerRouteId":"tinfoil/glm-5.3","shortDescription":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.","sourceReferences":[{"url":"https://docs.tinfoil.sh/verification/attestation-architecture","label":"Tinfoil attestation architecture"},{"url":"https://inference.tinfoil.sh/v1/models","label":"Tinfoil models"},{"url":"https://huggingface.co/zai-org/GLM-5.3","label":"Creator model card"}],"inputPriceUsdPerMillion":1.8,"outputPriceUsdPerMillion":5.75,"cacheReadPriceUsdPerMillion":0.45,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/zai-org-glm-5-3","routeId":"zai-org/GLM-5.3","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.9,"outputPriceUsdPerMillion":4,"cacheReadPriceUsdPerMillion":0.2,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":1048576,"maxOutputTokens":16384,"availability":"needs-verification","callable":true,"statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/zai-org-glm-5-3","routeId":"zai-org/GLM-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.14,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/z-ai-glm-5-3","routeId":"z-ai/glm-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.75,"outputPriceUsdPerMillion":2.4,"cacheReadPriceUsdPerMillion":0.075,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/zai-org-glm-5-3","routeId":"zai-org/GLM-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.98,"outputPriceUsdPerMillion":3.08,"cacheReadPriceUsdPerMillion":0.18,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/glm-5-3","routeId":"GLM-5.3","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.4,"cacheReadPriceUsdPerMillion":0.26,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3","routeId":"z-ai-glm-5-3","privacyLevel":"anonymous","privacySummary":"Anonymous route","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":5.5,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5.3","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5-3","routeId":"glm-5.3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.77,"outputPriceUsdPerMillion":2.42,"cacheReadPriceUsdPerMillion":0.143,"cacheWritePriceUsdPerMillion":0.77,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5-3","routeId":"glm-5.3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.04893,"outputPriceUsdPerMillion":0.98,"cacheReadPriceUsdPerMillion":0.04823,"cacheWritePriceUsdPerMillion":0.04893,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3-e2ee","routeId":"e2ee-glm-5-3-p","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":1.75,"outputPriceUsdPerMillion":5.5,"cacheReadPriceUsdPerMillion":0.325,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/zai-org/GLM-5.3","label":"Model source"}]}],"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.","alias":{"id":"~z-ai/glm-latest","creator":"z-ai","displayName":"GLM Latest","family":"GLM","targetModelId":"z-ai/glm-5.3","revision":1,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"z-ai/glm-5.3","recordedAt":"2026-10-16","note":"Initial reviewed target"}],"targetModelName":"GLM 5.3"}},{"id":"~z-ai/glm-flash-latest","routeId":"zai-org/GLM-5.3-Flash","features":["streaming","tool-calling","vision","video-input","reasoning","prompt-caching"],"provider":"deepinfra","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":["low","medium","high"],"effortConfigurable":true},"modalities":["text","image","video"],"moderation":"unknown","statusNote":"DeepInfra changed identity, capability, privacy, context, or pricing metadata after this route was reviewed; re-audit is required.","displayName":"GLM Flash Latest","pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens.","availability":"needs-verification","privacyLevel":"private","privacyNotes":["DeepInfra states inference inputs and outputs are held only in memory during the request and deleted afterward; they are not written to disk.","DeepInfra says it generally does not log request content, logging only metadata such as request id, cost, and sampling parameters, and reserves the right to log a small fraction of requests for debugging or security.","This is a DeepInfra-hosted route (is_partner=false), not a partner endpoint that forwards the request to another model provider."],"providerName":"DeepInfra","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":1048576,"privacySummary":"DeepInfra in-memory inference, no post-request retention","maxOutputTokens":16384,"primaryModality":"text","providerRouteId":"deepinfra/zai-org-glm-5-3-flash","shortDescription":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}],"inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"baseten","providerName":"Baseten","providerRouteId":"baseten/zai-org-glm-5-3-flash","routeId":"zai-org/GLM-5.3-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"relace","providerName":"Relace","providerRouteId":"relace/z-ai-glm-5-3-flash","routeId":"z-ai/glm-5.3-flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.075,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.0075,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"sail","providerName":"Sail","providerRouteId":"sail/zai-org-glm-5-3-flash","routeId":"zai-org/GLM-5.3-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.11,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.02,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Owner-reviewed price table in USD per 1M tokens.","contextTokens":1043334,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"wafer","providerName":"Wafer","providerRouteId":"wafer/glm-5-3-flash","routeId":"GLM-5.3-Flash","privacyLevel":"private","privacySummary":"Private route","inputPriceUsdPerMillion":0.05,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3-flash","routeId":"z-ai-glm-5-3-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route","inputPriceUsdPerMillion":0.15,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.03,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/zai-org/GLM-5.3-Flash","label":"Model source"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/glm-5-3-flash","routeId":"glm-5.3-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.06,"outputPriceUsdPerMillion":0.2,"cacheReadPriceUsdPerMillion":0.012,"cacheWritePriceUsdPerMillion":0.06,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/glm-5-3-flash","routeId":"glm-5.3-flash","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.105,"outputPriceUsdPerMillion":0.35,"cacheReadPriceUsdPerMillion":0.021,"cacheWritePriceUsdPerMillion":0.105,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"venice","providerName":"Venice","providerRouteId":"z-ai/glm-5.3-flash-e2ee","routeId":"e2ee-glm-5-3-flash","privacyLevel":"e2ee","privacySummary":"End-to-end encrypted inference","inputPriceUsdPerMillion":0.16,"outputPriceUsdPerMillion":0.54,"cacheReadPriceUsdPerMillion":0.038,"cacheWritePriceUsdPerMillion":null,"pricingNote":"USD per 1M tokens from the Venice models API.","contextTokens":1000000,"maxOutputTokens":32768,"availability":"available","callable":false,"sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://docs.venice.ai/guides/features/tee-e2ee-models","label":"Venice TEE/E2EE"},{"url":"https://huggingface.co/zai-org/GLM-5.3-Flash","label":"Model source"}]},{"provider":"near-ai","providerName":"NEAR AI","providerRouteId":"near-ai/glm-5.3-flash","routeId":"z-ai/glm-5.3-flash","privacyLevel":"e2ee","privacySummary":"Direct TLS-in-TEE enclave (Intel TDX + NVIDIA CC)","inputPriceUsdPerMillion":0.08,"outputPriceUsdPerMillion":0.5,"cacheReadPriceUsdPerMillion":0.012,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Pricing in USD per 1M tokens.","contextTokens":1048576,"maxOutputTokens":1048576,"availability":"available","callable":false,"sourceReferences":[]}],"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","alias":{"id":"~z-ai/glm-flash-latest","creator":"z-ai","displayName":"GLM Flash Latest","family":"GLM Flash","targetModelId":"z-ai/glm-5.3-flash","revision":1,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"z-ai/glm-5.3-flash","recordedAt":"2026-10-16","note":"Initial reviewed target"}],"targetModelName":"GLM 5.3 Flash"}},{"id":"~minimax/minimax-latest","routeId":"minimax-m3-preview","features":["streaming","tool-calling","reasoning","vision","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text","image","video"],"moderation":"unknown","releasedAt":"2026-06-12","displayName":"MiniMax Latest","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":524288,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"minimax/minimax-m3-preview","shortDescription":"MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/MiniMaxAI/MiniMax-M3","label":"Model source"}],"inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1.2,"cacheReadPriceUsdPerMillion":0.06,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/minimaxai-minimax-m3","routeId":"MiniMaxAI/MiniMax-M3","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.28,"outputPriceUsdPerMillion":1.1,"cacheReadPriceUsdPerMillion":0.056,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":524288,"maxOutputTokens":512000,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/minimax-m3","routeId":"minimax-m3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.225,"outputPriceUsdPerMillion":0.9,"cacheReadPriceUsdPerMillion":0.09,"cacheWritePriceUsdPerMillion":0.45,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m3","routeId":"minimax-m3","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.042,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":200000,"maxOutputTokens":32768,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/minimax-m3-preview","routeId":"minimax-m3-preview","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.21,"outputPriceUsdPerMillion":0.84,"cacheReadPriceUsdPerMillion":0.042,"cacheWritePriceUsdPerMillion":0.21,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":524288,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"MiniMax-M3 is MiniMax's natively multimodal Mixture-of-Experts model with about 428B total and 23B active parameters. It takes text, image and video input and produces text, with a context window of up to 1M tokens, and can also operate a desktop computer.","alias":{"id":"~minimax/minimax-latest","creator":"minimax","displayName":"MiniMax Latest","family":"MiniMax text models","targetModelId":"minimax/minimax-m3","revision":1,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"minimax/minimax-m3","recordedAt":"2026-10-16","note":"Initial reviewed target"}],"targetModelName":"MiniMax M3 Preview"}},{"id":"~qwen/qwen-latest","routeId":"qwen-3-8-2-4t-a95b","features":["streaming","tool-calling","reasoning","web-search","code-optimized","prompt-caching"],"provider":"venice","reasoning":{"alwaysOn":true,"supported":true,"canDisable":false,"defaultEffort":null,"supportedEfforts":[],"effortConfigurable":false},"modalities":["text"],"moderation":"unknown","releasedAt":"2026-08-12","displayName":"Qwen Latest","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":262144,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3.8-2.4t","shortDescription":"Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B","label":"Model source"}],"inputPriceUsdPerMillion":2.5,"outputPriceUsdPerMillion":7.5,"cacheReadPriceUsdPerMillion":0.3125,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"cheaperinference","providerName":"Cheaper Inference","providerRouteId":"cheaperinference/qwen3-8-2-4t-a95b","routeId":"qwen3.8-2.4t-a95b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.3,"outputPriceUsdPerMillion":3.9,"cacheReadPriceUsdPerMillion":0.1625,"cacheWritePriceUsdPerMillion":1.625,"pricingNote":"Provider list pricing in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-8-2-4t-a95b","routeId":"qwen3.8-2.4t-a95b","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":1.4,"outputPriceUsdPerMillion":4.2,"cacheReadPriceUsdPerMillion":0.175,"cacheWritePriceUsdPerMillion":1.4,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":1000000,"maxOutputTokens":131072,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.","alias":{"id":"~qwen/qwen-latest","creator":"qwen","displayName":"Qwen Latest","family":"Qwen flagship text models","targetModelId":"qwen/qwen-3.8-2.4t","revision":1,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"qwen/qwen-3.8-2.4t","recordedAt":"2026-10-16","note":"Initial reviewed target"}],"targetModelName":"Qwen 3.8 2.4T"}},{"id":"~qwen/qwen-coder-latest","routeId":"qwen3-coder-480b-a35b-instruct-turbo","features":["streaming","tool-calling","json-schema","web-search","code-optimized","prompt-caching"],"provider":"venice","modalities":["text"],"moderation":"unknown","releasedAt":"2026-01-27","displayName":"Qwen Coder Latest","pricingNote":"USD per 1M tokens from the Venice models API.","availability":"available","privacyLevel":"private","privacyNotes":["Venice lists this route as Private.","Prompt and response content is processed for inference and not retained after completion."],"providerName":"Venice","routingModes":["anonrouter-hosted","provider-direct"],"contextTokens":256000,"privacySummary":"Venice Private routing","maxOutputTokens":65536,"primaryModality":"text","providerRouteId":"qwen/qwen-3-coder-480b-turbo","shortDescription":"Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a…","sourceReferences":[{"url":"https://docs.venice.ai/overview/pricing","label":"Venice pricing"},{"url":"https://docs.venice.ai/overview/privacy","label":"Venice privacy"},{"url":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","label":"Model source"}],"inputPriceUsdPerMillion":0.35,"outputPriceUsdPerMillion":1.5,"cacheReadPriceUsdPerMillion":0.04,"cacheWritePriceUsdPerMillion":null,"updatedAt":"2026-10-27","callable":true,"operationalAvailability":"available","additionalProviderRoutes":[{"provider":"deepinfra","providerName":"DeepInfra","providerRouteId":"deepinfra/qwen-qwen3-coder-480b-a35b-instruct-turbo","routeId":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","privacyLevel":"private","privacySummary":"DeepInfra in-memory inference, no post-request retention","inputPriceUsdPerMillion":0.3,"outputPriceUsdPerMillion":1,"cacheReadPriceUsdPerMillion":0.1,"cacheWritePriceUsdPerMillion":null,"pricingNote":"Standard DeepInfra serverless pricing in USD per 1M tokens. Published optional service-tier multipliers (flex 0.8x) are not exposed by AnonRouter.","contextTokens":262144,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[{"url":"https://deepinfra.com/pricing","label":"DeepInfra pricing"},{"url":"https://docs.deepinfra.com/account/data-privacy","label":"DeepInfra data privacy"},{"url":"https://deepinfra.com/models","label":"DeepInfra models"}]},{"provider":"surplusintelligence","providerName":"Surplus Intelligence","providerRouteId":"surplusintelligence/qwen3-coder-turbo","routeId":"qwen3-coder-turbo","privacyLevel":"anonymous","privacySummary":"Anonymous route. The upstream service and its serving partners can read prompts and outputs; retention policies may vary.","inputPriceUsdPerMillion":0.245,"outputPriceUsdPerMillion":1.05,"cacheReadPriceUsdPerMillion":0.028,"cacheWritePriceUsdPerMillion":0.245,"pricingNote":"Provider list pricing less a fixed discount, in USD per 1M tokens.","contextTokens":256000,"maxOutputTokens":65536,"availability":"available","callable":true,"sourceReferences":[]}],"description":"Qwen 3 Coder 480B Turbo is a faster serving variant of Qwen3 Coder 480B A35B Instruct, Alibaba's Qwen team's Mixture-of-Experts coding model with 480B total and 35B active parameters. The model has a native 262K-token context window and is built for agentic coding, tool calling and repository-scale work.","alias":{"id":"~qwen/qwen-coder-latest","creator":"qwen","displayName":"Qwen Coder Latest","family":"Qwen Coder","targetModelId":"qwen/qwen-3-coder-480b-turbo","revision":1,"updatePolicy":"latest-reviewed-stable","history":[{"revision":1,"targetModelId":"qwen/qwen-3-coder-480b-turbo","recordedAt":"2026-10-16","note":"Initial reviewed target"}],"targetModelName":"Qwen 3 Coder 480B Turbo"}}],"routers":[{"id":"anonrouter/cheap","kind":"paid","displayName":"Cheap Router","description":"Picks the lowest-cost model that can handle each request.","models":["aion-labs/aion-3.0","aion-labs/aion-3.0-mini","aion-labs/aion-3.5","aion-labs/aion-3.5-mini","anthropic/claude-fable-5","anthropic/claude-fable-5.1","anthropic/claude-haiku-4-5","anthropic/claude-haiku-5.5","anthropic/claude-opus-4.5","anthropic/claude-opus-4.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.8","anthropic/claude-opus-4.8-fast","anthropic/claude-opus-5","anthropic/claude-opus-5-fast","anthropic/claude-opus-5.5","anthropic/claude-opus-5.5-fast","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.6","anthropic/claude-sonnet-5","anthropic/claude-sonnet-5.5","bytedance/seed-1.8","bytedance/seed-2.0-code","bytedance/seed-2.0-mini","bytedance/seed-2.0-pro","bytedance/seed-2.1-turbo","deepseek/deepseek-r1-0528","deepseek/deepseek-v3","deepseek/deepseek-v3.1","deepseek/deepseek-v3.2","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731-fast","deepseek/deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-pro","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","deepseek/deepseek-v4.1-flash-1017","deepseek/deepseek-v4.1-flash-fast","deepseek/deepseek-v4.1-flash-uncensored","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-3-flash-preview","google/gemini-3.1-flash-lite","google/gemini-3.1-pro-preview","google/gemini-3.5-flash","google/gemini-3.5-flash-lite","google/gemini-3.6-flash","google/gemini-3.7-flash","google/gemini-3.8-flash","google/gemini-4-argon","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-3-4b-it","google/gemma-4-12b-it","google/gemma-4-26b-a4b-it","google/gemma-4-26b-a4b-uncensored","google/gemma-4-31b-instruct","google/gemma-4-31b-it-nvfp4","google/gemma-4-31b-it-turbo","google/gemma-4-31b-it-ultra","google/gemma-4-uncensored","ibm-granite/granite-4.2-8b","inception/mercury-2","inception/mercury-2.5","inception/mercury-3","inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-vl","inclusionai/ling-3.1-flash","meta/llama-3.1-8b-instruct-turbo","meta/llama-3.2-3b","meta/llama-3.3-70b","meta/llama-3.3-70b-instruct-turbo","meta/llama-4-scout-17b-16e-instruct","meta/llama-guard-4-12b","meta/muse-glimmer-30b","meta/muse-spark-1.1","meta/muse-spark-1.2","meta/muse-spark-1.3","meta/muse-spark-open","meta/muse-wonder","microsoft/phi-4","minimax/minimax-m2","minimax/minimax-m2.1","minimax/minimax-m2.5","minimax/minimax-m2.7","minimax/minimax-m3","minimax/minimax-m3.1-flash","mistralai/devstral-2-123b","mistralai/magistral-small-2509","mistralai/ministral-3-14b-instruct","mistralai/ministral-3-3b-instruct","mistralai/ministral-3-8b-instruct","mistralai/mistral-large-3-675b-instruct","mistralai/mistral-large-4","mistralai/mistral-nemo-instruct-2407","mistralai/mistral-small-24b-instruct-2501","mistralai/mistral-small-3.2-24b-instruct-2506","mistralai/mistral-small-4","mistralai/mistral-uncensored-1.2","mistralai/mistral-uncensored-roleplay","mistralai/voxtral-mini-3b-2507","mistralai/voxtral-small-24b-2507","moonshotai/kimi-k2-thinking","moonshotai/kimi-k2.5","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k3","moonshotai/kimi-k3-fast","moonshotai/kimi-k3.1-pro","moonshotai/kimi-k3.1-pro-highspeed","nousresearch/hermes-3-llama-3.1-405b","nvidia/nemotron-content-safety-3.5","nvidia/nvidia-nemotron-3-nano-30b","nvidia/nvidia-nemotron-3-super-120b-a12b","nvidia/nvidia-nemotron-3-ultra","nvidia/nvidia-nemotron-3.5-lightning","nvidia/nvidia-nemotron-3.5-super-vl","nvidia/nvidia-nemotron-nano-12b-v2-vl","nvidia/nvidia-nemotron-nano-9b-v2","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","openai/gpt-4o","openai/gpt-4o-mini","openai/gpt-5","openai/gpt-5-mini","openai/gpt-5-nano","openai/gpt-5.1","openai/gpt-5.2","openai/gpt-5.3-codex","openai/gpt-5.4","openai/gpt-5.4-mini","openai/gpt-5.4-nano","openai/gpt-5.4-pro","openai/gpt-5.5","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-sol","openai/gpt-5.6-sol-pro","openai/gpt-5.6-terra","openai/gpt-5.6-terra-pro","openai/gpt-6-astra","openai/gpt-6-astra-pro","openai/gpt-6-luna","openai/gpt-6-sol","openai/gpt-6.1-sol","openai/gpt-6.1-sol-ultrafast","openai/gpt-oss-120b","openai/gpt-oss-120b-ultra","openai/gpt-oss-20b","openai/gpt-oss-safeguard-120b","openai/gpt-oss-safeguard-20b","openai/o3","openai/o3-mini","openai/o4-mini","qwen/qwen-2.5-7b","qwen/qwen-3-235b-a22b-instruct-2507","qwen/qwen-3-235b-a22b-thinking-2507","qwen/qwen-3-coder-480b","qwen/qwen-3-coder-480b-turbo","qwen/qwen-3-next-80b","qwen/qwen-3.5-35b-a3b","qwen/qwen-3.5-397b","qwen/qwen-3.5-9b","qwen/qwen-3.6-27b","qwen/qwen-3.6-35b-a3b","qwen/qwen-3.6-plus-uncensored","qwen/qwen-3.7-max","qwen/qwen-3.7-plus","qwen/qwen-3.8-2.4t","qwen/qwen-3.8-27b","qwen/qwen-3.8-27b-uncensored","qwen/qwen-3.8-flash","qwen/qwen-3.8-max","qwen/qwen-3.8-omni-flash","qwen/qwen2.5-72b-instruct","qwen/qwen3-14b","qwen/qwen3-235b-a22b-instruct-2507","qwen/qwen3-30b-a3b","qwen/qwen3-32b","qwen/qwen3-coder-30b-a3b-instruct","qwen/qwen3-coder-480b-a35b-instruct","qwen/qwen3-coder-next","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3-vl-235b","qwen/qwen3-vl-235b-a22b-thinking","qwen/qwen3-vl-30b-a3b","qwen/qwen3-vl-30b-a3b-thinking","qwen/qwen3.5-27b","sao10k/l3-8b-lunaris-v1-turbo","sao10k/l3.1-70b-euryale-v2.2","stepfun-ai/step-5-preview","tencent/hy3","tencent/hy4-preview","thinking-machines/inkling","thinking-machines/inkling-small","venice/hy4-preview","writer/palmyra-vision-7b","x-ai/grok-4.20","x-ai/grok-4.20-multi-agent","x-ai/grok-4.3","x-ai/grok-4.5","x-ai/grok-4.6","x-ai/grok-4.7","x-ai/grok-build-0.1","xiaomi/mimo-v2.5","xiaomi/mimo-v2.6-flash","xiaomi/mimo-v2.6-pro","z-ai/glm-4.5","z-ai/glm-4.5-air","z-ai/glm-4.6","z-ai/glm-4.7","z-ai/glm-4.7-flash","z-ai/glm-4.7-flash-heretic","z-ai/glm-5","z-ai/glm-5-turbo","z-ai/glm-5.1","z-ai/glm-5.2","z-ai/glm-5.2-fast","z-ai/glm-5.3","z-ai/glm-5.3-fast","z-ai/glm-5.3-flash","z-ai/glm-5.3-uncensored","z-ai/glm-5v-turbo"],"privacyLevels":["anonymous","private","tee"],"defaultPrivacyLevels":["private","tee"],"pricing":{"anonymous":{"input":{"min":0.0126,"max":30},"output":{"min":0.063,"max":180}},"private":{"input":{"min":0.02,"max":4.5},"output":{"min":0.03,"max":22.5}},"tee":{"input":{"min":0.1,"max":4},"output":{"min":0.2,"max":20}}},"contextTokens":2000000,"maxOutputTokens":1048576,"capabilities":{"streaming":true,"tools":true,"vision":true}},{"id":"anonrouter/fast","kind":"paid","displayName":"Fast Router","description":"Picks the fastest model that can handle each request, using measured response times.","models":["aion-labs/aion-3.0","aion-labs/aion-3.0-mini","aion-labs/aion-3.5","aion-labs/aion-3.5-mini","anthropic/claude-fable-5","anthropic/claude-fable-5.1","anthropic/claude-haiku-4-5","anthropic/claude-haiku-5.5","anthropic/claude-opus-4.5","anthropic/claude-opus-4.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.8","anthropic/claude-opus-4.8-fast","anthropic/claude-opus-5","anthropic/claude-opus-5-fast","anthropic/claude-opus-5.5","anthropic/claude-opus-5.5-fast","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.6","anthropic/claude-sonnet-5","anthropic/claude-sonnet-5.5","bytedance/seed-1.8","bytedance/seed-2.0-code","bytedance/seed-2.0-mini","bytedance/seed-2.0-pro","bytedance/seed-2.1-turbo","deepseek/deepseek-r1-0528","deepseek/deepseek-v3","deepseek/deepseek-v3.1","deepseek/deepseek-v3.2","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731-fast","deepseek/deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-pro","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","deepseek/deepseek-v4.1-flash-1017","deepseek/deepseek-v4.1-flash-fast","deepseek/deepseek-v4.1-flash-uncensored","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-3-flash-preview","google/gemini-3.1-flash-lite","google/gemini-3.1-pro-preview","google/gemini-3.5-flash","google/gemini-3.5-flash-lite","google/gemini-3.6-flash","google/gemini-3.7-flash","google/gemini-3.8-flash","google/gemini-4-argon","google/gemma-3-12b-it","google/gemma-3-27b-it","google/gemma-3-4b-it","google/gemma-4-12b-it","google/gemma-4-26b-a4b-it","google/gemma-4-26b-a4b-uncensored","google/gemma-4-31b-instruct","google/gemma-4-31b-it-nvfp4","google/gemma-4-31b-it-turbo","google/gemma-4-31b-it-ultra","google/gemma-4-uncensored","ibm-granite/granite-4.2-8b","inception/mercury-2","inception/mercury-2.5","inception/mercury-3","inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-vl","inclusionai/ling-3.1-flash","meta/llama-3.1-8b-instruct-turbo","meta/llama-3.2-3b","meta/llama-3.3-70b","meta/llama-3.3-70b-instruct-turbo","meta/llama-4-scout-17b-16e-instruct","meta/llama-guard-4-12b","meta/muse-glimmer-30b","meta/muse-spark-1.1","meta/muse-spark-1.2","meta/muse-spark-1.3","meta/muse-spark-open","meta/muse-wonder","microsoft/phi-4","minimax/minimax-m2","minimax/minimax-m2.1","minimax/minimax-m2.5","minimax/minimax-m2.7","minimax/minimax-m3","minimax/minimax-m3.1-flash","mistralai/devstral-2-123b","mistralai/magistral-small-2509","mistralai/ministral-3-14b-instruct","mistralai/ministral-3-3b-instruct","mistralai/ministral-3-8b-instruct","mistralai/mistral-large-3-675b-instruct","mistralai/mistral-large-4","mistralai/mistral-nemo-instruct-2407","mistralai/mistral-small-24b-instruct-2501","mistralai/mistral-small-3.2-24b-instruct-2506","mistralai/mistral-small-4","mistralai/mistral-uncensored-1.2","mistralai/mistral-uncensored-roleplay","mistralai/voxtral-mini-3b-2507","mistralai/voxtral-small-24b-2507","moonshotai/kimi-k2-thinking","moonshotai/kimi-k2.5","moonshotai/kimi-k2.6","moonshotai/kimi-k2.7-code","moonshotai/kimi-k3","moonshotai/kimi-k3-fast","moonshotai/kimi-k3.1-pro","moonshotai/kimi-k3.1-pro-highspeed","nousresearch/hermes-3-llama-3.1-405b","nvidia/nemotron-content-safety-3.5","nvidia/nvidia-nemotron-3-nano-30b","nvidia/nvidia-nemotron-3-super-120b-a12b","nvidia/nvidia-nemotron-3-ultra","nvidia/nvidia-nemotron-3.5-lightning","nvidia/nvidia-nemotron-3.5-super-vl","nvidia/nvidia-nemotron-nano-12b-v2-vl","nvidia/nvidia-nemotron-nano-9b-v2","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","openai/gpt-4o","openai/gpt-4o-mini","openai/gpt-5","openai/gpt-5-mini","openai/gpt-5-nano","openai/gpt-5.1","openai/gpt-5.2","openai/gpt-5.3-codex","openai/gpt-5.4","openai/gpt-5.4-mini","openai/gpt-5.4-nano","openai/gpt-5.4-pro","openai/gpt-5.5","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-sol","openai/gpt-5.6-sol-pro","openai/gpt-5.6-terra","openai/gpt-5.6-terra-pro","openai/gpt-6-astra","openai/gpt-6-astra-pro","openai/gpt-6-luna","openai/gpt-6-sol","openai/gpt-6.1-sol","openai/gpt-6.1-sol-ultrafast","openai/gpt-oss-120b","openai/gpt-oss-120b-ultra","openai/gpt-oss-20b","openai/gpt-oss-safeguard-120b","openai/gpt-oss-safeguard-20b","openai/o3","openai/o3-mini","openai/o4-mini","qwen/qwen-2.5-7b","qwen/qwen-3-235b-a22b-instruct-2507","qwen/qwen-3-235b-a22b-thinking-2507","qwen/qwen-3-coder-480b","qwen/qwen-3-coder-480b-turbo","qwen/qwen-3-next-80b","qwen/qwen-3.5-35b-a3b","qwen/qwen-3.5-397b","qwen/qwen-3.5-9b","qwen/qwen-3.6-27b","qwen/qwen-3.6-35b-a3b","qwen/qwen-3.6-plus-uncensored","qwen/qwen-3.7-max","qwen/qwen-3.7-plus","qwen/qwen-3.8-2.4t","qwen/qwen-3.8-27b","qwen/qwen-3.8-27b-uncensored","qwen/qwen-3.8-flash","qwen/qwen-3.8-max","qwen/qwen-3.8-omni-flash","qwen/qwen2.5-72b-instruct","qwen/qwen3-14b","qwen/qwen3-235b-a22b-instruct-2507","qwen/qwen3-30b-a3b","qwen/qwen3-32b","qwen/qwen3-coder-30b-a3b-instruct","qwen/qwen3-coder-480b-a35b-instruct","qwen/qwen3-coder-next","qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3-vl-235b","qwen/qwen3-vl-235b-a22b-thinking","qwen/qwen3-vl-30b-a3b","qwen/qwen3-vl-30b-a3b-thinking","qwen/qwen3.5-27b","sao10k/l3-8b-lunaris-v1-turbo","sao10k/l3.1-70b-euryale-v2.2","stepfun-ai/step-5-preview","tencent/hy3","tencent/hy4-preview","thinking-machines/inkling","thinking-machines/inkling-small","venice/hy4-preview","writer/palmyra-vision-7b","x-ai/grok-4.20","x-ai/grok-4.20-multi-agent","x-ai/grok-4.3","x-ai/grok-4.5","x-ai/grok-4.6","x-ai/grok-4.7","x-ai/grok-build-0.1","xiaomi/mimo-v2.5","xiaomi/mimo-v2.6-flash","xiaomi/mimo-v2.6-pro","z-ai/glm-4.5","z-ai/glm-4.5-air","z-ai/glm-4.6","z-ai/glm-4.7","z-ai/glm-4.7-flash","z-ai/glm-4.7-flash-heretic","z-ai/glm-5","z-ai/glm-5-turbo","z-ai/glm-5.1","z-ai/glm-5.2","z-ai/glm-5.2-fast","z-ai/glm-5.3","z-ai/glm-5.3-fast","z-ai/glm-5.3-flash","z-ai/glm-5.3-uncensored","z-ai/glm-5v-turbo"],"privacyLevels":["anonymous","private","tee"],"defaultPrivacyLevels":["private","tee"],"pricing":{"anonymous":{"input":{"min":0.0126,"max":30},"output":{"min":0.063,"max":180}},"private":{"input":{"min":0.02,"max":4.5},"output":{"min":0.03,"max":22.5}},"tee":{"input":{"min":0.1,"max":4},"output":{"min":0.2,"max":20}}},"contextTokens":2000000,"maxOutputTokens":1048576,"capabilities":{"streaming":true,"tools":true,"vision":true}},{"id":"anonrouter/coding","kind":"paid","displayName":"Coding Router","description":"Picks the strongest coding model from a reviewed list.","models":["anthropic/claude-opus-5.5","anthropic/claude-sonnet-5.5","deepseek/deepseek-v4-pro","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","minimax/minimax-m3","moonshotai/kimi-k2.7-code","moonshotai/kimi-k3","openai/gpt-5.3-codex","openai/gpt-5.5","qwen/qwen-3-coder-480b-turbo","x-ai/grok-build-0.1","z-ai/glm-5.2","z-ai/glm-5.3"],"privacyLevels":["anonymous","private","tee"],"defaultPrivacyLevels":["private","tee"],"pricing":{"anonymous":{"input":{"min":0.02387,"max":5},"output":{"min":0.418,"max":30}},"private":{"input":{"min":0.09,"max":3.75},"output":{"min":0.3,"max":18.75}},"tee":{"input":{"min":0.65,"max":4},"output":{"min":1.45,"max":20}}},"contextTokens":1048576,"maxOutputTokens":1048576,"capabilities":{"streaming":true,"tools":true,"vision":true}},{"id":"anonrouter/uncensored","kind":"paid","displayName":"Uncensored Router","description":"Picks the best uncensored or abliterated model from a reviewed list.","models":["google/gemma-4-26b-a4b-uncensored","google/gemma-4-uncensored","mistralai/mistral-uncensored-1.2","mistralai/mistral-uncensored-roleplay","qwen/qwen-3.6-plus-uncensored","qwen/qwen-3.8-27b-uncensored","z-ai/glm-4.7-flash-heretic","z-ai/glm-5.3-uncensored"],"privacyLevels":["anonymous","private","tee"],"defaultPrivacyLevels":["private","tee"],"pricing":{"anonymous":{"input":{"min":0.049,"max":3},"output":{"min":0.28,"max":5}},"private":{"input":{"min":0.07,"max":3},"output":{"min":0.4,"max":5}},"tee":{"input":{"min":0.15,"max":0.3},"output":{"min":0.7,"max":1.5}}},"contextTokens":1000000,"maxOutputTokens":262144,"capabilities":{"streaming":true,"tools":true,"vision":true}},{"id":"anonrouter/tee","kind":"paid","displayName":"TEE Router","description":"Uses only verified TEE routes, where the model runs inside attested confidential hardware.","models":["deepseek/deepseek-v3.2","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4.1-flash","google/gemma-4-26b-a4b-uncensored","google/gemma-4-31b-instruct","meta/llama-3.3-70b","mistralai/voxtral-small-24b-2507","moonshotai/kimi-k2.6","moonshotai/kimi-k3","openai/gpt-oss-120b","qwen/qwen-2.5-7b","qwen/qwen-3.5-397b","qwen/qwen-3.6-27b","qwen/qwen-3.8-27b","qwen/qwen-3.8-27b-uncensored","z-ai/glm-5.1","z-ai/glm-5.2","z-ai/glm-5.3"],"privacyLevels":["tee"],"defaultPrivacyLevels":["tee"],"pricing":{"tee":{"input":{"min":0.1,"max":4},"output":{"min":0.2,"max":20}}},"contextTokens":1048576,"maxOutputTokens":1048576,"capabilities":{"streaming":true,"tools":true,"vision":true}}]}