{"api_version":"v1","generated":"2026-10-24T05:40:31+00:00","source":"https://tensorust.com","license":"CC BY 4.0, credit Tensorust with a link","docs":"https://tensorust.com/developers/","count":71,"snapshot":"2026-10-23","unit":"USD per 1M tokens","workloads":[{"id":"chat","name":"Chatbot reply","input_tokens":1500,"output_tokens":400,"cached_input_tokens":1000,"description":"a 1,500-token prompt (1,000 of it a fixed system prompt) and a 400-token answer"},{"id":"rag","name":"Answer from your docs (RAG)","input_tokens":6000,"output_tokens":500,"cached_input_tokens":1000,"description":"6,000 tokens of retrieved context plus the question, a 500-token answer"},{"id":"sum","name":"Summarize a long document","input_tokens":20000,"output_tokens":800,"cached_input_tokens":1000,"description":"a 20,000-token document in, an 800-token summary out"},{"id":"agent","name":"Coding agent step","input_tokens":40000,"output_tokens":2000,"cached_input_tokens":30000,"description":"40,000 tokens of repo context and history (30,000 of it repeated from the last step), 2,000 out"},{"id":"batch","name":"Batch extraction","input_tokens":2000,"output_tokens":300,"cached_input_tokens":0,"description":"2,000 tokens per record in, 300 tokens of JSON out, sent through the batch API where there is one"},{"id":"long","name":"Long-document Q&A","input_tokens":150000,"output_tokens":1000,"cached_input_tokens":0,"description":"a 150,000-token contract or codebase in one prompt, a 1,000-token answer"}],"note":"Workload costs are USD for ONE request. Prices come from each provider pricing page (source_url) on the date in checked.","models":[{"provider":"openai","model":"gpt-5-nano","name":"GPT-5 nano","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.05,"output":0.4,"cache_write":null,"cache_read":0.005,"batch_input":0.025,"batch_output":0.2,"long_context":null,"other_tiers":{"flex":{"input":0.025,"output":0.2,"cache_read":0.0025}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.0025; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5-nano","note":"Page labels this model \"Deprecated\"."},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-5-nano","slug":"gpt-5-nano","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-nano/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-nano","chat_cost_rank":1,"workloads":{"chat":{"standard":0.000235,"with_cache":0.00019,"batch":null},"rag":{"standard":0.0005,"with_cache":0.000455,"batch":null},"sum":{"standard":0.00132,"with_cache":0.001275,"batch":null},"agent":{"standard":0.0028,"with_cache":0.00145,"batch":null},"batch":{"standard":0.00022,"with_cache":null,"batch":0.00011},"long":{"standard":0.0079,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4.1-nano","name":"GPT-4.1 nano","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.1,"output":0.4,"cache_write":null,"cache_read":0.025,"batch_input":0.05,"batch_output":0.2,"long_context":null,"other_tiers":{"fast":{"input":0.2,"output":0.8,"cache_read":0.05}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1047576,"max_output":32768,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-4.1-nano","note":"Page labels this model \"Shut down\"."},"ctx":1047576,"maxout":32768,"mod":["text","image"],"tools":true,"life":"shut down","ok":false,"id":"gpt-4.1-nano","slug":"gpt-4-1-nano","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4-1-nano/","api":"https://api.tensorust.com/v1/llm/models/gpt-4-1-nano","chat_cost_rank":2,"workloads":{"chat":{"standard":0.00031,"with_cache":0.000235,"batch":null},"rag":{"standard":0.0008,"with_cache":0.000725,"batch":null},"sum":{"standard":0.00232,"with_cache":0.002245,"batch":null},"agent":{"standard":0.0048,"with_cache":0.00255,"batch":null},"batch":{"standard":0.00032,"with_cache":null,"batch":0.00016},"long":{"standard":0.0154,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.1,"output":0.4,"cache_write":null,"cache_read":0.01,"batch_input":0.05,"batch_output":0.2,"long_context":null,"other_tiers":{"flex":{"input":0.05,"output":0.2,"cache_read":0.01},"priority":{"input":0.18,"output":0.72,"cache_read":0.018}},"scheduled":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; explicit cache storage 1 USD per 1M tokens per hour; audio input is priced higher; see page","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite","note":"Per ai.google.dev/gemini-api/docs/models: access limited to users who have used 2.5 models before; not deprecated."},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"limited access","ok":false,"id":"gemini-2.5-flash-lite","slug":"gemini-2-5-flash-lite","provider_name":"Google","url":"https://tensorust.com/llm/gemini-2-5-flash-lite/","api":"https://api.tensorust.com/v1/llm/models/gemini-2-5-flash-lite","chat_cost_rank":3,"workloads":{"chat":{"standard":0.00031,"with_cache":0.00022,"batch":null},"rag":{"standard":0.0008,"with_cache":0.00071,"batch":null},"sum":{"standard":0.00232,"with_cache":0.00223,"batch":null},"agent":{"standard":0.0048,"with_cache":0.0021,"batch":null},"batch":{"standard":0.00032,"with_cache":null,"batch":0.00016},"long":{"standard":0.0154,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-haiku-5-5","name":"Claude Haiku 5.5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.1,"output":0.5,"cache_write":{"5m":0.125,"1h":0.2},"cache_read":0.01,"batch_input":0.05,"batch_output":0.25,"long_context":{"threshold_tokens":100000,"applies_when":"prompt (all input tokens incl. cache reads and writes) is over threshold_tokens","input":0.5,"output":2.5,"cache_write":{"5m":0.625,"1h":1},"cache_read":0.05,"batch_input":0.25,"batch_output":1.25},"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://platform.claude.com/docs/en/about-claude/models/overview","note":"Current model. Page lists 1M tokens context, 128K tokens max output"},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":1,"big":false,"id":"claude-haiku-5-5","slug":"claude-haiku-5-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-haiku-5-5/","api":"https://api.tensorust.com/v1/llm/models/claude-haiku-5-5","chat_cost_rank":4,"workloads":{"chat":{"standard":0.00035,"with_cache":0.00026,"batch":null},"rag":{"standard":0.00085,"with_cache":0.00076,"batch":null},"sum":{"standard":0.0024,"with_cache":0.00231,"batch":null},"agent":{"standard":0.005,"with_cache":0.0023,"batch":null},"batch":{"standard":0.00035,"with_cache":null,"batch":0.000175},"long":{"standard":0.0775,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-6-luna","name":"GPT-6 Luna","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.1,"output":0.5,"cache_write":{"30m":0.125,"12h":0.25},"cache_read":0.01,"batch_input":0.05,"batch_output":0.25,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":0.2,"output":0.75,"cache_write":{"30m":0.25,"12h":0.5},"cache_read":0.02,"batch_input":0.1,"batch_output":0.375},"other_tiers":{"flex":{"input":0.05,"output":0.25,"cache_read":0.005},"fast":{"input":0.2,"output":1,"cache_read":0.02}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.005; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-6-luna"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":1,"big":false,"id":"gpt-6-luna","slug":"gpt-6-luna","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-6-luna/","api":"https://api.tensorust.com/v1/llm/models/gpt-6-luna","chat_cost_rank":5,"workloads":{"chat":{"standard":0.00035,"with_cache":0.00026,"batch":null},"rag":{"standard":0.00085,"with_cache":0.00076,"batch":null},"sum":{"standard":0.0024,"with_cache":0.00231,"batch":null},"agent":{"standard":0.005,"with_cache":0.0023,"batch":null},"batch":{"standard":0.00035,"with_cache":null,"batch":0.000175},"long":{"standard":0.0155,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4o-mini","name":"GPT-4o mini","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.15,"output":0.6,"cache_write":null,"cache_read":0.075,"batch_input":0.075,"batch_output":0.3,"long_context":null,"other_tiers":{"fast":{"input":0.25,"output":1,"cache_read":0.125}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":128000,"max_output":16384,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-4o-mini","note":"Page labels this model \"Deprecated\"."},"ctx":128000,"maxout":16384,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-4o-mini","slug":"gpt-4o-mini","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4o-mini/","api":"https://api.tensorust.com/v1/llm/models/gpt-4o-mini","chat_cost_rank":6,"workloads":{"chat":{"standard":0.000465,"with_cache":0.00039,"batch":null},"rag":{"standard":0.0012,"with_cache":0.001125,"batch":null},"sum":{"standard":0.00348,"with_cache":0.003405,"batch":null},"agent":{"standard":0.0072,"with_cache":0.00495,"batch":null},"batch":{"standard":0.00048,"with_cache":null,"batch":0.00024},"long":{"standard":0.0231,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.6-luna","name":"GPT-5.6 Luna","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.2,"output":1.2,"cache_write":{"30m":0.25,"12h":0.5},"cache_read":0.02,"batch_input":0.1,"batch_output":0.6,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":0.4,"output":1.8,"cache_write":{"30m":0.5,"12h":1},"cache_read":0.04,"batch_input":0.2,"batch_output":0.9},"other_tiers":{"flex":{"input":0.1,"output":0.6,"cache_read":0.01},"fast":{"input":0.4,"output":2.4,"cache_read":0.04}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.01; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.6-luna"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":3,"big":false,"id":"gpt-5.6-luna","slug":"gpt-5-6-luna","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-6-luna/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-6-luna","chat_cost_rank":7,"workloads":{"chat":{"standard":0.00078,"with_cache":0.0006,"batch":null},"rag":{"standard":0.0018,"with_cache":0.00162,"batch":null},"sum":{"standard":0.00496,"with_cache":0.00478,"batch":null},"agent":{"standard":0.0104,"with_cache":0.005,"batch":null},"batch":{"standard":0.00076,"with_cache":null,"batch":0.00038},"long":{"standard":0.0312,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.4-nano","name":"GPT-5.4 nano","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.2,"output":1.25,"cache_write":null,"cache_read":0.02,"batch_input":0.1,"batch_output":0.625,"long_context":null,"other_tiers":{"flex":{"input":0.1,"output":0.625,"cache_read":0.01}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.01; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.4-nano","note":"Page labels this model \"Deprecated\"."},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-5.4-nano","slug":"gpt-5-4-nano","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-4-nano/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-4-nano","chat_cost_rank":8,"workloads":{"chat":{"standard":0.0008,"with_cache":0.00062,"batch":null},"rag":{"standard":0.001825,"with_cache":0.001645,"batch":null},"sum":{"standard":0.005,"with_cache":0.00482,"batch":null},"agent":{"standard":0.0105,"with_cache":0.0051,"batch":null},"batch":{"standard":0.000775,"with_cache":null,"batch":0.000387},"long":{"standard":0.03125,"with_cache":null,"batch":null}}},{"provider":"deepseek","model":"deepseek-flash","name":"DeepSeek Flash","aliases":["deepseek-v4-flash","deepseek-v4-flash-vision-exp"],"status":"listed","unit":"USD per 1M tokens","input":0.3,"output":1.2,"cache_write":null,"cache_read":0.006,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":{"offpeak":{"input":0.15,"output":0.6,"cache_read":0.003}},"scheduled":null,"source_url":"https://api-docs.deepseek.com/quick_start/pricing","checked":"2026-10-23","note":"input/output/cache_read are peak-hour prices; other_tiers.offpeak is the off-peak price (peak hours: 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays); deepseek-v4-flash and deepseek-v4-flash-vision-exp are retired names now billed at the flash price; null means the page lists no price: batch_input, batch_output","f":{"context_window":1000000,"max_output":384000,"input_modalities":["text","image"],"tools":true,"source_url":"https://api-docs.deepseek.com/quick_start/pricing/","note":"Page states context length 1M and max output maximum 384K; served by DeepSeek-V4.1-Flash-1017; Vision supported."},"ctx":1000000,"maxout":384000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":4,"big":false,"id":"deepseek-flash","slug":"deepseek-flash","provider_name":"DeepSeek","url":"https://tensorust.com/llm/deepseek-flash/","api":"https://api.tensorust.com/v1/llm/models/deepseek-flash","chat_cost_rank":9,"workloads":{"chat":{"standard":0.00093,"with_cache":0.000636,"batch":null},"rag":{"standard":0.0024,"with_cache":0.002106,"batch":null},"sum":{"standard":0.00696,"with_cache":0.006666,"batch":null},"agent":{"standard":0.0144,"with_cache":0.00558,"batch":null},"batch":{"standard":0.00096,"with_cache":null,"batch":null},"long":{"standard":0.0462,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.25,"output":1.5,"cache_write":null,"cache_read":0.025,"batch_input":0.125,"batch_output":0.75,"long_context":null,"other_tiers":{"flex":{"input":0.125,"output":0.75,"cache_read":0.0125},"priority":{"input":0.45,"output":2.7,"cache_read":0.045}},"scheduled":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; explicit cache storage 1 USD per 1M tokens per hour; audio input is priced higher; see page","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite"},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"current","ok":true,"ccrank":5,"big":false,"id":"gemini-3.1-flash-lite","slug":"gemini-3-1-flash-lite","provider_name":"Google","url":"https://tensorust.com/llm/gemini-3-1-flash-lite/","api":"https://api.tensorust.com/v1/llm/models/gemini-3-1-flash-lite","chat_cost_rank":10,"workloads":{"chat":{"standard":0.000975,"with_cache":0.00075,"batch":null},"rag":{"standard":0.00225,"with_cache":0.002025,"batch":null},"sum":{"standard":0.0062,"with_cache":0.005975,"batch":null},"agent":{"standard":0.013,"with_cache":0.00625,"batch":null},"batch":{"standard":0.00095,"with_cache":null,"batch":0.000475},"long":{"standard":0.039,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5-mini","name":"GPT-5 mini","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.25,"output":2,"cache_write":null,"cache_read":0.025,"batch_input":0.125,"batch_output":1,"long_context":null,"other_tiers":{"flex":{"input":0.125,"output":1,"cache_read":0.0125},"fast":{"input":0.45,"output":3.6,"cache_read":0.045}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.0125; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5-mini","note":"Page labels this model \"Deprecated\"."},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-5-mini","slug":"gpt-5-mini","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-mini/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-mini","chat_cost_rank":11,"workloads":{"chat":{"standard":0.001175,"with_cache":0.00095,"batch":null},"rag":{"standard":0.0025,"with_cache":0.002275,"batch":null},"sum":{"standard":0.0066,"with_cache":0.006375,"batch":null},"agent":{"standard":0.014,"with_cache":0.00725,"batch":null},"batch":{"standard":0.0011,"with_cache":null,"batch":0.00055},"long":{"standard":0.0395,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4.1-mini","name":"GPT-4.1 mini","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.4,"output":1.6,"cache_write":null,"cache_read":0.1,"batch_input":0.2,"batch_output":0.8,"long_context":null,"other_tiers":{"fast":{"input":0.7,"output":2.8,"cache_read":0.175}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1047576,"max_output":32768,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-4.1-mini","note":"Page labels this model \"Deprecated\"."},"ctx":1047576,"maxout":32768,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-4.1-mini","slug":"gpt-4-1-mini","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4-1-mini/","api":"https://api.tensorust.com/v1/llm/models/gpt-4-1-mini","chat_cost_rank":12,"workloads":{"chat":{"standard":0.00124,"with_cache":0.00094,"batch":null},"rag":{"standard":0.0032,"with_cache":0.0029,"batch":null},"sum":{"standard":0.00928,"with_cache":0.00898,"batch":null},"agent":{"standard":0.0192,"with_cache":0.0102,"batch":null},"batch":{"standard":0.00128,"with_cache":null,"batch":0.00064},"long":{"standard":0.0616,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-3.5-turbo","name":"GPT-3.5 Turbo","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.5,"output":1.5,"cache_write":null,"cache_read":null,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read, batch_input, batch_output","f":{"context_window":16385,"max_output":4096,"input_modalities":["text"],"tools":false,"source_url":"https://developers.openai.com/api/docs/models/gpt-3.5-turbo","note":"Page labels this model \"Shut down\"."},"ctx":16385,"maxout":4096,"mod":["text"],"tools":false,"life":"shut down","ok":false,"id":"gpt-3.5-turbo","slug":"gpt-3-5-turbo","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-3-5-turbo/","api":"https://api.tensorust.com/v1/llm/models/gpt-3-5-turbo","chat_cost_rank":13,"workloads":{"chat":{"standard":0.00135,"with_cache":null,"batch":null},"rag":{"standard":0.00375,"with_cache":null,"batch":null},"sum":{"standard":0.0112,"with_cache":null,"batch":null},"agent":{"standard":0.023,"with_cache":null,"batch":null},"batch":{"standard":0.00145,"with_cache":null,"batch":null},"long":{"standard":0.0765,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-3.5-turbo-0125","name":"GPT-3.5 Turbo (0125)","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.5,"output":1.5,"cache_write":null,"cache_read":null,"batch_input":0.25,"batch_output":0.75,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"no spec page","ok":false,"id":"gpt-3.5-turbo-0125","slug":"gpt-3-5-turbo-0125","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-3-5-turbo-0125/","api":"https://api.tensorust.com/v1/llm/models/gpt-3-5-turbo-0125","chat_cost_rank":14,"workloads":{"chat":{"standard":0.00135,"with_cache":null,"batch":null},"rag":{"standard":0.00375,"with_cache":null,"batch":null},"sum":{"standard":0.0112,"with_cache":null,"batch":null},"agent":{"standard":0.023,"with_cache":null,"batch":null},"batch":{"standard":0.00145,"with_cache":null,"batch":0.000725},"long":{"standard":0.0765,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.3,"output":2.5,"cache_write":null,"cache_read":0.03,"batch_input":0.15,"batch_output":1.25,"long_context":null,"other_tiers":{"flex":{"input":0.15,"output":1.25,"cache_read":0.02},"priority":{"input":0.54,"output":4.5,"cache_read":0.05}},"scheduled":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; explicit cache storage 1 USD per 1M tokens per hour","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite"},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"current","ok":true,"ccrank":6,"big":false,"id":"gemini-3.5-flash-lite","slug":"gemini-3-5-flash-lite","provider_name":"Google","url":"https://tensorust.com/llm/gemini-3-5-flash-lite/","api":"https://api.tensorust.com/v1/llm/models/gemini-3-5-flash-lite","chat_cost_rank":15,"workloads":{"chat":{"standard":0.00145,"with_cache":0.00118,"batch":null},"rag":{"standard":0.00305,"with_cache":0.00278,"batch":null},"sum":{"standard":0.008,"with_cache":0.00773,"batch":null},"agent":{"standard":0.017,"with_cache":0.0089,"batch":null},"batch":{"standard":0.00135,"with_cache":null,"batch":0.000675},"long":{"standard":0.0475,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.3,"output":2.5,"cache_write":null,"cache_read":0.03,"batch_input":0.15,"batch_output":1.25,"long_context":null,"other_tiers":{"flex":{"input":0.15,"output":1.25,"cache_read":0.03},"priority":{"input":0.54,"output":4.5,"cache_read":0.054}},"scheduled":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; explicit cache storage 1 USD per 1M tokens per hour; audio input is priced higher; see page","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash","note":"Per ai.google.dev/gemini-api/docs/models: access limited to users who have used 2.5 models before; not deprecated."},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio"],"tools":true,"life":"limited access","ok":false,"id":"gemini-2.5-flash","slug":"gemini-2-5-flash","provider_name":"Google","url":"https://tensorust.com/llm/gemini-2-5-flash/","api":"https://api.tensorust.com/v1/llm/models/gemini-2-5-flash","chat_cost_rank":16,"workloads":{"chat":{"standard":0.00145,"with_cache":0.00118,"batch":null},"rag":{"standard":0.00305,"with_cache":0.00278,"batch":null},"sum":{"standard":0.008,"with_cache":0.00773,"batch":null},"agent":{"standard":0.017,"with_cache":0.0089,"batch":null},"batch":{"standard":0.00135,"with_cache":null,"batch":0.000675},"long":{"standard":0.0475,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.5,"output":3,"cache_write":null,"cache_read":0.05,"batch_input":0.25,"batch_output":1.5,"long_context":null,"other_tiers":{"flex":{"input":0.25,"output":1.5,"cache_read":0.05},"priority":{"input":0.9,"output":5.4,"cache_read":0.09}},"scheduled":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; explicit cache storage 1 USD per 1M tokens per hour; audio input is priced higher; see page","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview","note":"Preview model."},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"preview","ok":true,"ccrank":7,"big":false,"id":"gemini-3-flash-preview","slug":"gemini-3-flash-preview","provider_name":"Google","url":"https://tensorust.com/llm/gemini-3-flash-preview/","api":"https://api.tensorust.com/v1/llm/models/gemini-3-flash-preview","chat_cost_rank":17,"workloads":{"chat":{"standard":0.00195,"with_cache":0.0015,"batch":null},"rag":{"standard":0.0045,"with_cache":0.00405,"batch":null},"sum":{"standard":0.0124,"with_cache":0.01195,"batch":null},"agent":{"standard":0.026,"with_cache":0.0125,"batch":null},"batch":{"standard":0.0019,"with_cache":null,"batch":0.00095},"long":{"standard":0.078,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.75,"output":3.75,"cache_write":null,"cache_read":0.075,"batch_input":0.375,"batch_output":1.875,"long_context":null,"other_tiers":{"flex":{"input":0.375,"output":1.875,"cache_read":0.0375},"priority":{"input":1.35,"output":6.75,"cache_read":0.135}},"scheduled":[{"effective":"2027-01-01","input":1.5,"output":7.5,"cache_read":0.15,"batch_input":0.75,"batch_output":3.75}],"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; current prices are promotional until the day before 2027-01-01; scheduled holds the published later prices; explicit cache storage 0.5 USD per 1M tokens per hour","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash"},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"current","ok":true,"ccrank":8,"big":true,"id":"gemini-3.8-flash","slug":"gemini-3-8-flash","provider_name":"Google","url":"https://tensorust.com/llm/gemini-3-8-flash/","api":"https://api.tensorust.com/v1/llm/models/gemini-3-8-flash","chat_cost_rank":18,"workloads":{"chat":{"standard":0.002625,"with_cache":0.00195,"batch":null},"rag":{"standard":0.006375,"with_cache":0.0057,"batch":null},"sum":{"standard":0.018,"with_cache":0.017325,"batch":null},"agent":{"standard":0.0375,"with_cache":0.01725,"batch":null},"batch":{"standard":0.002625,"with_cache":null,"batch":0.001313},"long":{"standard":0.11625,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.75,"output":3.75,"cache_write":null,"cache_read":0.075,"batch_input":0.375,"batch_output":1.875,"long_context":null,"other_tiers":{"flex":{"input":0.375,"output":1.875,"cache_read":0.0375},"priority":{"input":1.35,"output":6.75,"cache_read":0.135}},"scheduled":[{"effective":"2027-01-01","input":1.5,"output":7.5,"cache_read":0.15,"batch_input":0.75,"batch_output":3.75}],"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; current prices are promotional until the day before 2027-01-01; scheduled holds the published later prices; explicit cache storage 0.5 USD per 1M tokens per hour","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-3.6-flash"},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"current","ok":true,"ccrank":8,"big":true,"id":"gemini-3.6-flash","slug":"gemini-3-6-flash","provider_name":"Google","url":"https://tensorust.com/llm/gemini-3-6-flash/","api":"https://api.tensorust.com/v1/llm/models/gemini-3-6-flash","chat_cost_rank":19,"workloads":{"chat":{"standard":0.002625,"with_cache":0.00195,"batch":null},"rag":{"standard":0.006375,"with_cache":0.0057,"batch":null},"sum":{"standard":0.018,"with_cache":0.017325,"batch":null},"agent":{"standard":0.0375,"with_cache":0.01725,"batch":null},"batch":{"standard":0.002625,"with_cache":null,"batch":0.001313},"long":{"standard":0.11625,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-3-5-haiku-20241022","name":"Claude Haiku 3.5","aliases":[],"status":"retired","unit":"USD per 1M tokens","input":0.8,"output":4,"cache_write":{"5m":1,"1h":1.6},"cache_read":0.08,"batch_input":0.4,"batch_output":2,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"page marks this model retired on the Claude API; still sold on some cloud platforms; US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"retired","ok":false,"id":"claude-3-5-haiku-20241022","slug":"claude-3-5-haiku-20241022","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-3-5-haiku-20241022/","api":"https://api.tensorust.com/v1/llm/models/claude-3-5-haiku-20241022","chat_cost_rank":20,"workloads":{"chat":{"standard":0.0028,"with_cache":0.00208,"batch":null},"rag":{"standard":0.0068,"with_cache":0.00608,"batch":null},"sum":{"standard":0.0192,"with_cache":0.01848,"batch":null},"agent":{"standard":0.04,"with_cache":0.0184,"batch":null},"batch":{"standard":0.0028,"with_cache":null,"batch":0.0014},"long":{"standard":0.124,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.4-mini","name":"GPT-5.4 mini","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":0.75,"output":4.5,"cache_write":null,"cache_read":0.075,"batch_input":0.375,"batch_output":2.25,"long_context":null,"other_tiers":{"flex":{"input":0.375,"output":2.25,"cache_read":0.0375},"fast":{"input":1.5,"output":9,"cache_read":0.15}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.0375; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.4-mini"},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":10,"big":false,"id":"gpt-5.4-mini","slug":"gpt-5-4-mini","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-4-mini/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-4-mini","chat_cost_rank":21,"workloads":{"chat":{"standard":0.002925,"with_cache":0.00225,"batch":null},"rag":{"standard":0.00675,"with_cache":0.006075,"batch":null},"sum":{"standard":0.0186,"with_cache":0.017925,"batch":null},"agent":{"standard":0.039,"with_cache":0.01875,"batch":null},"batch":{"standard":0.00285,"with_cache":null,"batch":0.001425},"long":{"standard":0.117,"with_cache":null,"batch":null}}},{"provider":"openai","model":"o4-mini","name":"o4-mini","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.1,"output":4.4,"cache_write":null,"cache_read":0.275,"batch_input":0.55,"batch_output":2.2,"long_context":null,"other_tiers":{"flex":{"input":0.55,"output":2.2,"cache_read":0.138},"fast":{"input":2,"output":8,"cache_read":0.5}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":200000,"max_output":100000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/o4-mini","note":"Page labels this model \"Shut down\"."},"ctx":200000,"maxout":100000,"mod":["text","image"],"tools":true,"life":"shut down","ok":false,"id":"o4-mini","slug":"o4-mini","provider_name":"OpenAI","url":"https://tensorust.com/llm/o4-mini/","api":"https://api.tensorust.com/v1/llm/models/o4-mini","chat_cost_rank":22,"workloads":{"chat":{"standard":0.00341,"with_cache":0.002585,"batch":null},"rag":{"standard":0.0088,"with_cache":0.007975,"batch":null},"sum":{"standard":0.02552,"with_cache":0.024695,"batch":null},"agent":{"standard":0.0528,"with_cache":0.02805,"batch":null},"batch":{"standard":0.00352,"with_cache":null,"batch":0.00176},"long":{"standard":0.1694,"with_cache":null,"batch":null}}},{"provider":"openai","model":"o3-mini","name":"o3-mini","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.1,"output":4.4,"cache_write":null,"cache_read":0.55,"batch_input":0.55,"batch_output":2.2,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":200000,"max_output":100000,"input_modalities":["text"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/o3-mini","note":"Page labels this model \"Shut down\"."},"ctx":200000,"maxout":100000,"mod":["text"],"tools":true,"life":"shut down","ok":false,"id":"o3-mini","slug":"o3-mini","provider_name":"OpenAI","url":"https://tensorust.com/llm/o3-mini/","api":"https://api.tensorust.com/v1/llm/models/o3-mini","chat_cost_rank":23,"workloads":{"chat":{"standard":0.00341,"with_cache":0.00286,"batch":null},"rag":{"standard":0.0088,"with_cache":0.00825,"batch":null},"sum":{"standard":0.02552,"with_cache":0.02497,"batch":null},"agent":{"standard":0.0528,"with_cache":0.0363,"batch":null},"batch":{"standard":0.00352,"with_cache":null,"batch":0.00176},"long":{"standard":0.1694,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-haiku-4-5","name":"Claude Haiku 4.5","aliases":["claude-haiku-4-5-20251001"],"status":"listed","unit":"USD per 1M tokens","input":1,"output":5,"cache_write":{"5m":1.25,"1h":2},"cache_read":0.1,"batch_input":0.5,"batch_output":2.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":200000,"max_output":64000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/haiku-4-5/overview","note":"Legacy (still available). Alias for claude-haiku-4-5-20251001."},"ctx":200000,"maxout":64000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-haiku-4-5","slug":"claude-haiku-4-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-haiku-4-5/","api":"https://api.tensorust.com/v1/llm/models/claude-haiku-4-5","chat_cost_rank":24,"workloads":{"chat":{"standard":0.0035,"with_cache":0.0026,"batch":null},"rag":{"standard":0.0085,"with_cache":0.0076,"batch":null},"sum":{"standard":0.024,"with_cache":0.0231,"batch":null},"agent":{"standard":0.05,"with_cache":0.023,"batch":null},"batch":{"standard":0.0035,"with_cache":null,"batch":0.00175},"long":{"standard":0.155,"with_cache":null,"batch":null}}},{"provider":"deepseek","model":"deepseek-v4-pro","name":"DeepSeek V4 Pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.32,"output":3.96,"cache_write":null,"cache_read":0.044,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":{"offpeak":{"input":0.66,"output":1.98,"cache_read":0.022}},"scheduled":null,"source_url":"https://api-docs.deepseek.com/quick_start/pricing","checked":"2026-10-23","note":"input/output/cache_read are peak-hour prices; other_tiers.offpeak is the off-peak price (peak hours: 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays); null means the page lists no price: batch_input, batch_output","f":{"context_window":1000000,"max_output":384000,"input_modalities":["text"],"tools":true,"source_url":"https://api-docs.deepseek.com/quick_start/pricing/","note":"Page states context length 1M and max output maximum 384K; model version DeepSeek-V4-Pro-0813; Vision not supported."},"ctx":1000000,"maxout":384000,"mod":["text"],"tools":true,"life":"current","ok":true,"ccrank":11,"big":true,"id":"deepseek-v4-pro","slug":"deepseek-v4-pro","provider_name":"DeepSeek","url":"https://tensorust.com/llm/deepseek-v4-pro/","api":"https://api.tensorust.com/v1/llm/models/deepseek-v4-pro","chat_cost_rank":25,"workloads":{"chat":{"standard":0.003564,"with_cache":0.002288,"batch":null},"rag":{"standard":0.0099,"with_cache":0.008624,"batch":null},"sum":{"standard":0.029568,"with_cache":0.028292,"batch":null},"agent":{"standard":0.06072,"with_cache":0.02244,"batch":null},"batch":{"standard":0.003828,"with_cache":null,"batch":null},"long":{"standard":0.20196,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.1","name":"GPT-5.1","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.25,"output":10,"cache_write":null,"cache_read":0.125,"batch_input":0.625,"batch_output":5,"long_context":null,"other_tiers":{"flex":{"input":0.625,"output":5,"cache_read":0.0625},"fast":{"input":2.5,"output":20,"cache_read":0.25}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.0625; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.1","note":"Page labels this model \"Deprecated\"."},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-5.1","slug":"gpt-5-1","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-1/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-1","chat_cost_rank":26,"workloads":{"chat":{"standard":0.005875,"with_cache":0.00475,"batch":null},"rag":{"standard":0.0125,"with_cache":0.011375,"batch":null},"sum":{"standard":0.033,"with_cache":0.031875,"batch":null},"agent":{"standard":0.07,"with_cache":0.03625,"batch":null},"batch":{"standard":0.0055,"with_cache":null,"batch":0.00275},"long":{"standard":0.1975,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5","name":"GPT-5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.25,"output":10,"cache_write":null,"cache_read":0.125,"batch_input":0.625,"batch_output":5,"long_context":null,"other_tiers":{"flex":{"input":0.625,"output":5,"cache_read":0.0625},"fast":{"input":2.5,"output":20,"cache_read":0.25}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.0625; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5","note":"Page labels this model \"Deprecated\"."},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-5","slug":"gpt-5","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5/","api":"https://api.tensorust.com/v1/llm/models/gpt-5","chat_cost_rank":27,"workloads":{"chat":{"standard":0.005875,"with_cache":0.00475,"batch":null},"rag":{"standard":0.0125,"with_cache":0.011375,"batch":null},"sum":{"standard":0.033,"with_cache":0.031875,"batch":null},"agent":{"standard":0.07,"with_cache":0.03625,"batch":null},"batch":{"standard":0.0055,"with_cache":null,"batch":0.00275},"long":{"standard":0.1975,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5-search-api","name":"GPT-5 Search API","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.25,"output":10,"cache_write":null,"cache_read":0.125,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: batch_input, batch_output","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"no spec page","ok":false,"id":"gpt-5-search-api","slug":"gpt-5-search-api","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-search-api/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-search-api","chat_cost_rank":28,"workloads":{"chat":{"standard":0.005875,"with_cache":0.00475,"batch":null},"rag":{"standard":0.0125,"with_cache":0.011375,"batch":null},"sum":{"standard":0.033,"with_cache":0.031875,"batch":null},"agent":{"standard":0.07,"with_cache":0.03625,"batch":null},"batch":{"standard":0.0055,"with_cache":null,"batch":null},"long":{"standard":0.1975,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.25,"output":10,"cache_write":null,"cache_read":0.125,"batch_input":0.625,"batch_output":5,"long_context":{"threshold_tokens":200000,"applies_when":"prompt over 200k tokens","input":2.5,"output":15,"cache_write":null,"cache_read":0.25,"batch_input":1.25,"batch_output":7.5},"other_tiers":{"flex":{"input":0.625,"output":5,"cache_read":0.125},"priority":{"input":2.25,"output":18,"cache_read":0.225}},"scheduled":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; explicit cache storage 4.5 USD per 1M tokens per hour","f":{"context_window":1048576,"max_output":65536,"input_modalities":["audio","image","video","text","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro","note":"Per ai.google.dev/gemini-api/docs/models: access limited to users who have used 2.5 models before; not deprecated."},"ctx":1048576,"maxout":65536,"mod":["audio","image","video","text","pdf"],"tools":true,"life":"limited access","ok":false,"id":"gemini-2.5-pro","slug":"gemini-2-5-pro","provider_name":"Google","url":"https://tensorust.com/llm/gemini-2-5-pro/","api":"https://api.tensorust.com/v1/llm/models/gemini-2-5-pro","chat_cost_rank":29,"workloads":{"chat":{"standard":0.005875,"with_cache":0.00475,"batch":null},"rag":{"standard":0.0125,"with_cache":0.011375,"batch":null},"sum":{"standard":0.033,"with_cache":0.031875,"batch":null},"agent":{"standard":0.07,"with_cache":0.03625,"batch":null},"batch":{"standard":0.0055,"with_cache":null,"batch":0.00275},"long":{"standard":0.1975,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4.1","name":"GPT-4.1","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":8,"cache_write":null,"cache_read":0.5,"batch_input":1,"batch_output":4,"long_context":null,"other_tiers":{"fast":{"input":3.5,"output":14,"cache_read":0.875}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1047576,"max_output":32768,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-4.1","note":"Page labels this model \"Deprecated\"."},"ctx":1047576,"maxout":32768,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-4.1","slug":"gpt-4-1","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4-1/","api":"https://api.tensorust.com/v1/llm/models/gpt-4-1","chat_cost_rank":30,"workloads":{"chat":{"standard":0.0062,"with_cache":0.0047,"batch":null},"rag":{"standard":0.016,"with_cache":0.0145,"batch":null},"sum":{"standard":0.0464,"with_cache":0.0449,"batch":null},"agent":{"standard":0.096,"with_cache":0.051,"batch":null},"batch":{"standard":0.0064,"with_cache":null,"batch":0.0032},"long":{"standard":0.308,"with_cache":null,"batch":null}}},{"provider":"openai","model":"o3","name":"o3","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":8,"cache_write":null,"cache_read":0.5,"batch_input":1,"batch_output":4,"long_context":null,"other_tiers":{"flex":{"input":1,"output":4,"cache_read":0.25},"fast":{"input":3.5,"output":14,"cache_read":0.875}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":200000,"max_output":100000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/o3","note":"Page labels this model \"Deprecated\"."},"ctx":200000,"maxout":100000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"o3","slug":"o3","provider_name":"OpenAI","url":"https://tensorust.com/llm/o3/","api":"https://api.tensorust.com/v1/llm/models/o3","chat_cost_rank":31,"workloads":{"chat":{"standard":0.0062,"with_cache":0.0047,"batch":null},"rag":{"standard":0.016,"with_cache":0.0145,"batch":null},"sum":{"standard":0.0464,"with_cache":0.0449,"batch":null},"agent":{"standard":0.096,"with_cache":0.051,"batch":null},"batch":{"standard":0.0064,"with_cache":null,"batch":0.0032},"long":{"standard":0.308,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":10,"cache_write":{"5m":2.5,"1h":4},"cache_read":0.1,"batch_input":1,"batch_output":5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://platform.claude.com/docs/en/about-claude/models/overview","note":"Current model. Page lists 1M tokens context, 128K tokens max output"},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":12,"big":false,"id":"claude-sonnet-5-5","slug":"claude-sonnet-5-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-sonnet-5-5/","api":"https://api.tensorust.com/v1/llm/models/claude-sonnet-5-5","chat_cost_rank":32,"workloads":{"chat":{"standard":0.007,"with_cache":0.0051,"batch":null},"rag":{"standard":0.017,"with_cache":0.0151,"batch":null},"sum":{"standard":0.048,"with_cache":0.0461,"batch":null},"agent":{"standard":0.1,"with_cache":0.043,"batch":null},"batch":{"standard":0.007,"with_cache":null,"batch":0.0035},"long":{"standard":0.31,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-sonnet-5","name":"Claude Sonnet 5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":10,"cache_write":{"5m":2.5,"1h":4},"cache_read":0.2,"batch_input":1,"batch_output":5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/sonnet-5/overview","note":"Legacy (still available). Batch API (beta header) max output 300K tokens."},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-sonnet-5","slug":"claude-sonnet-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-sonnet-5/","api":"https://api.tensorust.com/v1/llm/models/claude-sonnet-5","chat_cost_rank":33,"workloads":{"chat":{"standard":0.007,"with_cache":0.0052,"batch":null},"rag":{"standard":0.017,"with_cache":0.0152,"batch":null},"sum":{"standard":0.048,"with_cache":0.0462,"batch":null},"agent":{"standard":0.1,"with_cache":0.046,"batch":null},"batch":{"standard":0.007,"with_cache":null,"batch":0.0035},"long":{"standard":0.31,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-6.1-sol","name":"GPT-6.1 Sol","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":10,"cache_write":{"30m":2.5,"12h":5},"cache_read":0.1,"batch_input":1,"batch_output":5,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":4,"output":15,"cache_write":{"30m":5,"12h":10},"cache_read":0.2,"batch_input":2,"batch_output":7.5},"other_tiers":{"flex":{"input":1,"output":5,"cache_read":0.05},"fast":{"input":4,"output":20,"cache_read":0.2},"ultrafast":{"input":12,"output":60,"cache_read":0.6}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.05; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-6.1-sol"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":12,"big":false,"id":"gpt-6.1-sol","slug":"gpt-6-1-sol","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-6-1-sol/","api":"https://api.tensorust.com/v1/llm/models/gpt-6-1-sol","chat_cost_rank":34,"workloads":{"chat":{"standard":0.007,"with_cache":0.0051,"batch":null},"rag":{"standard":0.017,"with_cache":0.0151,"batch":null},"sum":{"standard":0.048,"with_cache":0.0461,"batch":null},"agent":{"standard":0.1,"with_cache":0.043,"batch":null},"batch":{"standard":0.007,"with_cache":null,"batch":0.0035},"long":{"standard":0.31,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-6-sol","name":"GPT-6 Sol","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":10,"cache_write":{"30m":2.5,"12h":5},"cache_read":0.2,"batch_input":1,"batch_output":5,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":4,"output":15,"cache_write":{"30m":5,"12h":10},"cache_read":0.4,"batch_input":2,"batch_output":7.5},"other_tiers":{"flex":{"input":1,"output":5,"cache_read":0.1},"fast":{"input":4,"output":20,"cache_read":0.4}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.1; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-6-sol"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":12,"big":false,"id":"gpt-6-sol","slug":"gpt-6-sol","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-6-sol/","api":"https://api.tensorust.com/v1/llm/models/gpt-6-sol","chat_cost_rank":35,"workloads":{"chat":{"standard":0.007,"with_cache":0.0052,"batch":null},"rag":{"standard":0.017,"with_cache":0.0152,"batch":null},"sum":{"standard":0.048,"with_cache":0.0462,"batch":null},"agent":{"standard":0.1,"with_cache":0.046,"batch":null},"batch":{"standard":0.007,"with_cache":null,"batch":0.0035},"long":{"standard":0.31,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-4-argon","name":"Gemini 4 Argon","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":10,"cache_write":null,"cache_read":0.1,"batch_input":1,"batch_output":5,"long_context":null,"other_tiers":{"flex":{"input":1,"output":5,"cache_read":0.05},"priority":{"input":3.6,"output":18,"cache_read":0.18}},"scheduled":[{"effective":"2026-12-01","input":4,"output":20,"cache_read":0.2,"batch_input":2,"batch_output":10}],"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; current prices are promotional until the day before 2026-12-01; scheduled holds the published later prices; implicit caching only","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-4-argon","note":"Context window is a unified input and output limit; max output 65,536 default synchronous, up to 1,048,576 with long decode."},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"current","ok":true,"ccrank":12,"big":true,"id":"gemini-4-argon","slug":"gemini-4-argon","provider_name":"Google","url":"https://tensorust.com/llm/gemini-4-argon/","api":"https://api.tensorust.com/v1/llm/models/gemini-4-argon","chat_cost_rank":36,"workloads":{"chat":{"standard":0.007,"with_cache":0.0051,"batch":null},"rag":{"standard":0.017,"with_cache":0.0151,"batch":null},"sum":{"standard":0.048,"with_cache":0.0461,"batch":null},"agent":{"standard":0.1,"with_cache":0.043,"batch":null},"batch":{"standard":0.007,"with_cache":null,"batch":0.0035},"long":{"standard":0.31,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4o","name":"GPT-4o","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2.5,"output":10,"cache_write":null,"cache_read":1.25,"batch_input":1.25,"batch_output":5,"long_context":null,"other_tiers":{"fast":{"input":4.25,"output":17,"cache_read":2.125}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":128000,"max_output":16384,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-4o","note":"Page labels this model \"Deprecated\"."},"ctx":128000,"maxout":16384,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-4o","slug":"gpt-4o","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4o/","api":"https://api.tensorust.com/v1/llm/models/gpt-4o","chat_cost_rank":37,"workloads":{"chat":{"standard":0.00775,"with_cache":0.0065,"batch":null},"rag":{"standard":0.02,"with_cache":0.01875,"batch":null},"sum":{"standard":0.058,"with_cache":0.05675,"batch":null},"agent":{"standard":0.12,"with_cache":0.0825,"batch":null},"batch":{"standard":0.008,"with_cache":null,"batch":0.004},"long":{"standard":0.385,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.6-terra","name":"GPT-5.6 Terra","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":12,"cache_write":{"30m":2.5,"12h":5},"cache_read":0.2,"batch_input":1,"batch_output":6,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":4,"output":18,"cache_write":{"30m":5,"12h":10},"cache_read":0.4,"batch_input":2,"batch_output":9},"other_tiers":{"flex":{"input":1,"output":6,"cache_read":0.1},"fast":{"input":4,"output":24,"cache_read":0.4}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.1; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.6-terra"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":16,"big":false,"id":"gpt-5.6-terra","slug":"gpt-5-6-terra","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-6-terra/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-6-terra","chat_cost_rank":38,"workloads":{"chat":{"standard":0.0078,"with_cache":0.006,"batch":null},"rag":{"standard":0.018,"with_cache":0.0162,"batch":null},"sum":{"standard":0.0496,"with_cache":0.0478,"batch":null},"agent":{"standard":0.104,"with_cache":0.05,"batch":null},"batch":{"standard":0.0076,"with_cache":null,"batch":0.0038},"long":{"standard":0.312,"with_cache":null,"batch":null}}},{"provider":"google","model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2,"output":12,"cache_write":null,"cache_read":0.2,"batch_input":1,"batch_output":6,"long_context":{"threshold_tokens":200000,"applies_when":"prompt over 200k tokens","input":4,"output":18,"cache_write":null,"cache_read":0.4,"batch_input":2,"batch_output":9},"other_tiers":{"flex":{"input":1,"output":6,"cache_read":0.2},"priority":{"input":3.6,"output":21.6,"cache_read":0.36}},"scheduled":null,"source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked":"2026-10-23","note":"prices are the Paid Tier text-token prices; explicit cache storage 4.5 USD per 1M tokens per hour","f":{"context_window":1048576,"max_output":65536,"input_modalities":["text","image","video","audio","pdf"],"tools":true,"source_url":"https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview","note":"Preview model."},"ctx":1048576,"maxout":65536,"mod":["text","image","video","audio","pdf"],"tools":true,"life":"preview","ok":true,"ccrank":16,"big":true,"id":"gemini-3.1-pro-preview","slug":"gemini-3-1-pro-preview","provider_name":"Google","url":"https://tensorust.com/llm/gemini-3-1-pro-preview/","api":"https://api.tensorust.com/v1/llm/models/gemini-3-1-pro-preview","chat_cost_rank":39,"workloads":{"chat":{"standard":0.0078,"with_cache":0.006,"batch":null},"rag":{"standard":0.018,"with_cache":0.0162,"batch":null},"sum":{"standard":0.0496,"with_cache":0.0478,"batch":null},"agent":{"standard":0.104,"with_cache":0.05,"batch":null},"batch":{"standard":0.0076,"with_cache":null,"batch":0.0038},"long":{"standard":0.312,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.2","name":"GPT-5.2","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.75,"output":14,"cache_write":null,"cache_read":0.175,"batch_input":0.875,"batch_output":7,"long_context":null,"other_tiers":{"flex":{"input":0.875,"output":7,"cache_read":0.0875},"fast":{"input":3.5,"output":28,"cache_read":0.35}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.0875; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.2"},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":18,"big":false,"id":"gpt-5.2","slug":"gpt-5-2","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-2/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-2","chat_cost_rank":40,"workloads":{"chat":{"standard":0.008225,"with_cache":0.00665,"batch":null},"rag":{"standard":0.0175,"with_cache":0.015925,"batch":null},"sum":{"standard":0.0462,"with_cache":0.044625,"batch":null},"agent":{"standard":0.098,"with_cache":0.05075,"batch":null},"batch":{"standard":0.0077,"with_cache":null,"batch":0.00385},"long":{"standard":0.2765,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.3-codex","name":"GPT-5.3 Codex","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":1.75,"output":14,"cache_write":null,"cache_read":0.175,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":{"fast":{"input":3.5,"output":28,"cache_read":0.35}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: batch_input, batch_output","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.3-codex","note":"Page labels this model \"Deprecated\"."},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-5.3-codex","slug":"gpt-5-3-codex","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-3-codex/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-3-codex","chat_cost_rank":41,"workloads":{"chat":{"standard":0.008225,"with_cache":0.00665,"batch":null},"rag":{"standard":0.0175,"with_cache":0.015925,"batch":null},"sum":{"standard":0.0462,"with_cache":0.044625,"batch":null},"agent":{"standard":0.098,"with_cache":0.05075,"batch":null},"batch":{"standard":0.0077,"with_cache":null,"batch":null},"long":{"standard":0.2765,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.4","name":"GPT-5.4","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":2.5,"output":15,"cache_write":null,"cache_read":0.25,"batch_input":1.25,"batch_output":7.5,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":5,"output":22.5,"cache_write":null,"cache_read":0.5,"batch_input":2.5,"batch_output":11.25},"other_tiers":{"flex":{"input":1.25,"output":7.5,"cache_read":0.13},"fast":{"input":5,"output":30,"cache_read":0.5}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.13; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.4"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":19,"big":false,"id":"gpt-5.4","slug":"gpt-5-4","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-4/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-4","chat_cost_rank":42,"workloads":{"chat":{"standard":0.00975,"with_cache":0.0075,"batch":null},"rag":{"standard":0.0225,"with_cache":0.02025,"batch":null},"sum":{"standard":0.062,"with_cache":0.05975,"batch":null},"agent":{"standard":0.13,"with_cache":0.0625,"batch":null},"batch":{"standard":0.0095,"with_cache":null,"batch":0.00475},"long":{"standard":0.39,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":3,"output":15,"cache_write":{"5m":3.75,"1h":6},"cache_read":0.3,"batch_input":1.5,"batch_output":7.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/sonnet-4-6/overview","note":"Legacy (still available). Batch API (beta header) max output 300K tokens."},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-sonnet-4-6","slug":"claude-sonnet-4-6","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-sonnet-4-6/","api":"https://api.tensorust.com/v1/llm/models/claude-sonnet-4-6","chat_cost_rank":43,"workloads":{"chat":{"standard":0.0105,"with_cache":0.0078,"batch":null},"rag":{"standard":0.0255,"with_cache":0.0228,"batch":null},"sum":{"standard":0.072,"with_cache":0.0693,"batch":null},"agent":{"standard":0.15,"with_cache":0.069,"batch":null},"batch":{"standard":0.0105,"with_cache":null,"batch":0.00525},"long":{"standard":0.465,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":3,"output":15,"cache_write":{"5m":3.75,"1h":6},"cache_read":0.3,"batch_input":1.5,"batch_output":7.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":200000,"max_output":64000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/sonnet-4-5/overview","note":"Deprecated September 30, 2026; retires November 30, 2026."},"ctx":200000,"maxout":64000,"mod":["text","image"],"tools":null,"life":"deprecated","ok":false,"id":"claude-sonnet-4-5-20250929","slug":"claude-sonnet-4-5-20250929","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-sonnet-4-5-20250929/","api":"https://api.tensorust.com/v1/llm/models/claude-sonnet-4-5-20250929","chat_cost_rank":44,"workloads":{"chat":{"standard":0.0105,"with_cache":0.0078,"batch":null},"rag":{"standard":0.0255,"with_cache":0.0228,"batch":null},"sum":{"standard":0.072,"with_cache":0.0693,"batch":null},"agent":{"standard":0.15,"with_cache":0.069,"batch":null},"batch":{"standard":0.0105,"with_cache":null,"batch":0.00525},"long":{"standard":0.465,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-sonnet-4-20250514","name":"Claude Sonnet 4","aliases":[],"status":"retired","unit":"USD per 1M tokens","input":3,"output":15,"cache_write":{"5m":3.75,"1h":6},"cache_read":0.3,"batch_input":1.5,"batch_output":7.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"page marks this model retired on the Claude API; still sold on some cloud platforms; US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"retired","ok":false,"id":"claude-sonnet-4-20250514","slug":"claude-sonnet-4-20250514","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-sonnet-4-20250514/","api":"https://api.tensorust.com/v1/llm/models/claude-sonnet-4-20250514","chat_cost_rank":45,"workloads":{"chat":{"standard":0.0105,"with_cache":0.0078,"batch":null},"rag":{"standard":0.0255,"with_cache":0.0228,"batch":null},"sum":{"standard":0.072,"with_cache":0.0693,"batch":null},"agent":{"standard":0.15,"with_cache":0.069,"batch":null},"batch":{"standard":0.0105,"with_cache":null,"batch":0.00525},"long":{"standard":0.465,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":5,"output":15,"cache_write":null,"cache_read":null,"batch_input":2.5,"batch_output":7.5,"long_context":null,"other_tiers":{"fast":{"input":8.75,"output":26.25,"cache_read":null}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"no spec page","ok":false,"id":"gpt-4o-2024-05-13","slug":"gpt-4o-2024-05-13","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4o-2024-05-13/","api":"https://api.tensorust.com/v1/llm/models/gpt-4o-2024-05-13","chat_cost_rank":46,"workloads":{"chat":{"standard":0.0135,"with_cache":null,"batch":null},"rag":{"standard":0.0375,"with_cache":null,"batch":null},"sum":{"standard":0.112,"with_cache":null,"batch":null},"agent":{"standard":0.23,"with_cache":null,"batch":null},"batch":{"standard":0.0145,"with_cache":null,"batch":0.00725},"long":{"standard":0.765,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-5-5","name":"Claude Opus 5.5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":4,"output":20,"cache_write":{"5m":5,"1h":8},"cache_read":0.2,"batch_input":2,"batch_output":10,"long_context":null,"other_tiers":{"fast":{"input":8,"output":40}},"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"fast mode (other_tiers.fast) is a separate premium tier; cache multipliers apply on top; US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://platform.claude.com/docs/en/about-claude/models/overview","note":"Current model. Page lists 1M tokens context, 128K tokens max output"},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":20,"big":true,"id":"claude-opus-5-5","slug":"claude-opus-5-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-5-5/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-5-5","chat_cost_rank":47,"workloads":{"chat":{"standard":0.014,"with_cache":0.0102,"batch":null},"rag":{"standard":0.034,"with_cache":0.0302,"batch":null},"sum":{"standard":0.096,"with_cache":0.0922,"batch":null},"agent":{"standard":0.2,"with_cache":0.086,"batch":null},"batch":{"standard":0.014,"with_cache":null,"batch":0.007},"long":{"standard":0.62,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.6-sol","name":"GPT-5.6 Sol","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":4,"output":20,"cache_write":{"30m":5,"12h":10},"cache_read":0.4,"batch_input":2,"batch_output":10,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":8,"output":30,"cache_write":{"30m":10,"12h":20},"cache_read":0.8,"batch_input":4,"batch_output":15},"other_tiers":{"flex":{"input":2,"output":10,"cache_read":0.2},"fast":{"input":8,"output":40,"cache_read":0.8}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.2; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.6-sol"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":20,"big":true,"id":"gpt-5.6-sol","slug":"gpt-5-6-sol","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-6-sol/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-6-sol","chat_cost_rank":48,"workloads":{"chat":{"standard":0.014,"with_cache":0.0104,"batch":null},"rag":{"standard":0.034,"with_cache":0.0304,"batch":null},"sum":{"standard":0.096,"with_cache":0.0924,"batch":null},"agent":{"standard":0.2,"with_cache":0.092,"batch":null},"batch":{"standard":0.014,"with_cache":null,"batch":0.007},"long":{"standard":0.62,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-5","name":"Claude Opus 5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":5,"output":25,"cache_write":{"5m":6.25,"1h":10},"cache_read":0.5,"batch_input":2.5,"batch_output":12.5,"long_context":null,"other_tiers":{"fast":{"input":10,"output":50}},"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"fast mode (other_tiers.fast) is a separate premium tier; cache multipliers apply on top; US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/opus-5/overview","note":"Legacy (still available). Batch API (beta header) max output 300K tokens."},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-opus-5","slug":"claude-opus-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-5/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-5","chat_cost_rank":49,"workloads":{"chat":{"standard":0.0175,"with_cache":0.013,"batch":null},"rag":{"standard":0.0425,"with_cache":0.038,"batch":null},"sum":{"standard":0.12,"with_cache":0.1155,"batch":null},"agent":{"standard":0.25,"with_cache":0.115,"batch":null},"batch":{"standard":0.0175,"with_cache":null,"batch":0.00875},"long":{"standard":0.775,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-4-8","name":"Claude Opus 4.8","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":5,"output":25,"cache_write":{"5m":6.25,"1h":10},"cache_read":0.5,"batch_input":2.5,"batch_output":12.5,"long_context":null,"other_tiers":{"fast":{"input":10,"output":50}},"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"fast mode (other_tiers.fast) is a separate premium tier; cache multipliers apply on top; US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/opus-4-8/overview","note":"Legacy (still available). Batch API (beta header) max output 300K tokens."},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-opus-4-8","slug":"claude-opus-4-8","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-4-8/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-4-8","chat_cost_rank":50,"workloads":{"chat":{"standard":0.0175,"with_cache":0.013,"batch":null},"rag":{"standard":0.0425,"with_cache":0.038,"batch":null},"sum":{"standard":0.12,"with_cache":0.1155,"batch":null},"agent":{"standard":0.25,"with_cache":0.115,"batch":null},"batch":{"standard":0.0175,"with_cache":null,"batch":0.00875},"long":{"standard":0.775,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-4-7","name":"Claude Opus 4.7","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":5,"output":25,"cache_write":{"5m":6.25,"1h":10},"cache_read":0.5,"batch_input":2.5,"batch_output":12.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/opus-4-7/overview","note":"Legacy (still available). Batch API (beta header) max output 300K tokens."},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-opus-4-7","slug":"claude-opus-4-7","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-4-7/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-4-7","chat_cost_rank":51,"workloads":{"chat":{"standard":0.0175,"with_cache":0.013,"batch":null},"rag":{"standard":0.0425,"with_cache":0.038,"batch":null},"sum":{"standard":0.12,"with_cache":0.1155,"batch":null},"agent":{"standard":0.25,"with_cache":0.115,"batch":null},"batch":{"standard":0.0175,"with_cache":null,"batch":0.00875},"long":{"standard":0.775,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-4-6","name":"Claude Opus 4.6","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":5,"output":25,"cache_write":{"5m":6.25,"1h":10},"cache_read":0.5,"batch_input":2.5,"batch_output":12.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/opus-4-6/overview","note":"Legacy (still available). Batch API (beta header) max output 300K tokens."},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-opus-4-6","slug":"claude-opus-4-6","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-4-6/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-4-6","chat_cost_rank":52,"workloads":{"chat":{"standard":0.0175,"with_cache":0.013,"batch":null},"rag":{"standard":0.0425,"with_cache":0.038,"batch":null},"sum":{"standard":0.12,"with_cache":0.1155,"batch":null},"agent":{"standard":0.25,"with_cache":0.115,"batch":null},"batch":{"standard":0.0175,"with_cache":null,"batch":0.00875},"long":{"standard":0.775,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-4-5","name":"Claude Opus 4.5","aliases":["claude-opus-4-5-20251101"],"status":"listed","unit":"USD per 1M tokens","input":5,"output":25,"cache_write":{"5m":6.25,"1h":10},"cache_read":0.5,"batch_input":2.5,"batch_output":12.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":200000,"max_output":64000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/opus-4-5/overview","note":"Legacy (still available). Pinned ID claude-opus-4-5-20251101; claude-opus-4-5 is the alias."},"ctx":200000,"maxout":64000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-opus-4-5","slug":"claude-opus-4-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-4-5/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-4-5","chat_cost_rank":53,"workloads":{"chat":{"standard":0.0175,"with_cache":0.013,"batch":null},"rag":{"standard":0.0425,"with_cache":0.038,"batch":null},"sum":{"standard":0.12,"with_cache":0.1155,"batch":null},"agent":{"standard":0.25,"with_cache":0.115,"batch":null},"batch":{"standard":0.0175,"with_cache":null,"batch":0.00875},"long":{"standard":0.775,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.5","name":"GPT-5.5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":5,"output":30,"cache_write":null,"cache_read":0.5,"batch_input":2.5,"batch_output":15,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":10,"output":45,"cache_write":null,"cache_read":1,"batch_input":5,"batch_output":22.5},"other_tiers":{"flex":{"input":2.5,"output":15,"cache_read":0.25},"fast":{"input":12.5,"output":75,"cache_read":1.25}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.25; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.5"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":22,"big":true,"id":"gpt-5.5","slug":"gpt-5-5","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-5/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-5","chat_cost_rank":54,"workloads":{"chat":{"standard":0.0195,"with_cache":0.015,"batch":null},"rag":{"standard":0.045,"with_cache":0.0405,"batch":null},"sum":{"standard":0.124,"with_cache":0.1195,"batch":null},"agent":{"standard":0.26,"with_cache":0.125,"batch":null},"batch":{"standard":0.019,"with_cache":null,"batch":0.0095},"long":{"standard":0.78,"with_cache":null,"batch":null}}},{"provider":"openai","model":"chat-latest","name":"chat-latest","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":5,"output":30,"cache_write":null,"cache_read":0.5,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: batch_input, batch_output","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/chat-latest","note":"Points to the latest Instant model used in ChatGPT; snapshot is regularly updated."},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":22,"big":true,"id":"chat-latest","slug":"chat-latest","provider_name":"OpenAI","url":"https://tensorust.com/llm/chat-latest/","api":"https://api.tensorust.com/v1/llm/models/chat-latest","chat_cost_rank":55,"workloads":{"chat":{"standard":0.0195,"with_cache":0.015,"batch":null},"rag":{"standard":0.045,"with_cache":0.0405,"batch":null},"sum":{"standard":0.124,"with_cache":0.1195,"batch":null},"agent":{"standard":0.26,"with_cache":0.125,"batch":null},"batch":{"standard":0.019,"with_cache":null,"batch":null},"long":{"standard":0.78,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4-turbo-2024-04-09","name":"GPT-4 Turbo (2024-04-09)","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":10,"output":30,"cache_write":null,"cache_read":null,"batch_input":5,"batch_output":15,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"no spec page","ok":false,"id":"gpt-4-turbo-2024-04-09","slug":"gpt-4-turbo-2024-04-09","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4-turbo-2024-04-09/","api":"https://api.tensorust.com/v1/llm/models/gpt-4-turbo-2024-04-09","chat_cost_rank":56,"workloads":{"chat":{"standard":0.027,"with_cache":null,"batch":null},"rag":{"standard":0.075,"with_cache":null,"batch":null},"sum":{"standard":0.224,"with_cache":null,"batch":null},"agent":{"standard":0.46,"with_cache":null,"batch":null},"batch":{"standard":0.029,"with_cache":null,"batch":0.0145},"long":{"standard":1.53,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-fable-5-1","name":"Claude Fable 5.1","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":10,"output":50,"cache_write":{"5m":12.5,"1h":20},"cache_read":0.25,"batch_input":5,"batch_output":25,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://platform.claude.com/docs/en/about-claude/models/overview","note":"Current model. Page lists 1M tokens context, 128K tokens max output"},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":24,"big":true,"id":"claude-fable-5-1","slug":"claude-fable-5-1","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-fable-5-1/","api":"https://api.tensorust.com/v1/llm/models/claude-fable-5-1","chat_cost_rank":57,"workloads":{"chat":{"standard":0.035,"with_cache":0.02525,"batch":null},"rag":{"standard":0.085,"with_cache":0.07525,"batch":null},"sum":{"standard":0.24,"with_cache":0.23025,"batch":null},"agent":{"standard":0.5,"with_cache":0.2075,"batch":null},"batch":{"standard":0.035,"with_cache":null,"batch":0.0175},"long":{"standard":1.55,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-fable-5","name":"Claude Fable 5","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":10,"output":50,"cache_write":{"5m":12.5,"1h":20},"cache_read":1,"batch_input":5,"batch_output":25,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":{"context_window":1000000,"max_output":128000,"input_modalities":["text","image"],"tools":null,"source_url":"https://platform.claude.com/docs/en/models/fable-5/overview","note":"Legacy (still available)."},"ctx":1000000,"maxout":128000,"mod":["text","image"],"tools":null,"life":"legacy","ok":false,"id":"claude-fable-5","slug":"claude-fable-5","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-fable-5/","api":"https://api.tensorust.com/v1/llm/models/claude-fable-5","chat_cost_rank":58,"workloads":{"chat":{"standard":0.035,"with_cache":0.026,"batch":null},"rag":{"standard":0.085,"with_cache":0.076,"batch":null},"sum":{"standard":0.24,"with_cache":0.231,"batch":null},"agent":{"standard":0.5,"with_cache":0.23,"batch":null},"batch":{"standard":0.035,"with_cache":null,"batch":0.0175},"long":{"standard":1.55,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-6-astra","name":"GPT-6 Astra","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":10,"output":50,"cache_write":{"30m":12.5,"12h":25},"cache_read":1,"batch_input":5,"batch_output":25,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":20,"output":75,"cache_write":{"30m":25,"12h":50},"cache_read":2,"batch_input":10,"batch_output":37.5},"other_tiers":{"flex":{"input":5,"output":25,"cache_read":0.5},"fast":{"input":20,"output":100,"cache_read":2},"ultrafast":{"input":60,"output":300,"cache_read":6}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"batch cached input 0.5; regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-6-astra"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":24,"big":true,"id":"gpt-6-astra","slug":"gpt-6-astra","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-6-astra/","api":"https://api.tensorust.com/v1/llm/models/gpt-6-astra","chat_cost_rank":59,"workloads":{"chat":{"standard":0.035,"with_cache":0.026,"batch":null},"rag":{"standard":0.085,"with_cache":0.076,"batch":null},"sum":{"standard":0.24,"with_cache":0.231,"batch":null},"agent":{"standard":0.5,"with_cache":0.23,"batch":null},"batch":{"standard":0.035,"with_cache":null,"batch":0.0175},"long":{"standard":1.55,"with_cache":null,"batch":null}}},{"provider":"openai","model":"o1","name":"o1","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":15,"output":60,"cache_write":null,"cache_read":7.5,"batch_input":7.5,"batch_output":30,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05","f":{"context_window":200000,"max_output":100000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/o1","note":"Page labels this model \"Shut down\"."},"ctx":200000,"maxout":100000,"mod":["text","image"],"tools":true,"life":"shut down","ok":false,"id":"o1","slug":"o1","provider_name":"OpenAI","url":"https://tensorust.com/llm/o1/","api":"https://api.tensorust.com/v1/llm/models/o1","chat_cost_rank":60,"workloads":{"chat":{"standard":0.0465,"with_cache":0.039,"batch":null},"rag":{"standard":0.12,"with_cache":0.1125,"batch":null},"sum":{"standard":0.348,"with_cache":0.3405,"batch":null},"agent":{"standard":0.72,"with_cache":0.495,"batch":null},"batch":{"standard":0.048,"with_cache":null,"batch":0.024},"long":{"standard":2.31,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.6-cyber","name":"GPT-5.6 Cyber","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":12.5,"output":75,"cache_write":{"30m":15.625,"12h":31.25},"cache_read":1.25,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: batch_input, batch_output","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.6-cyber"},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":26,"big":true,"id":"gpt-5.6-cyber","slug":"gpt-5-6-cyber","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-6-cyber/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-6-cyber","chat_cost_rank":61,"workloads":{"chat":{"standard":0.04875,"with_cache":0.0375,"batch":null},"rag":{"standard":0.1125,"with_cache":0.10125,"batch":null},"sum":{"standard":0.31,"with_cache":0.29875,"batch":null},"agent":{"standard":0.65,"with_cache":0.3125,"batch":null},"batch":{"standard":0.0475,"with_cache":null,"batch":null},"long":{"standard":1.95,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.5-cyber","name":"GPT-5.5 Cyber","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":12.5,"output":75,"cache_write":null,"cache_read":1.25,"batch_input":null,"batch_output":null,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: batch_input, batch_output","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"no spec page","ok":false,"id":"gpt-5.5-cyber","slug":"gpt-5-5-cyber","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-5-cyber/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-5-cyber","chat_cost_rank":62,"workloads":{"chat":{"standard":0.04875,"with_cache":0.0375,"batch":null},"rag":{"standard":0.1125,"with_cache":0.10125,"batch":null},"sum":{"standard":0.31,"with_cache":0.29875,"batch":null},"agent":{"standard":0.65,"with_cache":0.3125,"batch":null},"batch":{"standard":0.0475,"with_cache":null,"batch":null},"long":{"standard":1.95,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-4-1-20250805","name":"Claude Opus 4.1","aliases":[],"status":"retired","unit":"USD per 1M tokens","input":15,"output":75,"cache_write":{"5m":18.75,"1h":30},"cache_read":1.5,"batch_input":7.5,"batch_output":37.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"page marks this model retired on the Claude API; still sold on some cloud platforms; US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"retired","ok":false,"id":"claude-opus-4-1-20250805","slug":"claude-opus-4-1-20250805","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-4-1-20250805/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-4-1-20250805","chat_cost_rank":63,"workloads":{"chat":{"standard":0.0525,"with_cache":0.039,"batch":null},"rag":{"standard":0.1275,"with_cache":0.114,"batch":null},"sum":{"standard":0.36,"with_cache":0.3465,"batch":null},"agent":{"standard":0.75,"with_cache":0.345,"batch":null},"batch":{"standard":0.0525,"with_cache":null,"batch":0.02625},"long":{"standard":2.325,"with_cache":null,"batch":null}}},{"provider":"anthropic","model":"claude-opus-4-20250514","name":"Claude Opus 4","aliases":[],"status":"retired","unit":"USD per 1M tokens","input":15,"output":75,"cache_write":{"5m":18.75,"1h":30},"cache_read":1.5,"batch_input":7.5,"batch_output":37.5,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-10-23","note":"page marks this model retired on the Claude API; still sold on some cloud platforms; US-only inference (inference_geo \"us\") is 1.1x on Claude 4.6 and later","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"retired","ok":false,"id":"claude-opus-4-20250514","slug":"claude-opus-4-20250514","provider_name":"Anthropic","url":"https://tensorust.com/llm/claude-opus-4-20250514/","api":"https://api.tensorust.com/v1/llm/models/claude-opus-4-20250514","chat_cost_rank":64,"workloads":{"chat":{"standard":0.0525,"with_cache":0.039,"batch":null},"rag":{"standard":0.1275,"with_cache":0.114,"batch":null},"sum":{"standard":0.36,"with_cache":0.3465,"batch":null},"agent":{"standard":0.75,"with_cache":0.345,"batch":null},"batch":{"standard":0.0525,"with_cache":null,"batch":0.02625},"long":{"standard":2.325,"with_cache":null,"batch":null}}},{"provider":"openai","model":"o3-pro","name":"o3-pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":20,"output":80,"cache_write":null,"cache_read":null,"batch_input":10,"batch_output":40,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":{"context_window":200000,"max_output":100000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/o3-pro","note":"Page labels this model \"Deprecated\"."},"ctx":200000,"maxout":100000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"o3-pro","slug":"o3-pro","provider_name":"OpenAI","url":"https://tensorust.com/llm/o3-pro/","api":"https://api.tensorust.com/v1/llm/models/o3-pro","chat_cost_rank":65,"workloads":{"chat":{"standard":0.062,"with_cache":null,"batch":null},"rag":{"standard":0.16,"with_cache":null,"batch":null},"sum":{"standard":0.464,"with_cache":null,"batch":null},"agent":{"standard":0.96,"with_cache":null,"batch":null},"batch":{"standard":0.064,"with_cache":null,"batch":0.032},"long":{"standard":3.08,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-4-0613","name":"GPT-4 (0613)","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":30,"output":60,"cache_write":null,"cache_read":null,"batch_input":15,"batch_output":30,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":null,"ctx":null,"maxout":null,"mod":null,"tools":null,"life":"no spec page","ok":false,"id":"gpt-4-0613","slug":"gpt-4-0613","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-4-0613/","api":"https://api.tensorust.com/v1/llm/models/gpt-4-0613","chat_cost_rank":66,"workloads":{"chat":{"standard":0.069,"with_cache":null,"batch":null},"rag":{"standard":0.21,"with_cache":null,"batch":null},"sum":{"standard":0.648,"with_cache":null,"batch":null},"agent":{"standard":1.32,"with_cache":null,"batch":null},"batch":{"standard":0.078,"with_cache":null,"batch":0.039},"long":{"standard":4.56,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5-pro","name":"GPT-5 Pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":15,"output":120,"cache_write":null,"cache_read":null,"batch_input":7.5,"batch_output":60,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":{"context_window":400000,"max_output":272000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5-pro","note":"Page labels this model \"Deprecated\"."},"ctx":400000,"maxout":272000,"mod":["text","image"],"tools":true,"life":"deprecated","ok":false,"id":"gpt-5-pro","slug":"gpt-5-pro","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-pro/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-pro","chat_cost_rank":67,"workloads":{"chat":{"standard":0.0705,"with_cache":null,"batch":null},"rag":{"standard":0.15,"with_cache":null,"batch":null},"sum":{"standard":0.396,"with_cache":null,"batch":null},"agent":{"standard":0.84,"with_cache":null,"batch":null},"batch":{"standard":0.066,"with_cache":null,"batch":0.033},"long":{"standard":2.37,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.2-pro","name":"GPT-5.2 Pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":21,"output":168,"cache_write":null,"cache_read":null,"batch_input":10.5,"batch_output":84,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":{"context_window":400000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.2-pro"},"ctx":400000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":27,"big":true,"id":"gpt-5.2-pro","slug":"gpt-5-2-pro","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-2-pro/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-2-pro","chat_cost_rank":68,"workloads":{"chat":{"standard":0.0987,"with_cache":null,"batch":null},"rag":{"standard":0.21,"with_cache":null,"batch":null},"sum":{"standard":0.5544,"with_cache":null,"batch":null},"agent":{"standard":1.176,"with_cache":null,"batch":null},"batch":{"standard":0.0924,"with_cache":null,"batch":0.0462},"long":{"standard":3.318,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.5-pro","name":"GPT-5.5 Pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":30,"output":180,"cache_write":null,"cache_read":null,"batch_input":15,"batch_output":90,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":60,"output":270,"cache_write":null,"cache_read":null,"batch_input":null,"batch_output":null},"other_tiers":{"flex":{"input":15,"output":90,"cache_read":null}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.5-pro"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":28,"big":true,"id":"gpt-5.5-pro","slug":"gpt-5-5-pro","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-5-pro/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-5-pro","chat_cost_rank":69,"workloads":{"chat":{"standard":0.117,"with_cache":null,"batch":null},"rag":{"standard":0.27,"with_cache":null,"batch":null},"sum":{"standard":0.744,"with_cache":null,"batch":null},"agent":{"standard":1.56,"with_cache":null,"batch":null},"batch":{"standard":0.114,"with_cache":null,"batch":0.057},"long":{"standard":4.68,"with_cache":null,"batch":null}}},{"provider":"openai","model":"gpt-5.4-pro","name":"GPT-5.4 Pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":30,"output":180,"cache_write":null,"cache_read":null,"batch_input":15,"batch_output":90,"long_context":{"threshold_tokens":272000,"applies_when":"input tokens over 272K (page: short context is up to 272K input tokens)","input":60,"output":270,"cache_write":null,"cache_read":null,"batch_input":30,"batch_output":135},"other_tiers":{"flex":{"input":15,"output":90,"cache_read":null}},"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":{"context_window":1050000,"max_output":128000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/gpt-5.4-pro"},"ctx":1050000,"maxout":128000,"mod":["text","image"],"tools":true,"life":"current","ok":true,"ccrank":28,"big":true,"id":"gpt-5.4-pro","slug":"gpt-5-4-pro","provider_name":"OpenAI","url":"https://tensorust.com/llm/gpt-5-4-pro/","api":"https://api.tensorust.com/v1/llm/models/gpt-5-4-pro","chat_cost_rank":70,"workloads":{"chat":{"standard":0.117,"with_cache":null,"batch":null},"rag":{"standard":0.27,"with_cache":null,"batch":null},"sum":{"standard":0.744,"with_cache":null,"batch":null},"agent":{"standard":1.56,"with_cache":null,"batch":null},"batch":{"standard":0.114,"with_cache":null,"batch":0.057},"long":{"standard":4.68,"with_cache":null,"batch":null}}},{"provider":"openai","model":"o1-pro","name":"o1-pro","aliases":[],"status":"listed","unit":"USD per 1M tokens","input":150,"output":600,"cache_write":null,"cache_read":null,"batch_input":75,"batch_output":300,"long_context":null,"other_tiers":null,"scheduled":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-10-23","note":"regional processing (data residency) adds 10% for models released on or after 2026-03-05; null means the page lists no price: cache_read","f":{"context_window":200000,"max_output":100000,"input_modalities":["text","image"],"tools":true,"source_url":"https://developers.openai.com/api/docs/models/o1-pro","note":"Page labels this model \"Shut down\"."},"ctx":200000,"maxout":100000,"mod":["text","image"],"tools":true,"life":"shut down","ok":false,"id":"o1-pro","slug":"o1-pro","provider_name":"OpenAI","url":"https://tensorust.com/llm/o1-pro/","api":"https://api.tensorust.com/v1/llm/models/o1-pro","chat_cost_rank":71,"workloads":{"chat":{"standard":0.465,"with_cache":null,"batch":null},"rag":{"standard":1.2,"with_cache":null,"batch":null},"sum":{"standard":3.48,"with_cache":null,"batch":null},"agent":{"standard":7.2,"with_cache":null,"batch":null},"batch":{"standard":0.48,"with_cache":null,"batch":0.24},"long":{"standard":23.1,"with_cache":null,"batch":null}}}]}