{"chain_id":4663,"data_policy_note":"tee is the upstream's attested-hardware flag from the gateway's data-policy table (pricing/data-policy.json); data_policy.known is false where the provider's policy for that route could not be verified from a published source (a model a marketplace forwards to a partner whose own policy it does not state is one), and such a route never serves a request that asks for zero retention or no training.","gateway":"https://api.usdf.fi","generated_at":"2026-10-10T22:04:18.623Z","models":[{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-fable-5","max_output":128000,"modality":"text","name":"Claude Fable 5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":20,"cache_write_5m":12.5,"cached_input":1,"input":10,"output":50},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-fable-5","upstream_price":{"cache_write_1h":20,"cache_write_5m":12.5,"cached_input":1,"input":10,"output":50}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-fable-5","upstream_price":{"cache_write_5m":12.5,"cached_input":1,"input":10,"output":50}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-fable-5-1","max_output":128000,"modality":"text","name":"Claude Fable 5.1","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":20,"cache_write_5m":12.5,"cached_input":0.25,"input":10,"output":50},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-fable-5-1","upstream_price":{"cache_write_1h":20,"cache_write_5m":12.5,"cached_input":0.25,"input":10,"output":50}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-fable-5.1","upstream_price":{"cache_write_5m":12.5,"cached_input":0.25,"input":10,"output":50}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":200000,"endpoints":["chat"],"id":"claude-haiku-4-5","max_output":64000,"modality":"text","name":"Claude Haiku 4.5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":2,"cache_write_5m":1.25,"cached_input":0.1,"input":1,"output":5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-haiku-4-5","upstream_price":{"cache_write_1h":2,"cache_write_5m":1.25,"cached_input":0.1,"input":1,"output":5}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-haiku-4.5","upstream_price":{"cache_write_5m":1.25,"cached_input":0.1,"input":1,"output":5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-haiku-5-5","max_output":128000,"modality":"text","name":"Claude Haiku 5.5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cache_write_1h":0.2,"cache_write_5m":0.125,"cached_input":0.01,"input":0.1,"long_context":{"above_prompt_tokens":100000,"batch_cache_write_1h":0.5,"batch_cache_write_5m":0.3125,"batch_cached_input":0.025,"batch_input":0.25,"batch_output":1.25,"cache_write_1h":1,"cache_write_5m":0.625,"cached_input":0.05,"input":0.5,"output":2.5},"output":0.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-haiku-5-5","upstream_price":{"cache_write_1h":0.2,"cache_write_5m":0.125,"cached_input":0.01,"input":0.1,"long_context":{"above_prompt_tokens":100000,"batch_cache_write_1h":0.5,"batch_cache_write_5m":0.3125,"batch_cached_input":0.025,"batch_input":0.25,"batch_output":1.25,"cache_write_1h":1,"cache_write_5m":0.625,"cached_input":0.05,"input":0.5,"output":2.5},"output":0.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"claude-opus-4-5","max_output":64000,"modality":"text","name":"Claude Opus 4.5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-opus-4-5-20251101","upstream_price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-opus-4-6","max_output":128000,"modality":"text","name":"Claude Opus 4.6","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-opus-4-6","upstream_price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-opus-4-7","max_output":128000,"modality":"text","name":"Claude Opus 4.7","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-opus-4-7","upstream_price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-opus-4-8","max_output":128000,"modality":"text","name":"Claude Opus 4.8","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-opus-4-8","upstream_price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-opus-4.8","upstream_price":{"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-opus-5","max_output":128000,"modality":"text","name":"Claude Opus 5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-opus-5","upstream_price":{"cache_write_1h":10,"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-opus-5","upstream_price":{"cache_write_5m":6.25,"cached_input":0.5,"input":5,"output":25}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-opus-5-5","max_output":128000,"modality":"text","name":"Claude Opus 5.5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":8,"cache_write_5m":5,"cached_input":0.2,"input":4,"output":20},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-opus-5-5","upstream_price":{"cache_write_1h":8,"cache_write_5m":5,"cached_input":0.2,"input":4,"output":20}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-opus-5.5","upstream_price":{"cache_write_5m":5,"cached_input":0.2,"input":4,"output":20}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"anthropic/claude-opus-5-5","upstream_price":{"cached_input":0.2,"input":4,"output":20}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-sonnet-4-6","max_output":128000,"modality":"text","name":"Claude Sonnet 4.6","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":6,"cache_write_5m":3.75,"cached_input":0.3,"input":3,"output":15},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-sonnet-4-6","upstream_price":{"cache_write_1h":6,"cache_write_5m":3.75,"cached_input":0.3,"input":3,"output":15}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-sonnet-4.6","upstream_price":{"cache_write_5m":3.75,"cached_input":0.3,"input":3,"output":15}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-sonnet-5","max_output":128000,"modality":"text","name":"Claude Sonnet 5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":4,"cache_write_5m":2.5,"cached_input":0.2,"input":2,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-sonnet-5","upstream_price":{"cache_write_1h":4,"cache_write_5m":2.5,"cached_input":0.2,"input":2,"output":10}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-sonnet-5","upstream_price":{"cache_write_5m":2.5,"cached_input":0.2,"input":2,"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1000000,"endpoints":["chat"],"id":"claude-sonnet-5-5","max_output":128000,"modality":"text","name":"Claude Sonnet 5.5","owned_by":"anthropic","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_1h":4,"cache_write_5m":2.5,"cached_input":0.1,"input":2,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"anthropic","region":"unknown","tee":false,"upstream_model":"claude-sonnet-5-5","upstream_price":{"cache_write_1h":4,"cache_write_5m":2.5,"cached_input":0.1,"input":2,"output":10}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"anthropic/claude-sonnet-5.5","upstream_price":{"cache_write_5m":2.5,"cached_input":0.1,"input":2,"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":5000,"endpoints":["speech"],"id":"audio8-tts-preview-0.6b","max_output":1,"modality":"speech","name":"Audio8-TTS-Preview-0.6b","owned_by":"audio8","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":5,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Audio8/Audio8-TTS-Preview-0.6b","upstream_price":{"input":5,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"bge-base-en-v1.5","max_output":1024,"modality":"embedding","name":"bge-base-en-v1.5","owned_by":"baai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"BAAI/bge-base-en-v1.5","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":8192,"endpoints":["embeddings"],"id":"bge-en-icl","max_output":1024,"modality":"embedding","name":"bge-en-icl","owned_by":"baai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"BAAI/bge-en-icl","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"bge-large-en-v1.5","max_output":1024,"modality":"embedding","name":"bge-large-en-v1.5","owned_by":"baai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"BAAI/bge-large-en-v1.5","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":8192,"endpoints":["embeddings"],"id":"bge-m3","max_output":1024,"modality":"embedding","name":"Bge M3","owned_by":"baai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"BAAI/bge-m3","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens"},{"available":false,"context":8192,"endpoints":["embeddings"],"id":"bge-multilingual-gemma2","max_output":1024,"modality":"embedding","name":"Bge Multilingual gemma2","owned_by":"baai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.114,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"bge-multilingual-gemma2","upstream_price":{"input":0.114,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":3686400,"endpoints":["images"],"id":"flux-1-dev","image_unit":{"height":1024,"width":1024},"max_output":4,"modality":"image","name":"FLUX-1 Dev","owned_by":"black-forest-labs","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"input":0,"output":0.009},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"black-forest-labs/FLUX-1-dev","upstream_price":{"input":0,"output":0.009}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image unit: 1024 x 1024 output pixels at the model's default step count","usage_unit":"thousandths of an image unit"},{"available":true,"context":3686400,"endpoints":["images"],"id":"flux-1-schnell","image_unit":{"height":1024,"width":1024},"max_output":4,"modality":"image","name":"FLUX-1 Schnell","owned_by":"black-forest-labs","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"input":0,"output":0.0005},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"black-forest-labs/FLUX-1-schnell","upstream_price":{"input":0,"output":0.0005}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image unit: 1024 x 1024 output pixels at the model's default step count","usage_unit":"thousandths of an image unit"},{"available":false,"context":2073600,"endpoints":["images"],"id":"flux-1.1-pro","max_output":4,"modality":"image","name":"FLUX-1.1-pro","owned_by":"black-forest-labs","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"black-forest-labs/FLUX-1.1-pro","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":true,"context":3686400,"endpoints":["image_edits"],"id":"flux-2-dev","image_unit":{"height":1024,"width":1024},"max_output":4,"modality":"image","name":"FLUX-2 Dev","owned_by":"black-forest-labs","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"input":0,"output":0.01},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"black-forest-labs/FLUX-2-dev","upstream_price":{"input":0,"output":0.01}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image unit: 1024 x 1024 output pixels at the model's default step count","usage_unit":"thousandths of an image unit"},{"available":false,"context":3686400,"endpoints":["images"],"id":"flux-2-klein-4b","image_unit":{"height":1024,"width":1024},"max_output":4,"modality":"image","name":"FLUX-2-klein-4b","owned_by":"black-forest-labs","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.014},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"black-forest-labs/FLUX-2-klein-4b","upstream_price":{"input":0,"output":0.014}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image unit: 1024 x 1024 output pixels at the model's default step count","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":1048576,"endpoints":["images"],"id":"flux-2-pro","max_output":4,"modality":"image","name":"FLUX-2-pro","owned_by":"black-forest-labs","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"black-forest-labs/FLUX-2-pro","upstream_price":{"input":0,"output":0.03}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":1500,"endpoints":["speech"],"id":"higgsaudiov2.5","max_output":1,"modality":"speech","name":"HiggsAudioV2.5","owned_by":"bosonai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":20,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"bosonai/HiggsAudioV2.5","upstream_price":{"input":20,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"bria-3.2","max_output":4,"modality":"image","name":"Bria-3.2","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/Bria-3.2","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"bria-3.2-vector","max_output":4,"modality":"image","name":"Bria-3.2-vector","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/Bria-3.2-vector","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-blur-background","max_output":4,"modality":"image","name":"blur_background","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/blur_background","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-enhance","max_output":4,"modality":"image","name":"enhance","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/enhance","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-erase","max_output":4,"modality":"image","name":"erase","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/erase","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-erase-foreground","max_output":4,"modality":"image","name":"erase_foreground","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/erase_foreground","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-expand","max_output":4,"modality":"image","name":"expand","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/expand","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-fibo-edit","max_output":4,"modality":"image","name":"fibo_edit","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/fibo_edit","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-fibo-edit-1.5","max_output":4,"modality":"image","name":"fibo_edit-1.5","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/fibo_edit-1.5","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-gen-fill","max_output":4,"modality":"image","name":"gen_fill","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/gen_fill","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"bria-remove-background","max_output":4,"modality":"image","name":"remove_background","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.018},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/remove_background","upstream_price":{"input":0,"output":0.018}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":2000,"endpoints":["videos"],"id":"bria-video-foreground-mask","max_output":60,"modality":"video","name":"video_foreground_mask","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.14},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/video_foreground_mask","upstream_price":{"input":0,"output":0.14}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 1080p","usage_unit":"milliseconds of video","verified":false,"video":{"input_video":"required","resolution":"1080p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"bria-video-increase-resolution","max_output":60,"modality":"video","name":"video_increase_resolution","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.05},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/video_increase_resolution","upstream_price":{"input":0,"output":0.05}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 1080p","usage_unit":"milliseconds of video","verified":false,"video":{"input_video":"required","resolution":"1080p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"bria-video-mask-by-prompt","max_output":60,"modality":"video","name":"video_mask_by_prompt","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.14},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/video_mask_by_prompt","upstream_price":{"input":0,"output":0.14}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 1080p","usage_unit":"milliseconds of video","verified":false,"video":{"input_video":"required","resolution":"1080p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"bria-video-remove-background","max_output":60,"modality":"video","name":"video_remove_background","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.05},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/video_remove_background","upstream_price":{"input":0,"output":0.05}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 1080p","usage_unit":"milliseconds of video","verified":false,"video":{"input_video":"required","resolution":"1080p"}},{"available":false,"context":3686400,"endpoints":["images"],"id":"fibo","max_output":4,"modality":"image","name":"fibo","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/fibo","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"fibo-1.5","max_output":4,"modality":"image","name":"fibo-1.5","owned_by":"bria","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Bria/fibo-1.5","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":true,"context":256000,"endpoints":["chat"],"id":"seed-1.8","max_output":256000,"modality":"text","name":"Seed 1.8","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.05,"input":0.25,"long_context":{"above_prompt_tokens":128000,"cached_input":0.1,"input":0.5,"output":4},"output":2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seed-1.8","upstream_price":{"cached_input":0.05,"input":0.25,"long_context":{"above_prompt_tokens":128000,"cached_input":0.1,"input":0.5,"output":4},"output":2}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($2 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":256000,"endpoints":["chat"],"id":"seed-2.0-code","max_output":256000,"modality":"text","name":"Seed 2.0 Code","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.1,"input":0.5,"long_context":{"above_prompt_tokens":128000,"cached_input":0.2,"input":1,"output":6},"output":3},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seed-2.0-code","upstream_price":{"cached_input":0.1,"input":0.5,"long_context":{"above_prompt_tokens":128000,"cached_input":0.2,"input":1,"output":6},"output":3}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($3 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":256000,"endpoints":["chat"],"id":"seed-2.0-mini","max_output":256000,"modality":"text","name":"Seed 2.0 Mini","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.02,"input":0.1,"long_context":{"above_prompt_tokens":128000,"cached_input":0.2,"input":0.2,"output":0.8},"output":0.4},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seed-2.0-mini","upstream_price":{"cached_input":0.02,"input":0.1,"long_context":{"above_prompt_tokens":128000,"cached_input":0.2,"input":0.2,"output":0.8},"output":0.4}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.4 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":256000,"endpoints":["chat"],"id":"seed-2.0-pro","max_output":256000,"modality":"text","name":"Seed 2.0 Pro","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.1,"input":0.5,"long_context":{"above_prompt_tokens":128000,"cached_input":0.2,"input":1,"output":6},"output":3},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seed-2.0-pro","upstream_price":{"cached_input":0.1,"input":0.5,"long_context":{"above_prompt_tokens":128000,"cached_input":0.2,"input":1,"output":6},"output":3}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($3 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":2000,"endpoints":["videos"],"id":"seedance-1.5-pro","max_output":12,"modality":"video","name":"Seedance-1.5-Pro","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":1.2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seedance-1.5-Pro","upstream_price":{"input":0,"output":1.2}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false,"video":{"image":"optional","resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"seedance-2.0","max_output":15,"modality":"video","name":"Seedance-2.0","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":7.7},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seedance-2.0","upstream_price":{"input":0,"output":7.7}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false,"video":{"image":"optional","resolution":"720p"}},{"available":false,"context":3686400,"endpoints":["images"],"id":"seedream-4","max_output":4,"modality":"image","name":"Seedream-4","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seedream-4","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"seedream-4.5","max_output":4,"modality":"image","name":"Seedream-4.5","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seedream-4.5","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"seedream-5.0-pro","max_output":4,"modality":"image","name":"Seedream-5.0-Pro","owned_by":"bytedance","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.099},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ByteDance/Seedream-5.0-Pro","upstream_price":{"input":0,"output":0.099}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":300,"endpoints":["speech"],"id":"orpheus-3b-0.1-ft","max_output":1,"modality":"speech","name":"orpheus-3b-0.1-ft","owned_by":"canopylabs","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":7,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"canopylabs/orpheus-3b-0.1-ft","upstream_price":{"input":7,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"clarity-creative","max_output":4,"modality":"image","name":"creative","owned_by":"clarityai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.05},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ClarityAI/creative","upstream_price":{"input":0,"output":0.05}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"clarity-crystal","max_output":4,"modality":"image","name":"crystal","owned_by":"clarityai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.05},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ClarityAI/crystal","upstream_price":{"input":0,"output":0.05}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"clarity-flux","max_output":4,"modality":"image","name":"flux","owned_by":"clarityai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ClarityAI/flux","upstream_price":{"input":0,"output":0.2}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":true,"context":163840,"endpoints":["chat"],"id":"deepseek-r1-0528","max_output":16384,"modality":"text","name":"DeepSeek R1 0528","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.35,"input":0.5,"output":2.15},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-R1-0528","upstream_price":{"cached_input":0.35,"input":0.5,"output":2.15}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($2.15 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":131072,"endpoints":["chat"],"id":"deepseek-r1-distill-llama-8b","max_output":8192,"modality":"text","name":"DeepSeek R1 Distill Llama 8B","owned_by":"deepseek","parameters_b":8,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.05,"output":0.05},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B:nscale","upstream_price":{"input":0.05,"output":0.05}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 8B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":131072,"endpoints":["chat"],"id":"deepseek-r1-distill-qwen-14b","max_output":8192,"modality":"text","name":"DeepSeek R1 Distill Qwen 14B","owned_by":"deepseek","parameters_b":14,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.2,"output":0.2},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B:nscale","upstream_price":{"input":0.2,"output":0.2}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 14B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":131072,"endpoints":["chat"],"id":"deepseek-r1-distill-qwen-7b","max_output":8192,"modality":"text","name":"DeepSeek R1 Distill Qwen 7B","owned_by":"deepseek","parameters_b":7,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.15,"output":0.15},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B:nscale","upstream_price":{"input":0.15,"output":0.15}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 7B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":true,"context":163840,"endpoints":["chat"],"id":"deepseek-v3","max_output":163840,"modality":"text","name":"DeepSeek V3","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.32,"output":0.89},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V3","upstream_price":{"input":0.32,"output":0.89}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.89 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":163840,"endpoints":["chat"],"id":"deepseek-v3.1","max_output":32768,"modality":"text","name":"DeepSeek V3.1","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.13,"input":0.25,"output":0.95},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V3.1","upstream_price":{"cached_input":0.13,"input":0.25,"output":0.95}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.95 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":163840,"endpoints":["chat"],"id":"deepseek-v3.2","max_output":16384,"modality":"text","name":"DeepSeek V3.2","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.13,"input":0.26,"output":0.38},"price_private":{"cached_input":0.5,"input":1,"output":1},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V3.2","upstream_price":{"cached_input":0.13,"input":0.26,"output":0.38}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"deepseek/deepseek-v3.2","upstream_price":{"cached_input":0.5,"input":1,"output":1}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.38 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"deepseek-v4-flash","max_output":65536,"modality":"text","name":"DeepSeek V4 Flash","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.018,"input":0.09,"output":0.18},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V4-Flash","upstream_price":{"cached_input":0.018,"input":0.09,"output":0.18}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.18 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"deepseek-v4-flash-0731","max_output":384000,"modality":"text","name":"DeepSeek V4 Flash 0731","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.015,"input":0.06,"output":0.18},"price_private":{"cached_input":0.028,"input":0.44,"output":1.32},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V4-Flash-0731","upstream_price":{"cached_input":0.015,"input":0.06,"output":0.18}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"deepseek/deepseek-v4-flash-0731","upstream_price":{"cached_input":0.028,"input":0.44,"output":1.32}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.18 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"deepseek-v4-flash-vision-exp","max_output":262144,"modality":"text+image","name":"DeepSeek V4 Flash Vision Exp","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.02,"input":0.55,"output":1.65},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","upstream_price":{"cached_input":0.014,"input":0.44,"output":1.32}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($1.65 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"deepseek-v4-pro","max_output":1048576,"modality":"text","name":"DeepSeek V4 Pro","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.1,"input":1.3,"output":2.6},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V4-Pro","upstream_price":{"cached_input":0.1,"input":1.3,"output":2.6}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($2.6 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"deepseek-v4-pro-0813","max_output":1048576,"modality":"text","name":"DeepSeek V4 Pro 0813","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.1,"input":1.3,"output":2.6},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V4-Pro-0813","upstream_price":{"cached_input":0.1,"input":1.3,"output":2.6}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($2.6 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"deepseek-v4.1-flash","max_output":16384,"modality":"text","name":"DeepSeek V4.1 Flash","owned_by":"deepseek","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.008571,"input":0.285714,"output":0.857142},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"deepseek-ai/DeepSeek-V4.1-Flash","upstream_price":{"cached_input":0.006,"input":0.2,"output":0.6}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.857142 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":2000,"endpoints":["videos"],"id":"fastwan-qad-fp8-1.3b","max_output":5,"modality":"video","name":"FastWan QAD FP8 1.3B","owned_by":"fastvideo","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.0025},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"FastVideo/FastWan-QAD-FP8-1.3B","upstream_price":{"input":0,"output":0.0025}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 480p","usage_unit":"milliseconds of video","video":{"resolution":"480p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"fastwan2.2-ti2v-5b","max_output":5,"modality":"video","name":"FastWan2.2-TI2V-5B-FullAttn-Diffusers","owned_by":"fastvideo","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.0045},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers","upstream_price":{"input":0,"output":0.0045}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"720p"}},{"available":false,"context":2048,"endpoints":["embeddings"],"id":"embeddinggemma-300m","max_output":1024,"modality":"embedding","name":"embeddinggemma-300m","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.002,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/embeddinggemma-300m","upstream_price":{"input":0.002,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-2.5-flash","max_output":65536,"modality":"text","name":"Gemini 2.5 Flash","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.03,"input":0.3,"output":2.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-2.5-flash","upstream_price":{"cached_input":0.03,"input":0.3,"output":2.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-2.5-flash-lite","max_output":65536,"modality":"text","name":"Gemini 2.5 Flash-Lite","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.01,"input":0.1,"output":0.4},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-2.5-flash-lite","upstream_price":{"cached_input":0.01,"input":0.1,"output":0.4}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":5000,"endpoints":["speech"],"id":"gemini-2.5-flash-preview-tts","max_output":1,"modality":"speech","name":"Gemini 2.5 Flash Preview TTS","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.5,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-2.5-flash-preview-tts","upstream_price":{"input":0.5,"output":10}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-2.5-pro","max_output":65536,"modality":"text","name":"Gemini 2.5 Pro","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.125,"input":1.25,"long_context":{"above_prompt_tokens":200000,"batch_cached_input":0.25,"batch_input":1.25,"batch_output":7.5,"cached_input":0.25,"input":2.5,"output":15},"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-2.5-pro","upstream_price":{"cached_input":0.125,"input":1.25,"long_context":{"above_prompt_tokens":200000,"batch_cached_input":0.25,"batch_input":1.25,"batch_output":7.5,"cached_input":0.25,"input":2.5,"output":15},"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":5000,"endpoints":["speech"],"id":"gemini-2.5-pro-preview-tts","max_output":1,"modality":"speech","name":"Gemini 2.5 Pro Preview TTS","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":1,"output":20},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-2.5-pro-preview-tts","upstream_price":{"input":1,"output":20}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3-flash-preview","max_output":65536,"modality":"text","name":"Gemini 3 Flash Preview","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.05,"input":0.5,"output":3},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3-flash-preview","upstream_price":{"cached_input":0.05,"input":0.5,"output":3}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":3686400,"endpoints":["images","image_edits"],"id":"gemini-3-pro-image","max_output":1,"modality":"image","name":"Gemini 3 Pro Image","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":2,"output":120,"output_text":12},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3-pro-image","upstream_price":{"input":2,"output":120,"output_text":12}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":3686400,"endpoints":["images","image_edits"],"id":"gemini-3.1-flash-image","max_output":1,"modality":"image","name":"Gemini 3.1 Flash Image","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.5,"output":60,"output_text":3},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.1-flash-image","upstream_price":{"input":0.5,"output":60,"output_text":3}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.1-flash-lite","max_output":65536,"modality":"text","name":"Gemini 3.1 Flash-Lite","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.025,"input":0.25,"output":1.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.1-flash-lite","upstream_price":{"cached_input":0.025,"input":0.25,"output":1.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":3686400,"endpoints":["images","image_edits"],"id":"gemini-3.1-flash-lite-image","max_output":1,"modality":"image","name":"Gemini 3.1 Flash Lite Image","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.25,"output":30,"output_text":1.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.1-flash-lite-image","upstream_price":{"input":0.25,"output":30,"output_text":1.5}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":5000,"endpoints":["speech"],"id":"gemini-3.1-flash-tts-preview","max_output":1,"modality":"speech","name":"Gemini 3.1 Flash TTS Preview","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":1,"output":20},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.1-flash-tts-preview","upstream_price":{"input":1,"output":20}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.1-pro-preview","max_output":65536,"modality":"text","name":"Gemini 3.1 Pro Preview","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":200000,"batch_input":2,"batch_output":9,"cached_input":0.4,"input":4,"output":18},"output":12},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.1-pro-preview","upstream_price":{"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":200000,"batch_input":2,"batch_output":9,"cached_input":0.4,"input":4,"output":18},"output":12}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vertex","region":"unknown","tee":false,"upstream_model":"google/gemini-3.1-pro-preview","upstream_price":{"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":200000,"cached_input":0.4,"input":4,"output":18},"output":12}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"google/gemini-3.1-pro-preview","upstream_price":{"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":200000,"cached_input":0.4,"input":4,"output":18},"output":12}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.1-pro-preview-customtools","max_output":65536,"modality":"text","name":"Gemini 3.1 Pro Preview (custom tools)","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":200000,"batch_cached_input":0.4,"batch_input":2,"batch_output":9,"cached_input":0.4,"input":4,"output":18},"output":12},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.1-pro-preview-customtools","upstream_price":{"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":200000,"batch_cached_input":0.4,"batch_input":2,"batch_output":9,"cached_input":0.4,"input":4,"output":18},"output":12}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.5-flash","max_output":65536,"modality":"text","name":"Gemini 3.5 Flash","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.15,"input":1.5,"output":9},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.5-flash","upstream_price":{"cached_input":0.15,"input":1.5,"output":9}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.5-flash-lite","max_output":65536,"modality":"text","name":"Gemini 3.5 Flash-Lite","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cached_input":0.03,"input":0.3,"output":2.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.5-flash-lite","upstream_price":{"cached_input":0.03,"input":0.3,"output":2.5}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vertex","region":"unknown","tee":false,"upstream_model":"google/gemini-3.5-flash-lite","upstream_price":{"cached_input":0.03,"input":0.3,"output":2.5}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"google/gemini-3.5-flash-lite","upstream_price":{"cached_input":0.03,"input":0.3,"output":2.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"gemini-3.5-transcribe","max_output":1,"modality":"transcription","name":"Gemini 3.5 Transcribe","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":2,"output":12},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.5-transcribe","upstream_price":{"input":2,"output":12}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.6-flash","max_output":65536,"modality":"text","name":"Gemini 3.6 Flash","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.075,"input":0.75,"output":3.75},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.6-flash","upstream_price":{"cached_input":0.075,"input":0.75,"output":3.75}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.7-flash","max_output":65536,"modality":"text","name":"Gemini 3.7 Flash","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.075,"input":0.75,"output":3.75},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.7-flash","upstream_price":{"cached_input":0.075,"input":0.75,"output":3.75}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1048576,"endpoints":["chat"],"id":"gemini-3.8-flash","max_output":65536,"modality":"text","name":"Gemini 3.8 Flash","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cached_input":0.075,"input":0.75,"output":3.75},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.8-flash","upstream_price":{"cached_input":0.075,"input":0.75,"output":3.75}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vertex","region":"unknown","tee":false,"upstream_model":"google/gemini-3.8-flash","upstream_price":{"cached_input":0.075,"input":0.75,"output":3.75}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"google/gemini-3.8-flash","upstream_price":{"cached_input":0.075,"input":0.75,"output":3.75}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":5000,"endpoints":["speech"],"id":"gemini-3.8-flash-lite-tts","max_output":1,"modality":"speech","name":"Gemini 3.8 Flash-Lite TTS","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.125,"input":0.5,"output":6},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.8-flash-lite-tts","upstream_price":{"cached_input":0.125,"input":0.5,"output":6}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":5000,"endpoints":["speech"],"id":"gemini-3.8-flash-tts","max_output":1,"modality":"speech","name":"Gemini 3.8 Flash TTS","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.125,"input":0.5,"output":9},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-3.8-flash-tts","upstream_price":{"cached_input":0.125,"input":0.5,"output":9}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":8192,"endpoints":["embeddings"],"id":"gemini-embedding-2","max_output":1024,"modality":"embedding","name":"Gemini Embedding 2","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.2,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-embedding-2","upstream_price":{"input":0.2,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":3686400,"endpoints":["images","image_edits"],"id":"gemini-nano-banana-2.1","max_output":1,"modality":"image","name":"Gemini Nano Banana 2.1","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":1.5,"output":30,"output_text":7.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-nano-banana-2.1","upstream_price":{"input":1.5,"output":30,"output_text":7.5}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":2000,"endpoints":["videos"],"id":"gemini-omni-1.1-flash","max_output":10,"modality":"video","name":"Gemini Omni Flash","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":1.5,"output":17.5,"output_text":9},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"gemini-omni-1.1-flash","upstream_price":{"input":1.5,"output":17.5,"output_text":9}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false,"video":{"image":"optional","resolution":"720p"}},{"available":true,"context":131072,"endpoints":["chat"],"id":"gemma-3-12b-it","max_output":131072,"modality":"text","name":"Gemma 3 12B IT","owned_by":"google","parameters_b":12,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.05,"output":0.15},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/gemma-3-12b-it","upstream_price":{"input":0.05,"output":0.15}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 12B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"gemma-3-27b-it","max_output":131072,"modality":"text","name":"Gemma 3 27B IT","owned_by":"google","parameters_b":27,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.08,"output":0.16},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/gemma-3-27b-it","upstream_price":{"input":0.08,"output":0.16}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 27B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"gemma-3-4b-it","max_output":131072,"modality":"text","name":"Gemma 3 4B IT","owned_by":"google","parameters_b":4,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.05,"output":0.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/gemma-3-4b-it","upstream_price":{"input":0.05,"output":0.1}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 4B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"gemma-4-26b-a4b-it","max_output":262144,"modality":"text","name":"Gemma 4 26B A4B IT","owned_by":"google","parameters_b":26,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.07,"output":0.34},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/gemma-4-26B-A4B-it","upstream_price":{"input":0.07,"output":0.34}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 26B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":262144,"endpoints":["chat"],"id":"gemma-4-31b-it","max_output":262144,"modality":"text","name":"Gemma 4 31B IT","owned_by":"google","parameters_b":31,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"input":0.13,"output":0.38},"price_private":{"cached_input":0.13,"input":0.15,"output":0.46},"pricing":"list","private":false,"private_listed":true,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/gemma-4-31B-it","upstream_price":{"input":0.13,"output":0.38}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"google/gemma-4-31b-it","upstream_price":{"cached_input":0.075,"input":0.15,"output":0.46}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 31B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"gemma-4-31b-it-turbo","max_output":16384,"modality":"text","name":"Gemma 4 31B IT Turbo","owned_by":"google","parameters_b":31,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.05,"input":0.09,"output":0.34},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/gemma-4-31B-it-turbo","upstream_price":{"cached_input":0.05,"input":0.09,"output":0.34}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 31B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"gemma-4-31b-it-ultra","max_output":8192,"modality":"text","name":"Gemma 4 31B IT Ultra","owned_by":"google","parameters_b":31,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.27,"output":0.76},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/gemma-4-31B-it-Ultra","upstream_price":{"input":0.27,"output":0.76}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 31B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":2000,"endpoints":["videos"],"id":"veo-3.1","max_output":8,"modality":"video","name":"Veo 3.1","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.4},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"veo-3.1-generate-preview","upstream_price":{"input":0,"output":0.4}},{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/veo-3.1","upstream_price":{"input":0,"output":0.4}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"audio":true,"image":"optional","resolution":"720p"}},{"available":true,"context":2000,"endpoints":["videos"],"id":"veo-3.1-fast","max_output":8,"modality":"video","name":"Veo 3.1 Fast","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.15},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"google/veo-3.1-fast","upstream_price":{"input":0,"output":0.15}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"veo-3.1-fast-generate-preview","upstream_price":{"input":0,"output":0.1}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","video":{"image":"optional","resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"veo-3.1-lite","max_output":8,"modality":"video","name":"Veo 3.1 Lite","owned_by":"google","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.05},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"gemini","region":"unknown","tee":false,"upstream_model":"veo-3.1-lite-generate-preview","upstream_price":{"input":0,"output":0.05}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"audio":true,"image":"optional","resolution":"720p"}},{"available":true,"context":4096,"endpoints":["chat"],"id":"mythomax-l2-13b","max_output":4096,"modality":"text","name":"MythoMax L2 13B","owned_by":"gryphe","parameters_b":13,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.4,"output":0.4},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Gryphe/MythoMax-L2-13b","upstream_price":{"input":0.4,"output":0.4}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 13B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":10000,"endpoints":["speech"],"id":"kokoro-82m","max_output":1,"modality":"speech","name":"Kokoro 82M","owned_by":"hexgrad","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.62,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"hexgrad/Kokoro-82M","upstream_price":{"input":0.62,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters"},{"available":true,"context":131072,"endpoints":["chat"],"id":"granite-4.2-30b","max_output":131072,"modality":"text","name":"Granite 4.2 30B","owned_by":"ibm","parameters_b":30,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.04,"input":0.16,"output":0.65},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ibm-granite/granite-4.2-30b","upstream_price":{"cached_input":0.04,"input":0.16,"output":0.65}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 30B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"granite-4.2-3b","max_output":131072,"modality":"text","name":"Granite 4.2 3B","owned_by":"ibm","parameters_b":3,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.0075,"input":0.03,"output":0.12},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ibm-granite/granite-4.2-3b","upstream_price":{"cached_input":0.0075,"input":0.03,"output":0.12}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 3B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"granite-4.2-8b","max_output":131072,"modality":"text","name":"Granite 4.2 8B","owned_by":"ibm","parameters_b":8,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.015,"input":0.06,"output":0.25},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ibm-granite/granite-4.2-8b","upstream_price":{"cached_input":0.015,"input":0.06,"output":0.25}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 8B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"ling-3.0-flash","max_output":32768,"modality":"text","name":"Ling 3.0 Flash","owned_by":"inclusionai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.012,"input":0.06,"output":0.18},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"inclusionAI/Ling-3.0-flash","upstream_price":{"cached_input":0.012,"input":0.06,"output":0.18}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.18 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"ling-3.0-flash-vl","max_output":32768,"modality":"text+image","name":"Ling 3.0 Flash VL","owned_by":"inclusionai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.012,"input":0.06,"output":0.18},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"inclusionAI/Ling-3.0-flash-VL","upstream_price":{"cached_input":0.012,"input":0.06,"output":0.18}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.18 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":3686400,"endpoints":["images"],"id":"ming-image-0.1-design","max_output":4,"modality":"image","name":"Ming-Image-0.1-Design","owned_by":"inclusionai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.01},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"inclusionAI/Ming-Image-0.1-Design","upstream_price":{"input":0,"output":0.01}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"ming-image-0.1-design-layer","max_output":4,"modality":"image","name":"Ming-Image-0.1-Design-Layer","owned_by":"inclusionai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.01},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"inclusionAI/Ming-Image-0.1-Design-Layer","upstream_price":{"input":0,"output":0.01}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"e5-base-v2","max_output":1024,"modality":"embedding","name":"e5-base-v2","owned_by":"intfloat","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"intfloat/e5-base-v2","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"e5-large-v2","max_output":1024,"modality":"embedding","name":"e5-large-v2","owned_by":"intfloat","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"intfloat/e5-large-v2","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"multilingual-e5-large","max_output":1024,"modality":"embedding","name":"multilingual-e5-large","owned_by":"intfloat","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"intfloat/multilingual-e5-large","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"multilingual-e5-large-instruct","max_output":1024,"modality":"embedding","name":"multilingual-e5-large-instruct","owned_by":"intfloat","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"intfloat/multilingual-e5-large-instruct","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":2000,"endpoints":["speech"],"id":"realtime-tts-1.5-max","max_output":1,"modality":"speech","name":"realtime-tts-1.5-max","owned_by":"inworld-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":50,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"inworld-ai/realtime-tts-1.5-max","upstream_price":{"input":50,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":2000,"endpoints":["speech"],"id":"realtime-tts-1.5-mini","max_output":1,"modality":"speech","name":"realtime-tts-1.5-mini","owned_by":"inworld-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":25,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"inworld-ai/realtime-tts-1.5-mini","upstream_price":{"input":25,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":2000,"endpoints":["speech"],"id":"realtime-tts-2","max_output":1,"modality":"speech","name":"realtime-tts-2","owned_by":"inworld-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":35,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"inworld-ai/realtime-tts-2","upstream_price":{"input":35,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":true,"context":131072,"endpoints":["chat"],"id":"llama-3.1-70b-instruct-turbo","max_output":131072,"modality":"text","name":"Llama 3.1 70B Instruct Turbo","owned_by":"meta","parameters_b":70,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.4,"output":0.4},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","upstream_price":{"input":0.4,"output":0.4}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 70B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat","completions"],"id":"llama-3.1-8b-instruct","max_output":16384,"modality":"text","name":"Llama 3.1 8B Instruct","owned_by":"meta","parameters_b":8,"performance":{"latency_p50_ms":425,"latency_p95_ms":5190,"note":"insufficient samples for throughput","samples":77,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.02,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","upstream_price":{"input":0.02,"output":0.04}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 8B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat","completions"],"id":"llama-3.3-70b-instruct","max_output":16384,"modality":"text","name":"Llama 3.3 70B Instruct","owned_by":"meta","parameters_b":70,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"input":0.1,"output":0.32},"price_private":{"input":2,"output":2},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"meta-llama/Llama-3.3-70B-Instruct-Turbo","upstream_price":{"input":0.1,"output":0.32}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"meta-llama/llama-3.3-70b-instruct","upstream_price":{"input":2,"output":2}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 70B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":327680,"endpoints":["chat"],"id":"llama-4-scout","max_output":16384,"modality":"text","name":"Llama 4 Scout 17B-16E Instruct","owned_by":"meta","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.1,"output":0.3},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"meta-llama/Llama-4-Scout-17B-16E-Instruct","upstream_price":{"input":0.1,"output":0.3}},{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"meta-llama/Llama-4-Scout-17B-16E-Instruct:nscale","upstream_price":{"input":0.09,"output":0.29}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.3 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":163840,"endpoints":["chat"],"id":"llama-guard-4-12b","max_output":163840,"modality":"text","name":"Llama Guard 4 12B","owned_by":"meta","parameters_b":12,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.18,"output":0.18},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"meta-llama/Llama-Guard-4-12B","upstream_price":{"input":0.18,"output":0.18}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 12B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"muse-glimmer-30b","max_output":131072,"modality":"text","name":"Muse Glimmer 30B","owned_by":"meta","parameters_b":30,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.04,"input":0.3,"output":1.2},"price_private":{"cached_input":0.04,"input":0.3,"output":1.2},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"meta-models/Muse-Glimmer-30B","upstream_price":{"cached_input":0.04,"input":0.3,"output":1.2}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"meta/muse-glimmer-30b","upstream_price":{"cached_input":0.04,"input":0.3,"output":1.1}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 30B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":16384,"endpoints":["chat"],"id":"phi-4","max_output":16384,"modality":"text","name":"Phi 4","owned_by":"microsoft","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.07,"output":0.14},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"microsoft/phi-4","upstream_price":{"input":0.07,"output":0.14}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.14 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":524288,"endpoints":["chat"],"id":"minimax-m3","max_output":131072,"modality":"text","name":"MiniMax M3","owned_by":"minimax","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.056,"input":0.28,"output":1.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"MiniMaxAI/MiniMax-M3","upstream_price":{"cached_input":0.056,"input":0.28,"output":1.1}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($1.1 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":128000,"endpoints":["chat"],"id":"codestral-2508","max_output":128000,"modality":"text","name":"Codestral 25.08","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.03,"input":0.3,"output":0.9},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"codestral-2508","upstream_price":{"cached_input":0.03,"input":0.3,"output":0.9}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":8192,"endpoints":["embeddings"],"id":"codestral-embed","max_output":1024,"modality":"embedding","name":"Codestral Embed","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.15,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"codestral-embed-2505","upstream_price":{"input":0.15,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":256000,"endpoints":["chat"],"id":"ministral-3-14b","max_output":256000,"modality":"text","name":"Ministral 3 14B","owned_by":"mistralai","parameters_b":14,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.02,"input":0.2,"output":0.2},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"ministral-14b-2512","upstream_price":{"cached_input":0.02,"input":0.2,"output":0.2}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":256000,"endpoints":["chat"],"id":"ministral-3-3b","max_output":256000,"modality":"text","name":"Ministral 3 3B","owned_by":"mistralai","parameters_b":3,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.01,"input":0.1,"output":0.1},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"ministral-3b-2512","upstream_price":{"cached_input":0.01,"input":0.1,"output":0.1}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":256000,"endpoints":["chat"],"id":"ministral-3-8b","max_output":256000,"modality":"text","name":"Ministral 3 8B","owned_by":"mistralai","parameters_b":8,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.015,"input":0.15,"output":0.15},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"ministral-8b-2512","upstream_price":{"cached_input":0.015,"input":0.15,"output":0.15}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":8192,"endpoints":["embeddings"],"id":"mistral-embed","max_output":1024,"modality":"embedding","name":"Mistral Embed","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.1,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"mistral-embed","upstream_price":{"input":0.1,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":256000,"endpoints":["chat"],"id":"mistral-large-3","max_output":256000,"modality":"text","name":"Mistral Large 3","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.05,"input":0.5,"output":1.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"mistral-large-2512","upstream_price":{"cached_input":0.05,"input":0.5,"output":1.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":256000,"endpoints":["chat"],"id":"mistral-medium-3.5","max_output":256000,"modality":"text","name":"Mistral Medium 3.5","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.15,"input":1.5,"output":7.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"mistral-medium-3-5","upstream_price":{"cached_input":0.15,"input":1.5,"output":7.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":true,"context":131072,"endpoints":["chat"],"id":"mistral-nemo-instruct-2407","max_output":131072,"modality":"text","name":"Mistral Nemo Instruct 2407","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.029,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"mistralai/Mistral-Nemo-Instruct-2407","upstream_price":{"input":0.029,"output":0.03}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.03 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":32768,"endpoints":["chat"],"id":"mistral-small-24b-instruct-2501","max_output":32768,"modality":"text","name":"Mistral Small 24B Instruct 2501","owned_by":"mistralai","parameters_b":24,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.05,"output":0.08},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"mistralai/Mistral-Small-24B-Instruct-2501","upstream_price":{"input":0.05,"output":0.08}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 24B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":128000,"endpoints":["chat"],"id":"mistral-small-3.2-24b-instruct-2506","max_output":128000,"modality":"text","name":"Mistral Small 3.2 24B Instruct 2506","owned_by":"mistralai","parameters_b":24,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.075,"output":0.2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","upstream_price":{"input":0.075,"output":0.2}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 24B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":256000,"endpoints":["chat"],"id":"mistral-small-4","max_output":256000,"modality":"text","name":"Mistral Small 4","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.015,"input":0.15,"output":0.6},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"mistral-small-2603","upstream_price":{"cached_input":0.015,"input":0.15,"output":0.6}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"voxtral-mini-3b-2507","max_output":1,"modality":"transcription","name":"Voxtral-Mini-3B-2507","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.001,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"mistralai/Voxtral-Mini-3B-2507","upstream_price":{"input":0.001,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"voxtral-mini-transcribe-2","max_output":1,"modality":"transcription","name":"Voxtral Mini Transcribe 2","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.003,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"mistral","region":"unknown","tee":false,"upstream_model":"voxtral-mini-transcribe-2602","upstream_price":{"input":0.003,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"voxtral-small-24b-2507","max_output":1,"modality":"transcription","name":"Voxtral-Small-24B-2507","owned_by":"mistralai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.003,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"mistralai/Voxtral-Small-24B-2507","upstream_price":{"input":0.003,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":true,"context":262144,"endpoints":["chat"],"id":"kimi-k2.6","max_output":16384,"modality":"text","name":"Kimi K2.6","owned_by":"moonshotai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.15,"input":0.75,"output":3.5},"price_private":{"cached_input":0.37,"input":1.09,"output":4.6},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"moonshotai/Kimi-K2.6","upstream_price":{"cached_input":0.15,"input":0.75,"output":3.5}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"moonshotai/kimi-k2.6","upstream_price":{"cached_input":0.37,"input":1.09,"output":4.6}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($3.5 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"kimi-k3","max_output":16384,"modality":"text","name":"Kimi K3","owned_by":"moonshotai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.285,"input":2.85,"output":14.25},"price_private":{"cached_input":0.3,"input":3,"output":15},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"moonshotai/Kimi-K3","upstream_price":{"cached_input":0.285,"input":2.85,"output":14.25}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"moonshotai/kimi-k3","upstream_price":{"cached_input":0.3,"input":3,"output":15}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($14.25 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"hermes-3-llama-3.1-405b","max_output":131072,"modality":"text","name":"Hermes 3 Llama 3.1 405B","owned_by":"nousresearch","parameters_b":405,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":1,"output":1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"NousResearch/Hermes-3-Llama-3.1-405B","upstream_price":{"input":1,"output":1}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 405B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"hermes-3-llama-3.1-70b","max_output":131072,"modality":"text","name":"Hermes 3 Llama 3.1 70B","owned_by":"nousresearch","parameters_b":70,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.7,"output":0.7},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"NousResearch/Hermes-3-Llama-3.1-70B","upstream_price":{"input":0.7,"output":0.7}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 70B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":10240,"endpoints":["embeddings"],"id":"llama-nemotron-embed-vl-1b-v2","max_output":1024,"modality":"embedding","name":"llama-nemotron-embed-vl-1b-v2","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/llama-nemotron-embed-vl-1b-v2","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":10240,"endpoints":["rerank"],"id":"llama-nemotron-rerank-vl-1b-v2","max_output":1024,"modality":"rerank","name":"llama-nemotron-rerank-vl-1b-v2","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/llama-nemotron-rerank-vl-1b-v2","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"nemotron-3-diarization","max_output":1,"modality":"transcription","name":"Nemotron-3-Diarization","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.0006,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/Nemotron-3-Diarization","upstream_price":{"input":0.0006,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":false,"context":32768,"endpoints":["embeddings"],"id":"nemotron-3-embed-1b","max_output":1024,"modality":"embedding","name":"Nemotron-3-Embed-1B (NVFP4)","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/Nemotron-3-Embed-1B-NVFP4","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32768,"endpoints":["embeddings"],"id":"nemotron-3-embed-8b","max_output":1024,"modality":"embedding","name":"Nemotron-3-Embed-8B","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.035,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/Nemotron-3-Embed-8B","upstream_price":{"input":0.035,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":262144,"endpoints":["chat"],"id":"nemotron-3-ultra-550b-a55b","max_output":16384,"modality":"text","name":"Nemotron 3 Ultra 550B A55B","owned_by":"nvidia","parameters_b":550,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.1,"input":0.5,"output":2.2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","upstream_price":{"cached_input":0.1,"input":0.5,"output":2.2}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 550B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"nemotron-3.5-asr-streaming-multilingual-0.6b","max_output":1,"modality":"transcription","name":"Nemotron-3.5-ASR-Streaming-Multilingual-0.6b","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.0002,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b","upstream_price":{"input":0.0002,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":true,"context":262144,"endpoints":["chat"],"id":"nemotron-3.5-lightning","max_output":32768,"modality":"text","name":"Nemotron 3.5 Lightning","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.03,"input":0.06,"output":0.16},"price_private":{"cached_input":0.04,"input":0.07,"output":0.2},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/NVIDIA-Nemotron-3.5-Lightning","upstream_price":{"cached_input":0.03,"input":0.06,"output":0.16}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"nvidia/nemotron-3.5-lightning","upstream_price":{"cached_input":0.04,"input":0.07,"output":0.2}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.16 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"nemotron-content-safety-3.5","max_output":131072,"modality":"text","name":"Nemotron Content Safety 3.5","owned_by":"nvidia","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.2,"output":0.2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"nvidia/Nemotron-Content-Safety-3.5","upstream_price":{"input":0.2,"output":0.2}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.2 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":16385,"endpoints":["chat"],"id":"gpt-3.5-turbo-0125","max_output":4096,"modality":"text","name":"GPT-3.5 Turbo (0125)","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.5,"output":1.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-3.5-turbo-0125","upstream_price":{"input":0.5,"output":1.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":8192,"endpoints":["chat"],"id":"gpt-4-0613","max_output":8192,"modality":"text","name":"GPT-4 (0613)","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":30,"output":60},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4-0613","upstream_price":{"input":30,"output":60}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":128000,"endpoints":["chat"],"id":"gpt-4-turbo-2024-04-09","max_output":4096,"modality":"text","name":"GPT-4 Turbo (2024-04-09)","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":10,"output":30},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4-turbo-2024-04-09","upstream_price":{"input":10,"output":30}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1047576,"endpoints":["chat"],"id":"gpt-4.1","max_output":32768,"modality":"text","name":"GPT-4.1","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.5,"input":2,"output":8},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4.1","upstream_price":{"cached_input":0.5,"input":2,"output":8}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1047576,"endpoints":["chat"],"id":"gpt-4.1-mini","max_output":32768,"modality":"text","name":"GPT-4.1 Mini","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.1,"input":0.4,"output":1.6},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4.1-mini","upstream_price":{"cached_input":0.1,"input":0.4,"output":1.6}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1047576,"endpoints":["chat"],"id":"gpt-4.1-nano","max_output":32768,"modality":"text","name":"GPT-4.1 nano","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.025,"input":0.1,"output":0.4},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4.1-nano","upstream_price":{"cached_input":0.025,"input":0.1,"output":0.4}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":128000,"endpoints":["chat"],"id":"gpt-4o","max_output":16384,"modality":"text","name":"GPT-4o","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":1.25,"input":2.5,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4o","upstream_price":{"cached_input":1.25,"input":2.5,"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":128000,"endpoints":["chat"],"id":"gpt-4o-mini","max_output":16384,"modality":"text","name":"GPT-4o Mini","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.075,"input":0.15,"output":0.6},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4o-mini","upstream_price":{"cached_input":0.075,"input":0.15,"output":0.6}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"gpt-4o-mini-transcribe","max_output":1,"modality":"transcription","name":"GPT-4o mini Transcribe","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":1.25,"output":5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4o-mini-transcribe","upstream_price":{"input":1.25,"output":5}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":4096,"endpoints":["speech"],"id":"gpt-4o-mini-tts","max_output":1,"modality":"speech","name":"GPT-4o mini TTS","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.6,"output":12},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4o-mini-tts","upstream_price":{"input":0.6,"output":12}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"gpt-4o-transcribe","max_output":1,"modality":"transcription","name":"gpt-4o-transcribe","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":2.5,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4o-transcribe","upstream_price":{"input":2.5,"output":10}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"gpt-4o-transcribe-diarize","max_output":1,"modality":"transcription","name":"gpt-4o-transcribe-diarize","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":2.5,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-4o-transcribe-diarize","upstream_price":{"input":2.5,"output":10}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5","max_output":128000,"modality":"text","name":"GPT-5","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.125,"input":1.25,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5","upstream_price":{"cached_input":0.125,"input":1.25,"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5-mini","max_output":128000,"modality":"text","name":"GPT-5 Mini","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.025,"input":0.25,"output":2},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5-mini","upstream_price":{"cached_input":0.025,"input":0.25,"output":2}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5-nano","max_output":128000,"modality":"text","name":"GPT-5 nano","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.005,"input":0.05,"output":0.4},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5-nano","upstream_price":{"cached_input":0.005,"input":0.05,"output":0.4}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5-pro","max_output":272000,"modality":"text","name":"GPT-5 Pro","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":15,"output":120},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5-pro","upstream_price":{"input":15,"output":120}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5.1","max_output":128000,"modality":"text","name":"GPT-5.1","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.125,"input":1.25,"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.1","upstream_price":{"cached_input":0.125,"input":1.25,"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5.2","max_output":128000,"modality":"text","name":"GPT-5.2","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.175,"input":1.75,"output":14},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.2","upstream_price":{"cached_input":0.175,"input":1.75,"output":14}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5.2-pro","max_output":128000,"modality":"text","name":"GPT-5.2 Pro","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":21,"output":168},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.2-pro","upstream_price":{"input":21,"output":168}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5.3-codex","max_output":128000,"modality":"text","name":"GPT-5.3-Codex","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.175,"input":1.75,"output":14},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.3-codex","upstream_price":{"cached_input":0.175,"input":1.75,"output":14}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-5.4","max_output":128000,"modality":"text","name":"GPT-5.4","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.25,"input":2.5,"long_context":{"above_prompt_tokens":272000,"batch_cached_input":0.25,"batch_input":2.5,"batch_output":11.25,"cached_input":0.5,"input":5,"output":22.5},"output":15},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.4","upstream_price":{"cached_input":0.25,"input":2.5,"long_context":{"above_prompt_tokens":272000,"batch_cached_input":0.25,"batch_input":2.5,"batch_output":11.25,"cached_input":0.5,"input":5,"output":22.5},"output":15}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5.4-mini","max_output":128000,"modality":"text","name":"GPT-5.4 mini","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cached_input":0.075,"input":0.75,"output":4.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.4-mini","upstream_price":{"cached_input":0.075,"input":0.75,"output":4.5}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"openai/gpt-5.4-mini","upstream_price":{"cached_input":0.075,"input":0.75,"output":4.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":400000,"endpoints":["chat"],"id":"gpt-5.4-nano","max_output":128000,"modality":"text","name":"GPT-5.4 nano","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.02,"input":0.2,"output":1.25},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.4-nano","upstream_price":{"cached_input":0.02,"input":0.2,"output":1.25}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-5.4-pro","max_output":128000,"modality":"text","name":"GPT-5.4 Pro","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":30,"long_context":{"above_prompt_tokens":272000,"input":60,"output":270},"output":180},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.4-pro","upstream_price":{"input":30,"long_context":{"above_prompt_tokens":272000,"input":60,"output":270},"output":180}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-5.5","max_output":128000,"modality":"text","name":"GPT-5.5","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.5,"input":5,"long_context":{"above_prompt_tokens":272000,"batch_cached_input":0.5,"batch_input":5,"batch_output":22.5,"cached_input":1,"input":10,"output":45},"output":30},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.5","upstream_price":{"cached_input":0.5,"input":5,"long_context":{"above_prompt_tokens":272000,"batch_cached_input":0.5,"batch_input":5,"batch_output":22.5,"cached_input":1,"input":10,"output":45},"output":30}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-5.5-pro","max_output":128000,"modality":"text","name":"GPT-5.5 Pro","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":30,"long_context":{"above_prompt_tokens":272000,"input":60,"output":270},"output":180},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.5-pro","upstream_price":{"input":30,"long_context":{"above_prompt_tokens":272000,"input":60,"output":270},"output":180}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-5.6-luna","max_output":128000,"modality":"text","name":"GPT-5.6 Luna","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cache_write_5m":0.25,"cached_input":0.02,"input":0.2,"long_context":{"above_prompt_tokens":272000,"batch_cache_write_5m":0.25,"batch_cached_input":0.02,"batch_input":0.2,"batch_output":0.9,"cache_write_5m":0.5,"cached_input":0.04,"input":0.4,"output":1.8},"output":1.2},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.6-luna","upstream_price":{"cache_write_5m":0.25,"cached_input":0.02,"input":0.2,"long_context":{"above_prompt_tokens":272000,"batch_cache_write_5m":0.25,"batch_cached_input":0.02,"batch_input":0.2,"batch_output":0.9,"cache_write_5m":0.5,"cached_input":0.04,"input":0.4,"output":1.8},"output":1.2}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-5.6-terra","max_output":128000,"modality":"text","name":"GPT-5.6 Terra","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cache_write_5m":2.5,"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":272000,"batch_cache_write_5m":2.5,"batch_cached_input":0.2,"batch_input":2,"batch_output":9,"cache_write_5m":5,"cached_input":0.4,"input":4,"output":18},"output":12},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-5.6-terra","upstream_price":{"cache_write_5m":2.5,"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":272000,"batch_cache_write_5m":2.5,"batch_cached_input":0.2,"batch_input":2,"batch_output":9,"cache_write_5m":5,"cached_input":0.4,"input":4,"output":18},"output":12}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-6-astra","max_output":128000,"modality":"text","name":"GPT-6 Astra","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_5m":12.5,"cached_input":1,"input":10,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":25,"cached_input":2,"input":20,"output":75},"output":50},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-6-astra","upstream_price":{"cache_write_5m":12.5,"cached_input":1,"input":10,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":25,"cached_input":2,"input":20,"output":75},"output":50}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"bedrock","region":"unknown","tee":false,"upstream_model":"global.openai.gpt-6-astra","upstream_price":{"cache_write_5m":12.5,"cached_input":1,"input":10,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":25,"cached_input":2,"input":20,"output":75},"output":50}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"openai/gpt-6-astra","upstream_price":{"cache_write_5m":12.5,"cached_input":1,"input":10,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":25,"cached_input":2,"input":20,"output":75},"output":50}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-6-luna","max_output":128000,"modality":"text","name":"GPT-6 Luna","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_5m":0.125,"cached_input":0.01,"input":0.1,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":0.25,"cached_input":0.02,"input":0.2,"output":0.75},"output":0.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-6-luna","upstream_price":{"cache_write_5m":0.125,"cached_input":0.01,"input":0.1,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":0.25,"cached_input":0.02,"input":0.2,"output":0.75},"output":0.5}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"bedrock","region":"unknown","tee":false,"upstream_model":"global.openai.gpt-6-luna","upstream_price":{"cache_write_5m":0.125,"cached_input":0.01,"input":0.1,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":0.25,"cached_input":0.02,"input":0.2,"output":0.75},"output":0.5}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"openai/gpt-6-luna","upstream_price":{"cache_write_5m":0.125,"cached_input":0.01,"input":0.1,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":0.25,"cached_input":0.02,"input":0.2,"output":0.75},"output":0.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-6-sol","max_output":128000,"modality":"text","name":"GPT-6 Sol","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"cache_write_5m":2.5,"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":5,"cached_input":0.4,"input":4,"output":15},"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-6-sol","upstream_price":{"cache_write_5m":2.5,"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":5,"cached_input":0.4,"input":4,"output":15},"output":10}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"bedrock","region":"unknown","tee":false,"upstream_model":"global.openai.gpt-6-sol","upstream_price":{"cache_write_5m":2.5,"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":5,"cached_input":0.4,"input":4,"output":15},"output":10}},{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"vercel","region":"unknown","tee":false,"upstream_model":"openai/gpt-6-sol","upstream_price":{"cache_write_5m":2.5,"cached_input":0.2,"input":2,"long_context":{"above_prompt_tokens":272000,"cache_write_5m":5,"cached_input":0.4,"input":4,"output":15},"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens"},{"available":false,"context":1050000,"endpoints":["chat"],"id":"gpt-6.1-sol","max_output":128000,"modality":"text","name":"GPT-6.1 Sol","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cache_write_5m":2.5,"cached_input":0.1,"input":2,"long_context":{"above_prompt_tokens":272000,"batch_cache_write_5m":2.5,"batch_cached_input":0.1,"batch_input":2,"batch_output":7.5,"cache_write_5m":5,"cached_input":0.2,"input":4,"output":15},"output":10},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-6.1-sol","upstream_price":{"cache_write_5m":2.5,"cached_input":0.1,"input":2,"long_context":{"above_prompt_tokens":272000,"batch_cache_write_5m":2.5,"batch_cached_input":0.1,"batch_input":2,"batch_output":7.5,"cache_write_5m":5,"cached_input":0.2,"input":4,"output":15},"output":10}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1572864,"endpoints":["images","image_edits"],"id":"gpt-image-1","max_output":4,"modality":"image","name":"GPT Image 1","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":5,"input_image":10,"output":40},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-image-1","upstream_price":{"input":5,"input_image":10,"output":40}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1572864,"endpoints":["images","image_edits"],"id":"gpt-image-2","max_output":4,"modality":"image","name":"GPT Image 2","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":5,"input_image":8,"output":30},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-image-2","upstream_price":{"input":5,"input_image":8,"output":30}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1572864,"endpoints":["images","image_edits"],"id":"gpt-image-2.5-flare","max_output":4,"modality":"image","name":"GPT Image 2.5 Flare","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":5,"input_image":8,"output":30},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-image-2.5-flare","upstream_price":{"input":5,"input_image":8,"output":30}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":1572864,"endpoints":["images","image_edits"],"id":"gpt-image-2.5-sunburst","max_output":4,"modality":"image","name":"GPT Image 2.5 Sunburst","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":5,"input_image":8,"output":30},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-image-2.5-sunburst","upstream_price":{"input":5,"input_image":8,"output":30}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":131072,"endpoints":["chat","completions"],"id":"gpt-oss-120b","max_output":16384,"modality":"text","name":"gpt-oss-120b","owned_by":"openai","parameters_b":120,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"input":0.037,"output":0.17},"price_private":{"input":0.15,"output":0.6},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"openai/gpt-oss-120b","upstream_price":{"input":0.037,"output":0.17}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"openai/gpt-oss-120b","upstream_price":{"input":0.15,"output":0.6}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 120B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"gpt-oss-120b-turbo","max_output":131072,"modality":"text","name":"gpt-oss-120b Turbo","owned_by":"openai","parameters_b":120,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.15,"output":0.6},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"openai/gpt-oss-120b-Turbo","upstream_price":{"input":0.15,"output":0.6}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 120B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"gpt-oss-120b-ultra","max_output":131072,"modality":"text","name":"gpt-oss-120b Ultra","owned_by":"openai","parameters_b":120,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.2,"output":0.95},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"openai/gpt-oss-120b-Ultra","upstream_price":{"input":0.2,"output":0.95}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 120B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat","completions"],"id":"gpt-oss-20b","max_output":16384,"modality":"text","name":"gpt-oss-20b","owned_by":"openai","parameters_b":20,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.03,"output":0.14},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"openai/gpt-oss-20b","upstream_price":{"input":0.03,"output":0.14}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 20B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"gpt-transcribe","max_output":1,"modality":"transcription","name":"GPT Transcribe","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.0045,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"gpt-transcribe","upstream_price":{"input":0.0045,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"o1","max_output":100000,"modality":"text","name":"o1","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":7.5,"input":15,"output":60},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"o1","upstream_price":{"cached_input":7.5,"input":15,"output":60}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"o1-pro","max_output":100000,"modality":"text","name":"o1-pro","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":150,"output":600},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"o1-pro","upstream_price":{"input":150,"output":600}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"o3","max_output":100000,"modality":"text","name":"o3","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.5,"input":2,"output":8},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"o3","upstream_price":{"cached_input":0.5,"input":2,"output":8}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"o3-mini","max_output":100000,"modality":"text","name":"o3-mini","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.55,"input":1.1,"output":4.4},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"o3-mini","upstream_price":{"cached_input":0.55,"input":1.1,"output":4.4}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"o3-pro","max_output":100000,"modality":"text","name":"o3-pro","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":20,"output":80},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"o3-pro","upstream_price":{"input":20,"output":80}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"o4-mini","max_output":100000,"modality":"text","name":"o4-mini","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.275,"input":1.1,"output":4.4},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"o4-mini","upstream_price":{"cached_input":0.275,"input":1.1,"output":4.4}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":8191,"endpoints":["embeddings"],"id":"text-embedding-3-large","max_output":1024,"modality":"embedding","name":"text-embedding-3-large","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.13,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"text-embedding-3-large","upstream_price":{"input":0.13,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":8191,"endpoints":["embeddings"],"id":"text-embedding-3-small","max_output":1024,"modality":"embedding","name":"text-embedding-3-small","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.02,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"text-embedding-3-small","upstream_price":{"input":0.02,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":8191,"endpoints":["embeddings"],"id":"text-embedding-ada-002","max_output":1024,"modality":"embedding","name":"text-embedding-ada-002","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.1,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"text-embedding-ada-002","upstream_price":{"input":0.1,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":4096,"endpoints":["speech"],"id":"tts-1","max_output":1,"modality":"speech","name":"TTS-1","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":15,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"tts-1","upstream_price":{"input":15,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":4096,"endpoints":["speech"],"id":"tts-1-hd","max_output":1,"modality":"speech","name":"TTS-1 HD","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":30,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"tts-1-hd","upstream_price":{"input":30,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"whisper-1","max_output":1,"modality":"transcription","name":"Whisper","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.006,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"openai","region":"unknown","tee":false,"upstream_model":"whisper-1","upstream_price":{"input":0.006,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":true,"context":26214400,"endpoints":["transcriptions"],"id":"whisper-large-v3","max_output":1,"modality":"transcription","name":"Whisper Large V3","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.00045,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"openai/whisper-large-v3","upstream_price":{"input":0.00045,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio"},{"available":true,"context":26214400,"endpoints":["transcriptions"],"id":"whisper-large-v3-turbo","max_output":1,"modality":"transcription","name":"Whisper Large V3 Turbo","owned_by":"openai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.0002,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"openai/whisper-large-v3-turbo","upstream_price":{"input":0.0002,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio"},{"available":false,"context":2000,"endpoints":["videos"],"id":"pixverse-6-i2v","max_output":15,"modality":"video","name":"Pixverse-6-I2V","owned_by":"pixverse","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.06},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Pixverse/Pixverse-6-I2V","upstream_price":{"input":0,"output":0.06}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"audio":true,"image":"required","resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"pixverse-6-t2v","max_output":15,"modality":"video","name":"Pixverse-6-T2V","owned_by":"pixverse","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.06},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Pixverse/Pixverse-6-T2V","upstream_price":{"input":0,"output":0.06}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"audio":true,"resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"pixverse-t2v","max_output":5,"modality":"video","name":"Pixverse-T2V","owned_by":"pixverse","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.04},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Pixverse/Pixverse-T2V","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"pixverse-t2v-hd","max_output":5,"modality":"video","name":"Pixverse-T2V-HD","owned_by":"pixverse","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.08},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Pixverse/Pixverse-T2V-HD","upstream_price":{"input":0,"output":0.08}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 1080p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"1080p"}},{"available":false,"context":2073600,"endpoints":["images"],"id":"p-image","max_output":4,"modality":"image","name":"p-image","owned_by":"prunaai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.005},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"PrunaAI/p-image","upstream_price":{"input":0,"output":0.005}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":2073600,"endpoints":["image_edits"],"id":"p-image-edit","max_output":4,"modality":"image","name":"p-image-Edit","owned_by":"prunaai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.01},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"PrunaAI/p-image-Edit","upstream_price":{"input":0,"output":0.01}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":true,"context":2000,"endpoints":["videos"],"id":"p-video","max_output":10,"modality":"video","name":"P Video","owned_by":"prunaai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.02},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"PrunaAI/p-video","upstream_price":{"input":0,"output":0.02}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","video":{"resolution":"720p"}},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"qwen-image-edit-max","max_output":4,"modality":"image","name":"Qwen-Image-Edit-Max","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.075},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen-Image-Edit-Max","upstream_price":{"input":0,"output":0.075}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"qwen-image-max","max_output":4,"modality":"image","name":"Qwen-Image-Max","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.075},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen-Image-Max","upstream_price":{"input":0,"output":0.075}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":true,"context":32768,"endpoints":["chat"],"id":"qwen2.5-72b-instruct","max_output":32768,"modality":"text","name":"Qwen2.5 72B Instruct","owned_by":"qwen","parameters_b":72,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.36,"output":0.4},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen2.5-72B-Instruct","upstream_price":{"input":0.36,"output":0.4}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 72B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":32768,"endpoints":["chat"],"id":"qwen2.5-7b-instruct","max_output":32768,"modality":"text","name":"Qwen2.5 7B Instruct","owned_by":"qwen","parameters_b":7,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":true,"zdr":false},"price":{"input":0.1,"output":0.2},"price_private":{"input":0.1,"output":0.2},"pricing":"list","private":false,"private_listed":true,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen-2.5-7b-instruct","upstream_price":{"input":0.1,"output":0.2}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 7B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":131072,"endpoints":["chat"],"id":"qwen2.5-coder-32b-instruct","max_output":8192,"modality":"text","name":"Qwen2.5 Coder 32B Instruct","owned_by":"qwen","parameters_b":32,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.06,"output":0.2},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen2.5-Coder-32B-Instruct:nscale","upstream_price":{"input":0.06,"output":0.2}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 32B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":131072,"endpoints":["chat"],"id":"qwen2.5-coder-7b-instruct","max_output":8192,"modality":"text","name":"Qwen2.5 Coder 7B Instruct","owned_by":"qwen","parameters_b":7,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.01,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen2.5-Coder-7B-Instruct:nscale","upstream_price":{"input":0.01,"output":0.03}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 7B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":32768,"endpoints":["chat"],"id":"qwen2.5-vl-72b-instruct","max_output":8192,"modality":"text+image","name":"Qwen2.5 VL 72B Instruct","owned_by":"qwen","parameters_b":72,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":1.01,"output":1.01},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen2.5-VL-72B-Instruct:ovhcloud","upstream_price":{"input":1.01,"output":1.01}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 72B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":true,"context":40960,"endpoints":["chat"],"id":"qwen3-14b","max_output":40960,"modality":"text","name":"Qwen3 14B","owned_by":"qwen","parameters_b":14,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.12,"output":0.24},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-14B","upstream_price":{"input":0.12,"output":0.24}},{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen3-14B:nscale","upstream_price":{"input":0.07,"output":0.2}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 14B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":32000,"endpoints":["chat"],"id":"qwen3-235b-a22b","max_output":8192,"modality":"text","name":"Qwen3 235B A22B","owned_by":"qwen","parameters_b":235,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.2,"output":0.6},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen3-235B-A22B:nscale","upstream_price":{"input":0.2,"output":0.6}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 235B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3-235b-a22b-instruct-2507","max_output":16384,"modality":"text","name":"Qwen3 235B A22B Instruct 2507","owned_by":"qwen","parameters_b":235,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.09,"output":0.55},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-235B-A22B-Instruct-2507","upstream_price":{"input":0.09,"output":0.55}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 235B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":40960,"endpoints":["chat"],"id":"qwen3-30b-a3b","max_output":40960,"modality":"text","name":"Qwen3 30B A3B","owned_by":"qwen","parameters_b":30,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.12,"output":0.5},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-30B-A3B","upstream_price":{"input":0.12,"output":0.5}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 30B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":40960,"endpoints":["chat"],"id":"qwen3-32b","max_output":40960,"modality":"text","name":"Qwen3 32B","owned_by":"qwen","parameters_b":32,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"input":0.08,"output":0.28},"price_private":{"cached_input":0.08,"input":0.12,"output":0.5},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-32B","upstream_price":{"input":0.08,"output":0.28}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen3-32b","upstream_price":{"cached_input":0.052,"input":0.12,"output":0.5}},{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen3-32B:nscale","upstream_price":{"input":0.08,"output":0.25}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 32B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":262144,"endpoints":["chat"],"id":"qwen3-4b-instruct-2507","max_output":8192,"modality":"text","name":"Qwen3 4B Instruct 2507","owned_by":"qwen","parameters_b":4,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.01,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen3-4B-Instruct-2507:nscale","upstream_price":{"input":0.01,"output":0.03}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 4B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":262144,"endpoints":["chat"],"id":"qwen3-4b-thinking-2507","max_output":8192,"modality":"text","name":"Qwen3 4B Thinking 2507","owned_by":"qwen","parameters_b":4,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.01,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen3-4B-Thinking-2507:nscale","upstream_price":{"input":0.01,"output":0.03}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 4B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":40960,"endpoints":["chat"],"id":"qwen3-8b","max_output":8192,"modality":"text","name":"Qwen3 8B","owned_by":"qwen","parameters_b":8,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.07,"output":0.18},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen3-8B:nscale","upstream_price":{"input":0.07,"output":0.18}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 8B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"qwen3-asr-0.6b","max_output":1,"modality":"transcription","name":"Qwen3-ASR-0.6B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.0002,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-ASR-0.6B","upstream_price":{"input":0.0002,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"qwen3-asr-1.7b","max_output":1,"modality":"transcription","name":"Qwen3-ASR-1.7B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.00045,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-ASR-1.7B","upstream_price":{"input":0.00045,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":false,"context":128000,"endpoints":["chat"],"id":"qwen3-coder-30b-a3b-instruct","max_output":32000,"modality":"text","name":"Qwen3 Coder 30B A3B Instruct","owned_by":"qwen","parameters_b":30,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.228,"output":0.912},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"Qwen/Qwen3-Coder-30B-A3B-Instruct:scaleway","upstream_price":{"input":0.228,"output":0.912}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 30B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens","verified":false},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3-coder-480b","max_output":16384,"modality":"text","name":"Qwen3 Coder 480B A35B Instruct","owned_by":"qwen","parameters_b":480,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.1,"input":0.3,"output":1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","upstream_price":{"cached_input":0.1,"input":0.3,"output":1}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 480B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":32768,"endpoints":["embeddings"],"id":"qwen3-embedding-0.6b","max_output":1024,"modality":"embedding","name":"Qwen3-Embedding-0.6B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Embedding-0.6B","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32768,"endpoints":["embeddings"],"id":"qwen3-embedding-4b","max_output":1024,"modality":"embedding","name":"Qwen3-Embedding-4B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.02,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Embedding-4B","upstream_price":{"input":0.02,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":32768,"endpoints":["embeddings"],"id":"qwen3-embedding-8b","max_output":1024,"modality":"embedding","name":"Qwen3 Embedding 8B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Embedding-8B","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3-next-80b-a3b-instruct","max_output":262144,"modality":"text","name":"Qwen3 Next 80B A3B Instruct","owned_by":"qwen","parameters_b":80,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.09,"output":1.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Next-80B-A3B-Instruct","upstream_price":{"input":0.09,"output":1.1}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 80B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":32768,"endpoints":["rerank"],"id":"qwen3-reranker-0.6b","max_output":1024,"modality":"rerank","name":"Qwen3 Reranker 0.6B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Reranker-0.6B","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens"},{"available":false,"context":32768,"endpoints":["rerank"],"id":"qwen3-reranker-4b","max_output":1024,"modality":"rerank","name":"Qwen3-Reranker-4B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.025,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Reranker-4B","upstream_price":{"input":0.025,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":32768,"endpoints":["rerank"],"id":"qwen3-reranker-8b","max_output":1024,"modality":"rerank","name":"Qwen3 Reranker 8B","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.05,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-Reranker-8B","upstream_price":{"input":0.05,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens"},{"available":false,"context":4000,"endpoints":["speech"],"id":"qwen3-tts","max_output":1,"modality":"speech","name":"Qwen3-TTS","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":20,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-TTS","upstream_price":{"input":20,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":4000,"endpoints":["speech"],"id":"qwen3-tts-voicedesign","max_output":1,"modality":"speech","name":"Qwen3-TTS-VoiceDesign","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":20,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-TTS-VoiceDesign","upstream_price":{"input":20,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3-vl-235b-a22b-instruct","max_output":262144,"modality":"text+image","name":"Qwen3 VL 235B A22B Instruct","owned_by":"qwen","parameters_b":235,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.11,"input":0.2,"output":0.88},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-VL-235B-A22B-Instruct","upstream_price":{"cached_input":0.11,"input":0.2,"output":0.88}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 235B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3-vl-30b-a3b-instruct","max_output":262144,"modality":"text+image","name":"Qwen3 VL 30B A3B Instruct","owned_by":"qwen","parameters_b":30,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"input":0.15,"output":0.6},"price_private":{"cached_input":0.15,"input":0.2,"output":0.7},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3-VL-30B-A3B-Instruct","upstream_price":{"input":0.15,"output":0.6}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen3-vl-30b-a3b-instruct","upstream_price":{"cached_input":0.03,"input":0.2,"output":0.7}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 30B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3.5-27b","max_output":81920,"modality":"text","name":"Qwen3.5 27B","owned_by":"qwen","parameters_b":27,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"input":0.26,"output":2.6},"price_private":{"cached_input":0.26,"input":0.3,"output":2.6},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.5-27B","upstream_price":{"input":0.26,"output":2.6}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen3.5-27b","upstream_price":{"cached_input":0.03,"input":0.3,"output":2.4}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 27B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3.5-35b-a3b","max_output":81920,"modality":"text","name":"Qwen3.5 35B A3B","owned_by":"qwen","parameters_b":35,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.05,"input":0.14,"output":1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.5-35B-A3B","upstream_price":{"cached_input":0.05,"input":0.14,"output":1}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 35B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3.5-397b-a17b","max_output":81920,"modality":"text","name":"Qwen3.5 397B A17B","owned_by":"qwen","parameters_b":397,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.22,"input":0.45,"output":3},"price_private":{"cached_input":0.225,"input":0.55,"output":3.5},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.5-397B-A17B","upstream_price":{"cached_input":0.22,"input":0.45,"output":3}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen3.5-397b-a17b","upstream_price":{"cached_input":0.225,"input":0.55,"output":3.5}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 397B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3.5-9b","max_output":81920,"modality":"text","name":"Qwen3.5 9B","owned_by":"qwen","parameters_b":9,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.1,"output":0.15},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.5-9B","upstream_price":{"input":0.1,"output":0.15}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 9B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3.6-27b","max_output":81920,"modality":"text","name":"Qwen3.6 27B","owned_by":"qwen","parameters_b":27,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"input":0.32,"output":3.2},"price_private":{"cached_input":0.32,"input":0.32,"output":3.25},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.6-27B","upstream_price":{"input":0.32,"output":3.2}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen3.6-27b","upstream_price":{"cached_input":0.03,"input":0.32,"output":3.25}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 27B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3.6-35b-a3b","max_output":16384,"modality":"text","name":"Qwen3.6 35B A3B","owned_by":"qwen","parameters_b":35,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.1,"input":0.1,"output":0.95},"price_private":{"cached_input":0.1,"input":0.2,"output":1.27},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.6-35B-A3B","upstream_price":{"cached_input":0.1,"input":0.1,"output":0.95}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen3.6-35b-a3b","upstream_price":{"cached_input":0.056,"input":0.2,"output":1.27}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 35B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":128000,"endpoints":["chat"],"id":"qwen3.7-max","max_output":128000,"modality":"text","name":"Qwen3.7 Max","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.5,"input":2.5,"long_context":{"above_prompt_tokens":32000,"cached_input":1,"input":5,"output":15},"output":7.5},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.7-Max","upstream_price":{"cached_input":0.5,"input":2.5,"long_context":{"above_prompt_tokens":32000,"cached_input":1,"input":5,"output":15},"output":7.5}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($7.5 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":262144,"endpoints":["chat"],"id":"qwen3.8-27b","max_output":262144,"modality":"text","name":"Qwen3.8 27B","owned_by":"qwen","parameters_b":27,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.066666,"input":0.25,"output":3.13},"price_private":{"cached_input":0.066666,"input":0.25,"output":3.13},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.8-27B","upstream_price":{"cached_input":0.05,"input":0.2,"output":2.5}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"qwen/qwen3.8-27b","upstream_price":{"cached_input":0.05,"input":0.2,"output":2.5}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 27B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":1000000,"endpoints":["chat"],"id":"qwen3.8-flash","max_output":131072,"modality":"text","name":"Qwen3.8 Flash","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.0141,"input":0.113,"output":0.382},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.8-Flash","upstream_price":{"cached_input":0.0141,"input":0.113,"output":0.382}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.382 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":256000,"endpoints":["chat"],"id":"qwen3.8-max","max_output":256000,"modality":"text","name":"Qwen3.8 Max","owned_by":"qwen","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.206,"input":1.65,"output":4.951},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Qwen/Qwen3.8-Max","upstream_price":{"cached_input":0.206,"input":1.65,"output":4.951}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($4.951 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":5000,"endpoints":["speech"],"id":"chatterbox-multilingual","max_output":1,"modality":"speech","name":"chatterbox-multilingual","owned_by":"resembleai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":1,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ResembleAI/chatterbox-multilingual","upstream_price":{"input":1,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":true,"context":5000,"endpoints":["speech"],"id":"chatterbox-turbo","max_output":1,"modality":"speech","name":"Chatterbox Turbo","owned_by":"resembleai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":1,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"ResembleAI/chatterbox-turbo","upstream_price":{"input":1,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters"},{"available":true,"context":8192,"endpoints":["chat"],"id":"l3-8b-lunaris-v1-turbo","max_output":8192,"modality":"text","name":"L3 8B Lunaris V1 Turbo","owned_by":"sao10k","parameters_b":8,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.04,"output":0.05},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Sao10K/L3-8B-Lunaris-v1-Turbo","upstream_price":{"input":0.04,"output":0.05}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; 8B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":true,"context":131072,"endpoints":["chat"],"id":"l3.1-70b-euryale-v2.2","max_output":131072,"modality":"text","name":"L3.1 70B Euryale V2.2","owned_by":"sao10k","parameters_b":70,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.85,"output":0.85},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Sao10K/L3.1-70B-Euryale-v2.2","upstream_price":{"input":0.85,"output":0.85}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; 70B total parameters stated by the model id (70B and above is open-large)","unit":"USD per 1M tokens"},{"available":false,"context":512,"endpoints":["embeddings"],"id":"all-minilm-l12-v2","max_output":1024,"modality":"embedding","name":"all-MiniLM-L12-v2","owned_by":"sentence-transformers","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"sentence-transformers/all-MiniLM-L12-v2","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"all-minilm-l6-v2","max_output":1024,"modality":"embedding","name":"all-MiniLM-L6-v2","owned_by":"sentence-transformers","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"sentence-transformers/all-MiniLM-L6-v2","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"all-mpnet-base-v2","max_output":1024,"modality":"embedding","name":"all-mpnet-base-v2","owned_by":"sentence-transformers","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"sentence-transformers/all-mpnet-base-v2","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"clip-vit-b-32-multilingual-v1","max_output":1024,"modality":"embedding","name":"clip-ViT-B-32-multilingual-v1","owned_by":"sentence-transformers","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"sentence-transformers/clip-ViT-B-32-multilingual-v1","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"paraphrase-minilm-l6-v2","max_output":1024,"modality":"embedding","name":"paraphrase-MiniLM-L6-v2","owned_by":"sentence-transformers","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"sentence-transformers/paraphrase-MiniLM-L6-v2","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":200,"endpoints":["speech"],"id":"csm-1b","max_output":1,"modality":"speech","name":"csm-1b","owned_by":"sesame","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":7,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"sesame/csm-1b","upstream_price":{"input":7,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"text2vec-base-chinese","max_output":1024,"modality":"embedding","name":"text2vec-base-chinese","owned_by":"shibing624","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"shibing624/text2vec-base-chinese","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":3686400,"endpoints":["images"],"id":"sdxl-turbo","image_unit":{"height":1024,"width":1024},"max_output":4,"modality":"image","name":"Sdxl Turbo","owned_by":"stabilityai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":false},"price":{"input":0,"output":0.0002},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"stabilityai/sdxl-turbo","upstream_price":{"input":0,"output":0.0002}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image unit: 1024 x 1024 output pixels at the model's default step count","usage_unit":"thousandths of an image unit"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"hy4-preview","max_output":131072,"modality":"text","name":"Hy4 Preview","owned_by":"tencent","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.042,"input":0.834,"output":2.501},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"tencent/Hy4-preview","upstream_price":{"cached_input":0.042,"input":0.834,"output":2.501}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($2.501 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":512,"endpoints":["embeddings"],"id":"gte-base","max_output":1024,"modality":"embedding","name":"gte-base","owned_by":"thenlper","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.005,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"thenlper/gte-base","upstream_price":{"input":0.005,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":512,"endpoints":["embeddings"],"id":"gte-large","max_output":1024,"modality":"embedding","name":"gte-large","owned_by":"thenlper","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0.01,"output":0},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"thenlper/gte-large","upstream_price":{"input":0.01,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":true,"context":524288,"endpoints":["chat"],"id":"inkling","max_output":262144,"modality":"text+image","name":"Inkling","owned_by":"thinkingmachines","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.16,"input":0.95,"output":4.05},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"thinkingmachines/Inkling","upstream_price":{"cached_input":0.16,"input":0.95,"output":4.05}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($4.05 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":524288,"endpoints":["chat"],"id":"inkling-small","max_output":262144,"modality":"text+image","name":"Inkling Small","owned_by":"thinkingmachines","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.1,"input":0.45,"output":1.2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"thinkingmachines/Inkling-Small","upstream_price":{"cached_input":0.1,"input":0.45,"output":1.2}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($1.2 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-3-large","max_output":1024,"modality":"embedding","name":"voyage-3-large","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.18,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-3-large","upstream_price":{"input":0.18,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-3.5","max_output":1024,"modality":"embedding","name":"voyage-3.5","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.06,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-3.5","upstream_price":{"input":0.06,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-3.5-lite","max_output":1024,"modality":"embedding","name":"voyage-3.5-lite","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.02,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-3.5-lite","upstream_price":{"input":0.02,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-4","max_output":1024,"modality":"embedding","name":"voyage-4","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.06,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-4","upstream_price":{"input":0.06,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-4-large","max_output":1024,"modality":"embedding","name":"voyage-4-large","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-4-large","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-4-lite","max_output":1024,"modality":"embedding","name":"voyage-4-lite","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.02,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-4-lite","upstream_price":{"input":0.02,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":16000,"endpoints":["embeddings"],"id":"voyage-code-2","max_output":1024,"modality":"embedding","name":"voyage-code-2","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-code-2","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-code-3","max_output":1024,"modality":"embedding","name":"voyage-code-3","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.18,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-code-3","upstream_price":{"input":0.18,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-code-4","max_output":1024,"modality":"embedding","name":"voyage-code-4","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-code-4","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-context-3","max_output":1024,"modality":"embedding","name":"voyage-context-3","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.18,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-context-3","upstream_price":{"input":0.18,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-context-4","max_output":1024,"modality":"embedding","name":"voyage-context-4","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-context-4","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-finance-2","max_output":1024,"modality":"embedding","name":"voyage-finance-2","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-finance-2","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":16000,"endpoints":["embeddings"],"id":"voyage-law-2","max_output":1024,"modality":"embedding","name":"voyage-law-2","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-law-2","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-multilingual-2","max_output":1024,"modality":"embedding","name":"voyage-multilingual-2","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-multilingual-2","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-multimodal-3","max_output":1024,"modality":"embedding","name":"voyage-multimodal-3","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-multimodal-3","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["embeddings"],"id":"voyage-multimodal-3.5","max_output":1024,"modality":"embedding","name":"voyage-multimodal-3.5","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.12,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"voyage-multimodal-3.5","upstream_price":{"input":0.12,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["rerank"],"id":"voyage-rerank-2.5","max_output":1024,"modality":"rerank","name":"rerank-2.5","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.05,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"rerank-2.5","upstream_price":{"input":0.05,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["rerank"],"id":"voyage-rerank-2.5-lite","max_output":1024,"modality":"rerank","name":"rerank-2.5-lite","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.02,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"rerank-2.5-lite","upstream_price":{"input":0.02,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["rerank"],"id":"voyage-rerank-3","max_output":1024,"modality":"rerank","name":"rerank-3","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.05,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"rerank-3","upstream_price":{"input":0.05,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":32000,"endpoints":["rerank"],"id":"voyage-rerank-3-lite","max_output":1024,"modality":"rerank","name":"rerank-3-lite","owned_by":"voyageai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.02,"output":0},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":true,"zdr":false},"enabled":false,"provider":"voyage","region":"unknown","tee":false,"upstream_model":"rerank-3-lite","upstream_price":{"input":0.02,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M tokens","usage_unit":"tokens","verified":false},{"available":false,"context":2000,"endpoints":["videos"],"id":"wan2.2-t2v-a14b","max_output":5,"modality":"video","name":"Wan2.2-T2V-A14B","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.075},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.2-T2V-A14B","upstream_price":{"input":0,"output":0.075}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"wan2.6-i2v","max_output":15,"modality":"video","name":"Wan2.6-I2V","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.6-I2V","upstream_price":{"input":0,"output":0.1}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"image":"required","resolution":"720p"}},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"wan2.6-image-edit","max_output":4,"modality":"image","name":"Wan2.6-Image-Edit","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.6-Image-Edit","upstream_price":{"input":0,"output":0.03}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"wan2.6-t2i","max_output":4,"modality":"image","name":"Wan2.6-T2I","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.6-T2I","upstream_price":{"input":0,"output":0.03}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":2000,"endpoints":["videos"],"id":"wan2.6-t2v","max_output":15,"modality":"video","name":"Wan2.6-T2V","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.6-T2V","upstream_price":{"input":0,"output":0.1}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"wan2.7-i2v","max_output":15,"modality":"video","name":"Wan2.7 I2V","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.7-I2V","upstream_price":{"input":0,"output":0.1}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"image":"required","resolution":"720p"}},{"available":false,"context":3686400,"endpoints":["image_edits"],"id":"wan2.7-image-edit","max_output":4,"modality":"image","name":"Wan2.7-Image-Edit","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.03},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.7-Image-Edit","upstream_price":{"input":0,"output":0.03}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":2000,"endpoints":["videos"],"id":"wan2.7-r2v","max_output":15,"modality":"video","name":"Wan2.7-R2V","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":false,"retains":true,"trains":true,"zdr":false},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan2.7-R2V","upstream_price":{"input":0,"output":0.1}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"image":"required","resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"wan3.0-video","max_output":15,"modality":"video","name":"Wan3.0-Video","owned_by":"wan-ai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"input":0,"output":0.1},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"Wan-AI/Wan3.0-Video","upstream_price":{"input":0,"output":0.1}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"audio":true,"image":"optional","resolution":"720p"}},{"available":false,"context":1000000,"endpoints":["chat"],"id":"grok-4.20-non-reasoning","max_output":128000,"modality":"text","name":"Grok 4.20 (Non-Reasoning)","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.2,"input":1.25,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2.5,"output":5},"output":2.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-4.20-0309-non-reasoning","upstream_price":{"cached_input":0.2,"input":1.25,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2.5,"output":5},"output":2.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1000000,"endpoints":["chat"],"id":"grok-4.20-reasoning","max_output":128000,"modality":"text","name":"Grok 4.20","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.2,"input":1.25,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2.5,"output":5},"output":2.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-4.20-0309-reasoning","upstream_price":{"cached_input":0.2,"input":1.25,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2.5,"output":5},"output":2.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":1000000,"endpoints":["chat"],"id":"grok-4.3","max_output":128000,"modality":"text","name":"Grok 4.3","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.2,"input":1.25,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2.5,"output":5},"output":2.5},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-4.3","upstream_price":{"cached_input":0.2,"input":1.25,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2.5,"output":5},"output":2.5}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":500000,"endpoints":["chat"],"id":"grok-4.5","max_output":128000,"modality":"text","name":"Grok 4.5","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.3,"input":2,"long_context":{"above_prompt_tokens":199999,"cached_input":0.6,"input":4,"output":12},"output":6},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-4.5","upstream_price":{"cached_input":0.3,"input":2,"long_context":{"above_prompt_tokens":199999,"cached_input":0.6,"input":4,"output":12},"output":6}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":500000,"endpoints":["chat"],"id":"grok-4.6","max_output":128000,"modality":"text","name":"Grok 4.6","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.5,"input":2,"long_context":{"above_prompt_tokens":199999,"cached_input":1,"input":4,"output":12},"output":6},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-4.6","upstream_price":{"cached_input":0.5,"input":2,"long_context":{"above_prompt_tokens":199999,"cached_input":1,"input":4,"output":12},"output":6}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":500000,"endpoints":["chat"],"id":"grok-4.7","max_output":128000,"modality":"text","name":"Grok 4.7","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.5,"input":2,"long_context":{"above_prompt_tokens":199999,"cached_input":1,"input":4,"output":12},"output":6},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-4.7","upstream_price":{"cached_input":0.5,"input":2,"long_context":{"above_prompt_tokens":199999,"cached_input":1,"input":4,"output":12},"output":6}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":256000,"endpoints":["chat"],"id":"grok-build-0.1","max_output":128000,"modality":"text","name":"Grok Build 0.1","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.2,"input":1,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2,"output":4},"output":2},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-build-0.1","upstream_price":{"cached_input":0.2,"input":1,"long_context":{"above_prompt_tokens":199999,"cached_input":0.4,"input":2,"output":4},"output":2}}],"tee":false,"tier":"frontier","tier_basis":"a route to a frontier provider; priced at the provider's list price (passthrough)","unit":"USD per 1M tokens","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"grok-imagine-image","max_output":4,"modality":"image","name":"Grok Imagine Image","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.02},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-imagine-image","upstream_price":{"input":0,"output":0.02}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"grok-imagine-image-2.0","max_output":4,"modality":"image","name":"Grok Imagine Image 2.0","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.04},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-imagine-image-2.0","upstream_price":{"input":0,"output":0.04}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":3686400,"endpoints":["images"],"id":"grok-imagine-image-quality","max_output":4,"modality":"image","name":"Grok Imagine Image Quality","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.05},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-imagine-image-quality","upstream_price":{"input":0,"output":0.05}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per image","usage_unit":"thousandths of an image unit","verified":false},{"available":false,"context":2000,"endpoints":["videos"],"id":"grok-imagine-video","max_output":15,"modality":"video","name":"Grok Imagine Video","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.07},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-imagine-video","upstream_price":{"input":0,"output":0.07}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"grok-imagine-video-1.5","max_output":15,"modality":"video","name":"Grok Imagine Video 1.5","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.14},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-imagine-video-1.5","upstream_price":{"input":0,"output":0.14}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"720p"}},{"available":false,"context":2000,"endpoints":["videos"],"id":"grok-imagine-video-1.5-lite","max_output":15,"modality":"video","name":"Grok Imagine Video 1.5 Lite","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples: an image or video model gets one check request a night, so its latency is published once traffic brings it to 20 requests in 7 days","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0,"output":0.03},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-imagine-video-1.5-lite","upstream_price":{"input":0,"output":0.03}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per second of output video at 720p","usage_unit":"milliseconds of video","verified":false,"video":{"resolution":"720p"}},{"available":false,"context":60000,"endpoints":["speech"],"id":"grok-tts","max_output":1,"modality":"speech","name":"Grok TTS","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":15,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-tts","upstream_price":{"input":15,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per 1M characters","usage_unit":"characters","verified":false},{"available":false,"context":26214400,"endpoints":["transcriptions"],"id":"grok-voice-transcribe-2.0","max_output":1,"modality":"transcription","name":"Grok Voice Transcribe 2.0","owned_by":"xai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"input":0.0017,"output":0},"pricing":"passthrough","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":true,"trains":false,"zdr":false},"enabled":false,"provider":"xai","region":"unknown","tee":false,"upstream_model":"grok-voice-transcribe-2.0","upstream_price":{"input":0.0017,"output":0}}],"tee":false,"tier":null,"tier_basis":"another modality: priced per its own unit, not per token, so it belongs to no tier (the compute index prices text inference only)","unit":"USD per minute of audio","usage_unit":"milliseconds of audio","verified":false},{"available":true,"context":1048576,"endpoints":["chat"],"id":"mimo-v2.6-flash","max_output":1048576,"modality":"text","name":"MiMo V2.6 Flash","owned_by":"xiaomi","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.0028,"input":0.14,"output":0.28},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"XiaomiMiMo/MiMo-V2.6-Flash","upstream_price":{"cached_input":0.0028,"input":0.14,"output":0.28}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.28 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"mimo-v2.6-pro","max_output":1048576,"modality":"text","name":"MiMo V2.6 Pro","owned_by":"xiaomi","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.0036,"input":0.43,"output":0.87},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"XiaomiMiMo/MiMo-V2.6-Pro","upstream_price":{"cached_input":0.0036,"input":0.43,"output":0.87}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.87 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":128000,"endpoints":["chat"],"id":"glm-4.5-air","max_output":8192,"modality":"text","name":"GLM-4.5 Air","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.03,"input":0.2,"output":1.1},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"zai-org/GLM-4.5-Air:zai-org","upstream_price":{"cached_input":0.03,"input":0.2,"output":1.1}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($1.1 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens","verified":false},{"available":false,"context":64000,"endpoints":["chat"],"id":"glm-4.5v","max_output":8192,"modality":"text","name":"GLM-4.5V","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.11,"input":0.6,"output":1.8},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"zai-org/GLM-4.5V:zai-org","upstream_price":{"cached_input":0.11,"input":0.6,"output":1.8}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($1.8 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens","verified":false},{"available":true,"context":202752,"endpoints":["chat"],"id":"glm-4.6","max_output":131072,"modality":"text","name":"GLM-4.6","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.1,"input":0.5,"output":2},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"zai-org/GLM-4.6","upstream_price":{"cached_input":0.1,"input":0.5,"output":2}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($2 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":128000,"endpoints":["chat"],"id":"glm-4.6v","max_output":8192,"modality":"text","name":"GLM-4.6V","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.05,"input":0.3,"output":0.9},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"zai-org/GLM-4.6V:zai-org","upstream_price":{"cached_input":0.05,"input":0.3,"output":0.9}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.9 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens","verified":false},{"available":true,"context":202752,"endpoints":["chat"],"id":"glm-4.7","max_output":16384,"modality":"text","name":"GLM-4.7","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":false,"zdr":true},"price":{"cached_input":0.08,"input":0.4,"output":1.75},"pricing":"list","private":false,"private_listed":false,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"zai-org/GLM-4.7","upstream_price":{"cached_input":0.08,"input":0.4,"output":1.75}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($1.75 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":false,"context":200000,"endpoints":["chat"],"id":"glm-4.7-flash","max_output":8192,"modality":"text","name":"GLM-4.7 Flash","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.01,"input":0.07,"output":0.4},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"zai-org/GLM-4.7-Flash:zai-org","upstream_price":{"cached_input":0.01,"input":0.07,"output":0.4}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.4 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens","verified":false},{"available":false,"context":200000,"endpoints":["chat"],"id":"glm-5","max_output":8192,"modality":"text","name":"GLM-5","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":false,"zdr":false},"price":{"cached_input":0.2,"input":1,"output":3.2},"pricing":"list","private":false,"private_listed":false,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"zai-org/GLM-5:zai-org","upstream_price":{"cached_input":0.2,"input":1,"output":3.2}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($3.2 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens","verified":false},{"available":false,"context":202752,"endpoints":["chat"],"id":"glm-5.1","max_output":128000,"modality":"text","name":"GLM-5.1","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":false,"private":true,"zdr":false},"price":{"cached_input":0.6,"input":1.21,"output":4.2},"price_private":{"cached_input":0.6,"input":1.21,"output":4.2},"pricing":"list","private":false,"private_listed":true,"region":"unknown","routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"z-ai/glm-5.1","upstream_price":{"cached_input":0.6,"input":1.21,"output":4.2}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($4.2 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens","verified":false},{"available":true,"context":1048576,"endpoints":["chat"],"id":"glm-5.2","max_output":163840,"modality":"text","name":"GLM-5.2","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.18,"input":0.94,"output":3},"price_private":{"cached_input":0.22,"input":1.26,"output":3},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"zai-org/GLM-5.2","upstream_price":{"cached_input":0.14,"input":0.75,"output":2.4}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"z-ai/glm-5.2","upstream_price":{"cached_input":0.22,"input":1.26,"output":3}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($3 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"glm-5.3","max_output":131072,"modality":"text","name":"GLM-5.3","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.25,"input":1.13,"output":5},"price_private":{"cached_input":0.26,"input":1.4,"output":5},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"zai-org/GLM-5.3","upstream_price":{"cached_input":0.2,"input":0.9,"output":4}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"z-ai/glm-5.3","upstream_price":{"cached_input":0.26,"input":1.4,"output":4.4}}],"tee":false,"tier":"open-large","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($5 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"},{"available":true,"context":1048576,"endpoints":["chat"],"id":"glm-5.3-flash","max_output":16384,"modality":"text","name":"GLM-5.3 Flash","owned_by":"zai","parameters_b":null,"performance":{"latency_p50_ms":null,"latency_p95_ms":null,"note":"insufficient samples","samples":null,"tokens_per_second":null},"policy_asks":{"no_training":true,"private":true,"zdr":true},"price":{"cached_input":0.04,"input":0.19,"output":0.63},"price_private":{"cached_input":0.04,"input":0.19,"output":0.63},"pricing":"list","private":false,"private_listed":true,"region":["us"],"routes":[{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":true,"provider":"deepinfra","region":"us","tee":false,"upstream_model":"zai-org/GLM-5.3-Flash","upstream_price":{"cached_input":0.03,"input":0.15,"output":0.5}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"provider":"novita","region":"unknown","tee":false,"upstream_model":"zai-org/glm-5.3-flash","upstream_price":{"cached_input":0.03,"input":0.15,"output":0.5}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"provider":"fireworks","region":"unknown","tee":false,"upstream_model":"accounts/fireworks/models/glm-5p3-flash","upstream_price":{"cached_input":0.03,"input":0.15,"output":0.5}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":true},"enabled":false,"private":true,"provider":"redpill","region":"unknown","tee":true,"upstream_model":"z-ai/glm-5.3-flash","upstream_price":{"cached_input":0.03,"input":0.15,"output":0.5}},{"data_policy":{"known":true,"retains":false,"trains":false,"zdr":false},"enabled":false,"provider":"huggingface","region":"unknown","tee":false,"upstream_model":"zai-org/GLM-5.3-Flash:zai-org","upstream_price":{"cached_input":0.03,"input":0.15,"output":0.5}}],"tee":false,"tier":"open-small","tier_basis":"open-weight; the model id states no parameter count, so the sheet output price ($0.63 per 1M; $1.00 and above is open-large) decides","unit":"USD per 1M tokens"}],"models_available":92,"models_listed":334,"object":"catalog","performance":{"available":true,"min_samples":20,"note":"Latency is the gateway's wall time per request (ms, p50 and p95) over its own usage rows for the last 7 days, every endpoint but tool calls; throughput is the median of completion tokens per second of wall time (time to first token included) over completed text requests of at least 64 completion tokens (text models only). Under 20 requests every figure, the request count included, is null with the reason. The rows include the gateway's own nightly catalog check: every text model that passes gets its one-word check and 4 requests for about 200 tokens of output a night (count from 1 to 100, at most 256 tokens), and every embedding, rerank, speech and transcription model its check and 4 more of the same, so each has a measured latency and each text model a throughput; an image or video model gets its one check request, so its latency is published once traffic brings it to 20. Those requests are left out of every usage figure (/v1/network, /v1/rankings, /v1/stats, the compute index), which count market traffic only.","since":"2026-10-03T22:04:18.710258+00:00","throughput_min_completion_tokens":64,"window_days":7},"policy_asks_note":"Whether a request that asks for zero data retention (provider.zdr) or no training (provider.data_collection: deny) has a route for this model at its ordinary price, and whether an attested route can serve it privately (provider.private). False: every route's policy either keeps or trains on content or is not verified, and such a request is refused no_route_for_policy before anything is held.","price_sheet":{"archive":"https://api.usdf.fi/v1/pricing/sheets/b762726f315faa132fbf786059f11f26257871f4f3aee37596fea4909f26fef3","sha256":"b762726f315faa132fbf786059f11f26257871f4f3aee37596fea4909f26fef3","unit":"USD per 1M tokens","units":"unit is the sheet's unit for text models; every model carries its own unit (models[].unit), and a model of another modality is priced in it: per 1M tokens of input, per 1M characters, per minute of audio, per image unit or per second of video","url":"https://api.usdf.fi/v1/pricing","version":"2026-10-10.1"},"regions":{"checked":"2026-10-01","providers":{"anthropic":{"note":"No processing location is published for the commercial API.","region":"unknown","source":"https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-personal-data"},"deepinfra":{"note":"Privacy policy: data may be transferred, stored and processed outside the user's jurisdiction, specifically in the United States.","region":"us","source":"https://deepinfra.com/privacy"},"fireworks":{"note":"\"By default, deployments are multi-region: Fireworks can move and spread them across regions as needed.\" The Standard serverless routes the gateway uses are not pinned to a region; the US-only SKUs are a dearer service tier it does not route.","region":"unknown","source":"https://docs.fireworks.ai/deployments/regions"},"gemini":{"note":"Paid services terms: data may be stored transiently or cached in any country in which Google or its agents maintain facilities.","region":"unknown","source":"https://ai.google.dev/gemini-api/terms"},"huggingface":{"note":"Hugging Face publishes no processing location for the router, which every request crosses, so no route through it has a known region. Where the pinned providers say they process: Scaleway Paris, France (scaleway.com/en/docs/generative-apis/reference-content/data-privacy); OVHcloud AI Endpoints the European Union (ovhcloud.com/en/public-cloud/ai-endpoints); Z.ai Singapore (docs.z.ai/legal-agreement/privacy-policy, DPA 3(a)); Nscale, Cerebras, Novita and Fireworks serverless publish none.","region":"unknown","source":"https://huggingface.co/docs/inference-providers/security"},"mistral":{"note":"\"We prioritize selecting providers within the European Union ... However, in exceptional cases, we may opt for non-EU providers\"; api.mistral.ai is the global endpoint.","region":"unknown","source":"https://legal.mistral.ai/terms/privacy-policy"},"novita":{"note":"Privacy policy (last updated May 13, 2026), International Data Transfers: \"We may transfer Personal Information to countries outside your country or region, including the United States.\" No processing location is published for inference.","region":"unknown","source":"https://novita.ai/legal/privacy-policy"},"openai":{"note":"Without the data-residency setting on the account, processing is not pinned to a region; data residency (United States, Europe and others) is a per-project setting the gateway's account has not enabled.","region":"unknown","source":"https://developers.openai.com/api/docs/guides/your-data"},"redpill":{"note":"No location is published for the enclave backends; the attestation report, not a region, is what the Private tier offers.","region":"unknown","source":"https://redpill.ai/privacy"},"together":{"note":"No processing location is published for serverless inference.","region":"unknown","source":"https://www.together.ai/privacy"},"voyage":{"note":"The privacy policy publishes no processing location for the API.","region":"unknown","source":"https://www.voyageai.com/privacy"},"xai":{"note":"\"https://api.x.ai is the global endpoint. SpaceXAI may route requests between regions for capacity or reliability, so the processing location is not guaranteed.\" The US endpoint (us.api.x.ai) is 10% dearer and is never used.","region":"unknown","source":"https://docs.x.ai/developers/advanced-api-usage/regions"}}},"signer":"0xE19B4CaEB29409f2F6AFc10Edc98542c5d122B7a","tiers":{"frontier":"a route to a frontier provider (Anthropic, OpenAI other than gpt-oss, Google Gemini); priced at the provider's list price","none":"tier null: a model of another modality (embeddings, images, speech, transcription, rerank, video), priced per its own unit and outside the compute index","open-large":"open-weight; the id states 70B or more total parameters, or states none and the sheet output price is at or above $1.00 per 1M tokens","open-small":"every other open-weight model","rule":"the compute index's tier rule, read off the price sheet entry alone (GET /v1/index/tiers lists every model's tier)"},"token":{"address":"0x4A35a5eC2A50A4d2957B2F2366E017f526cAB318","note":"1 USDF = $1 of compute, redeemable 1:1 for USDG at any time.","symbol":"USDF","usd_per_token":"1"}}