scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 133

Merge 8eb6f6d835 into 01c68c199b

Browse source
This commit is contained in:
devin-ai-integration[bot] 2026-09-08 19:43:41 +00:00 • committed by GitHub
commit 1e90ad93ce
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 894 additions and 126 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

446
litellm/model_prices_and_context_window_backup.json
View file

@ -13792,7 +13792,8 @@
"max_output_tokens": 3072,
"max_tokens": 3072,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@cf/meta/llama-2-7b-chat-int8": {
"input_cost_per_token": 1.923e-06,
@ -13801,7 +13802,8 @@
"max_output_tokens": 2048,
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": {
"input_cost_per_token": 1.923e-06,
@ -13810,7 +13812,8 @@
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@hf/thebloke/codellama-7b-instruct-awq": {
"input_cost_per_token": 1.923e-06,
@ -13819,7 +13822,8 @@
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@cf/openai/gpt-oss-120b": {
"input_cost_per_token": 3.5e-07,
@ -13829,6 +13833,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.5e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13839,7 +13844,8 @@
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/meta/llama-3.2-3b-instruct": {
"input_cost_per_token": 5.09e-08,
@ -13848,7 +13854,8 @@
"max_output_tokens": 80000,
"max_tokens": 80000,
"mode": "chat",
"output_cost_per_token": 3.35e-07
"output_cost_per_token": 3.35e-07,
"rpm": 300
},
"cloudflare/@cf/meta/llama-guard-3-8b": {
"input_cost_per_token": 4.84e-07,
@ -13857,7 +13864,8 @@
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3e-08
"output_cost_per_token": 3e-08,
"rpm": 300
},
"cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora": {
"input_cost_per_token": 0.0,
@ -13866,7 +13874,8 @@
"max_output_tokens": 15000,
"max_tokens": 15000,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/moonshotai/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
@ -13877,6 +13886,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"rpm": 20,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13888,6 +13898,7 @@
"max_tokens": 80000,
"mode": "chat",
"output_cost_per_token": 4.881e-06,
"rpm": 300,
"supports_reasoning": true
},
"cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8": {
@ -13897,7 +13908,8 @@
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.87e-07
"output_cost_per_token": 2.87e-07,
"rpm": 300
},
"cloudflare/@cf/meta/llama-3.2-1b-instruct": {
"input_cost_per_token": 2.7e-08,
@ -13906,7 +13918,8 @@
"max_output_tokens": 60000,
"max_tokens": 60000,
"mode": "chat",
"output_cost_per_token": 2.01e-07
"output_cost_per_token": 2.01e-07,
"rpm": 300
},
"cloudflare/@cf/moonshotai/kimi-k2.6": {
"cache_read_input_token_cost": 1.6e-07,
@ -13917,6 +13930,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"rpm": 20,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13928,6 +13942,7 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13938,7 +13953,8 @@
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
"input_cost_per_token": 2.93e-07,
@ -13948,6 +13964,7 @@
"max_tokens": 24000,
"mode": "chat",
"output_cost_per_token": 2.253e-06,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/ibm-granite/granite-4.0-h-micro": {
@ -13958,6 +13975,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.12e-07,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct": {
@ -13967,7 +13985,8 @@
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1e-06
"output_cost_per_token": 1e-06,
"rpm": 300
},
"cloudflare/@cf/zai-org/glm-5.2": {
"cache_read_input_token_cost": 2.6e-07,
@ -13978,6 +13997,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"rpm": 20,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13989,6 +14009,7 @@
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 1.5e-06,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13999,7 +14020,8 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.55e-07
"output_cost_per_token": 5.55e-07,
"rpm": 300
},
"cloudflare/@cf/qwen/qwen3-30b-a3b-fp8": {
"input_cost_per_token": 5.09e-08,
@ -14009,6 +14031,7 @@
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 3.35e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -14019,7 +14042,8 @@
"max_output_tokens": 3500,
"max_tokens": 3500,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/google/gemma-4-26b-a4b-it": {
"input_cost_per_token": 1e-07,
@ -14029,6 +14053,7 @@
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 3e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -14040,6 +14065,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.55e-07,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/meta/llama-3.2-11b-vision-instruct": {
@ -14050,6 +14076,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.76e-07,
"rpm": 300,
"supports_vision": true
},
"cloudflare/@cf/openai/gpt-oss-20b": {
@ -14060,6 +14087,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -14071,6 +14099,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 8.5e-07,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/qwen/qwq-32b": {
@ -14081,6 +14110,7 @@
"max_tokens": 24000,
"mode": "chat",
"output_cost_per_token": 1e-06,
"rpm": 300,
"supports_reasoning": true
},
"codestral/codestral-2405": {
@ -14336,6 +14366,7 @@
"supports_tool_choice": true
},
"computer-use-preview": {
"deprecation_date": "2026-07-23",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -23829,9 +23860,9 @@
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 2e-06,
@ -23854,12 +23885,12 @@
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_pdf_input": false,
"supports_prompt_caching": false,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_url_context": false,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
@ -27651,6 +27682,70 @@
"max_tokens": 8191,
"mode": "embedding"
},
"chatgpt/gpt-5.5": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.5",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.6-luna": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.6-luna",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.6-sol": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.6-sol",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.6-terra": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.6-terra",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.4": {
"litellm_provider": "chatgpt",
"max_input_tokens": 1050000,
@ -29081,7 +29176,13 @@
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"search_context_cost_per_query": {
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"supports_web_search": true
},
"gpt-4o-mini-2024-07-18": {
"cache_read_input_token_cost": 7.5e-08,
@ -29098,9 +29199,9 @@
"output_cost_per_token_priority": 1e-06,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.03,
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29109,7 +29210,8 @@
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"supports_web_search": true
},
"gpt-4o-mini-audio-preview": {
"deprecation_date": "2026-05-07",
@ -29199,9 +29301,9 @@
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.03,
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29226,9 +29328,9 @@
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.03,
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29339,9 +29441,9 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.05,
"search_context_size_low": 0.03,
"search_context_size_medium": 0.035
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29366,9 +29468,9 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.05,
"search_context_size_low": 0.03,
"search_context_size_medium": 0.035
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -41530,6 +41632,28 @@
"mode": "rerank",
"output_cost_per_token": 0.0
},
"rerank-v4.0-fast": {
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "cohere",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://cohere.com/pricing"
},
"rerank-v4.0-pro": {
"input_cost_per_query": 0.0025,
"input_cost_per_token": 0.0,
"litellm_provider": "cohere",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://cohere.com/pricing"
},
"nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": {
"input_cost_per_query": 0.0,
"input_cost_per_token": 0.0,
@ -45710,8 +45834,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -45735,8 +45859,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -47716,7 +47840,7 @@
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
@ -47732,7 +47856,7 @@
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
@ -47747,14 +47871,17 @@
},
"vertex_ai/xai/grok-4.20-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/developers/models",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -47763,14 +47890,17 @@
},
"vertex_ai/xai/grok-4.20-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/developers/models",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -47778,6 +47908,42 @@
"supports_vision": true,
"supports_web_search": true
},
"vertex_ai/xai/grok-4.3": {
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/xai/grok-4.6": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 524288,
"max_tokens": 524288,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_200k_tokens": 1.2e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": {
"input_cost_per_token": 2.2e-07,
"litellm_provider": "vertex_ai-qwen_models",
@ -48036,6 +48202,16 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-multilingual-2": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://docs.voyageai.com/docs/pricing"
},
"voyage/voyage-3-large": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "voyage",
@ -52109,7 +52285,8 @@
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8e-07,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/openai/gpt-oss-120b": {
"input_cost_per_token": 1.5e-07,
@ -52148,7 +52325,8 @@
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_function_calling": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-01"
},
"scaleway/hcompany/holo2-30b-a3b": {
"input_cost_per_token": 3e-07,
@ -52159,7 +52337,8 @@
"mode": "chat",
"output_cost_per_token": 7e-07,
"supports_reasoning": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-09"
},
"scaleway/mistralai/mistral-medium-3.5-128b": {
"input_cost_per_token": 1.5e-06,
@ -52182,7 +52361,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 2e-06,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/voxtral-small-24b-2507": {
"input_cost_per_audio_token": 1.5e-07,
@ -52193,7 +52373,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 3.5e-07,
"supports_audio_input": true
"supports_audio_input": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": {
"input_cost_per_token": 1.5e-07,
@ -52215,7 +52396,8 @@
"mode": "chat",
"output_cost_per_token": 2e-07,
"supports_vision": true,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/BAAI/bge-multilingual-gemma2": {
"input_cost_per_token": 1e-07,
@ -54665,7 +54847,7 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-20b": {
"input_cost_per_token": 7.5e-08,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
@ -54699,8 +54881,8 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-safeguard-20b": {
"input_cost_per_token": 7.5e-08,
"output_cost_per_token": 3e-07,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
@ -54820,6 +55002,39 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": {
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html"
},
"bedrock_mantle/openai.gpt-5.6-luna": {
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
@ -56680,8 +56895,8 @@
"rpm": 10
},
"vertex_ai/gemini-3.5-transcribe-preview": {
"input_cost_per_audio_token": 2.5e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_audio_token": 2e-06,
"input_cost_per_token": 2e-06,
"litellm_provider": "vertex_ai",
"mode": "audio_transcription",
"output_cost_per_token": 1.2e-05,
@ -56716,6 +56931,27 @@
],
"supports_audio_input": true
},
"vertex_ai/gemini-3.5-live-translate-preview": {
"input_cost_per_audio_token": 3.5e-06,
"input_cost_per_token": 3.5e-06,
"litellm_provider": "vertex_ai",
"mode": "realtime",
"output_cost_per_audio_token": 2.1e-05,
"output_cost_per_token": 2.1e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"audio"
],
"supported_output_modalities": [
"audio",
"text"
],
"supports_audio_input": true,
"supports_audio_output": true
},
"perplexity/pplx-embed-context-v1-0.6b": {
"input_cost_per_token": 8e-09,
"litellm_provider": "perplexity",
@ -59407,6 +59643,73 @@
"image"
]
},
"xai/grok-imagine-video": {
"input_cost_per_image": 0.002,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.05,
"output_cost_per_second_480p": 0.05,
"source": "https://docs.x.ai/docs/models/grok-imagine-video",
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"video"
]
},
"xai/grok-imagine-video-1.5": {
"input_cost_per_image": 0.01,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.08,
"output_cost_per_second_1080p": 0.25,
"output_cost_per_second_480p": 0.08,
"source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"video"
]
},
"xai/grok-imagine-video-1.5-2026-05-30": {
"input_cost_per_image": 0.01,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.08,
"output_cost_per_second_1080p": 0.25,
"output_cost_per_second_480p": 0.08,
"source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"video"
]
},
"xai/grok-imagine-video-1.5-preview": {
"input_cost_per_image": 0.01,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.08,
"output_cost_per_second_1080p": 0.25,
"output_cost_per_second_480p": 0.08,
"source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"video"
]
},
"low/1024-x-1024/grok-imagine-image-2.0": {
"input_cost_per_image": 0.04,
"litellm_provider": "xai",
@ -60674,6 +60977,7 @@
"litellm_provider": "cloudflare",
"mode": "audio_transcription",
"output_cost_per_second": 0.0,
"rpm": 720,
"source": "https://developers.cloudflare.com/workers-ai/models/whisper/",
"supported_endpoints": [
"/v1/audio/transcriptions"
@ -60684,6 +60988,7 @@
"litellm_provider": "cloudflare",
"mode": "audio_transcription",
"output_cost_per_second": 0.0,
"rpm": 720,
"source": "https://developers.cloudflare.com/workers-ai/models/whisper-large-v3-turbo/",
"supported_endpoints": [
"/v1/audio/transcriptions"
@ -60739,6 +61044,31 @@
"supports_web_search": false,
"output_cost_per_image": 0.08
},
"gemini/lyria-3.5": {
"input_cost_per_token": 0,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 0,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"audio"
],
"supports_audio_input": false,
"supports_audio_output": true,
"supports_function_calling": false,
"supports_prompt_caching": false,
"supports_response_schema": false,
"supports_system_messages": false,
"supports_vision": false,
"supports_web_search": false,
"output_cost_per_image": 0.08
},
"perplexity/anthropic/claude-fable-5": {
"litellm_provider": "perplexity",
"mode": "responses",

446
model_prices_and_context_window.json
View file

@ -13792,7 +13792,8 @@
"max_output_tokens": 3072,
"max_tokens": 3072,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@cf/meta/llama-2-7b-chat-int8": {
"input_cost_per_token": 1.923e-06,
@ -13801,7 +13802,8 @@
"max_output_tokens": 2048,
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": {
"input_cost_per_token": 1.923e-06,
@ -13810,7 +13812,8 @@
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@hf/thebloke/codellama-7b-instruct-awq": {
"input_cost_per_token": 1.923e-06,
@ -13819,7 +13822,8 @@
"max_output_tokens": 4096,
"max_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.923e-06
"output_cost_per_token": 1.923e-06,
"rpm": 300
},
"cloudflare/@cf/openai/gpt-oss-120b": {
"input_cost_per_token": 3.5e-07,
@ -13829,6 +13833,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.5e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13839,7 +13844,8 @@
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/meta/llama-3.2-3b-instruct": {
"input_cost_per_token": 5.09e-08,
@ -13848,7 +13854,8 @@
"max_output_tokens": 80000,
"max_tokens": 80000,
"mode": "chat",
"output_cost_per_token": 3.35e-07
"output_cost_per_token": 3.35e-07,
"rpm": 300
},
"cloudflare/@cf/meta/llama-guard-3-8b": {
"input_cost_per_token": 4.84e-07,
@ -13857,7 +13864,8 @@
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3e-08
"output_cost_per_token": 3e-08,
"rpm": 300
},
"cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora": {
"input_cost_per_token": 0.0,
@ -13866,7 +13874,8 @@
"max_output_tokens": 15000,
"max_tokens": 15000,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/moonshotai/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
@ -13877,6 +13886,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"rpm": 20,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13888,6 +13898,7 @@
"max_tokens": 80000,
"mode": "chat",
"output_cost_per_token": 4.881e-06,
"rpm": 300,
"supports_reasoning": true
},
"cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8": {
@ -13897,7 +13908,8 @@
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.87e-07
"output_cost_per_token": 2.87e-07,
"rpm": 300
},
"cloudflare/@cf/meta/llama-3.2-1b-instruct": {
"input_cost_per_token": 2.7e-08,
@ -13906,7 +13918,8 @@
"max_output_tokens": 60000,
"max_tokens": 60000,
"mode": "chat",
"output_cost_per_token": 2.01e-07
"output_cost_per_token": 2.01e-07,
"rpm": 300
},
"cloudflare/@cf/moonshotai/kimi-k2.6": {
"cache_read_input_token_cost": 1.6e-07,
@ -13917,6 +13930,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"rpm": 20,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13928,6 +13942,7 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 4e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13938,7 +13953,8 @@
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
"input_cost_per_token": 2.93e-07,
@ -13948,6 +13964,7 @@
"max_tokens": 24000,
"mode": "chat",
"output_cost_per_token": 2.253e-06,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/ibm-granite/granite-4.0-h-micro": {
@ -13958,6 +13975,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 1.12e-07,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct": {
@ -13967,7 +13985,8 @@
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1e-06
"output_cost_per_token": 1e-06,
"rpm": 300
},
"cloudflare/@cf/zai-org/glm-5.2": {
"cache_read_input_token_cost": 2.6e-07,
@ -13978,6 +13997,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"rpm": 20,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13989,6 +14009,7 @@
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 1.5e-06,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -13999,7 +14020,8 @@
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.55e-07
"output_cost_per_token": 5.55e-07,
"rpm": 300
},
"cloudflare/@cf/qwen/qwen3-30b-a3b-fp8": {
"input_cost_per_token": 5.09e-08,
@ -14009,6 +14031,7 @@
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 3.35e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -14019,7 +14042,8 @@
"max_output_tokens": 3500,
"max_tokens": 3500,
"mode": "chat",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"rpm": 300
},
"cloudflare/@cf/google/gemma-4-26b-a4b-it": {
"input_cost_per_token": 1e-07,
@ -14029,6 +14053,7 @@
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 3e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -14040,6 +14065,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.55e-07,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/meta/llama-3.2-11b-vision-instruct": {
@ -14050,6 +14076,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6.76e-07,
"rpm": 300,
"supports_vision": true
},
"cloudflare/@cf/openai/gpt-oss-20b": {
@ -14060,6 +14087,7 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-07,
"rpm": 300,
"supports_function_calling": true,
"supports_reasoning": true
},
@ -14071,6 +14099,7 @@
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 8.5e-07,
"rpm": 300,
"supports_function_calling": true
},
"cloudflare/@cf/qwen/qwq-32b": {
@ -14081,6 +14110,7 @@
"max_tokens": 24000,
"mode": "chat",
"output_cost_per_token": 1e-06,
"rpm": 300,
"supports_reasoning": true
},
"codestral/codestral-2405": {
@ -14336,6 +14366,7 @@
"supports_tool_choice": true
},
"computer-use-preview": {
"deprecation_date": "2026-07-23",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -23829,9 +23860,9 @@
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "realtime",
"output_cost_per_audio_token": 1.2e-05,
"output_cost_per_token": 2e-06,
@ -23854,12 +23885,12 @@
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_pdf_input": false,
"supports_prompt_caching": false,
"supports_response_schema": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_url_context": false,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
@ -27651,6 +27682,70 @@
"max_tokens": 8191,
"mode": "embedding"
},
"chatgpt/gpt-5.5": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.5",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.6-luna": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.6-luna",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.6-sol": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.6-sol",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.6-terra": {
"litellm_provider": "chatgpt",
"source": "https://platform.openai.com/docs/models/gpt-5.6-terra",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"chatgpt/gpt-5.4": {
"litellm_provider": "chatgpt",
"max_input_tokens": 1050000,
@ -29081,7 +29176,13 @@
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"search_context_cost_per_query": {
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"supports_web_search": true
},
"gpt-4o-mini-2024-07-18": {
"cache_read_input_token_cost": 7.5e-08,
@ -29098,9 +29199,9 @@
"output_cost_per_token_priority": 1e-06,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.03,
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29109,7 +29210,8 @@
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"supports_web_search": true
},
"gpt-4o-mini-audio-preview": {
"deprecation_date": "2026-05-07",
@ -29199,9 +29301,9 @@
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.03,
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29226,9 +29328,9 @@
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.03,
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29339,9 +29441,9 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.05,
"search_context_size_low": 0.03,
"search_context_size_medium": 0.035
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -29366,9 +29468,9 @@
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.05,
"search_context_size_low": 0.03,
"search_context_size_medium": 0.035
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -41530,6 +41632,28 @@
"mode": "rerank",
"output_cost_per_token": 0.0
},
"rerank-v4.0-fast": {
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "cohere",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://cohere.com/pricing"
},
"rerank-v4.0-pro": {
"input_cost_per_query": 0.0025,
"input_cost_per_token": 0.0,
"litellm_provider": "cohere",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://cohere.com/pricing"
},
"nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": {
"input_cost_per_query": 0.0,
"input_cost_per_token": 0.0,
@ -45710,8 +45834,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -45735,8 +45859,8 @@
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 5e-06,
"regional_endpoint_uplift_multiplier": 1.1,
@ -47716,7 +47840,7 @@
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
@ -47732,7 +47856,7 @@
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
@ -47747,14 +47871,17 @@
},
"vertex_ai/xai/grok-4.20-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/developers/models",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -47763,14 +47890,17 @@
},
"vertex_ai/xai/grok-4.20-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://docs.x.ai/developers/models",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -47778,6 +47908,42 @@
"supports_vision": true,
"supports_web_search": true
},
"vertex_ai/xai/grok-4.3": {
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_above_200k_tokens": 2.5e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_above_200k_tokens": 5e-06,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/xai/grok-4.6": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_200k_tokens": 4e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 524288,
"max_tokens": 524288,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_200k_tokens": 1.2e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": {
"input_cost_per_token": 2.2e-07,
"litellm_provider": "vertex_ai-qwen_models",
@ -48036,6 +48202,16 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-multilingual-2": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://docs.voyageai.com/docs/pricing"
},
"voyage/voyage-3-large": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "voyage",
@ -52109,7 +52285,8 @@
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8e-07,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/openai/gpt-oss-120b": {
"input_cost_per_token": 1.5e-07,
@ -52148,7 +52325,8 @@
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_function_calling": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-01"
},
"scaleway/hcompany/holo2-30b-a3b": {
"input_cost_per_token": 3e-07,
@ -52159,7 +52337,8 @@
"mode": "chat",
"output_cost_per_token": 7e-07,
"supports_reasoning": true,
"supports_vision": true
"supports_vision": true,
"deprecation_date": "2026-08-09"
},
"scaleway/mistralai/mistral-medium-3.5-128b": {
"input_cost_per_token": 1.5e-06,
@ -52182,7 +52361,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 2e-06,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/voxtral-small-24b-2507": {
"input_cost_per_audio_token": 1.5e-07,
@ -52193,7 +52373,8 @@
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 3.5e-07,
"supports_audio_input": true
"supports_audio_input": true,
"deprecation_date": "2026-08-01"
},
"scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": {
"input_cost_per_token": 1.5e-07,
@ -52215,7 +52396,8 @@
"mode": "chat",
"output_cost_per_token": 2e-07,
"supports_vision": true,
"supports_function_calling": true
"supports_function_calling": true,
"deprecation_date": "2026-10-01"
},
"scaleway/BAAI/bge-multilingual-gemma2": {
"input_cost_per_token": 1e-07,
@ -54665,7 +54847,7 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-20b": {
"input_cost_per_token": 7.5e-08,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
@ -54699,8 +54881,8 @@
"supports_tool_choice": true
},
"bedrock_mantle/openai.gpt-oss-safeguard-20b": {
"input_cost_per_token": 7.5e-08,
"output_cost_per_token": 3e-07,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2e-07,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
@ -54820,6 +55002,39 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": {
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html"
},
"bedrock_mantle/openai.gpt-5.6-luna": {
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
@ -56680,8 +56895,8 @@
"rpm": 10
},
"vertex_ai/gemini-3.5-transcribe-preview": {
"input_cost_per_audio_token": 2.5e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_audio_token": 2e-06,
"input_cost_per_token": 2e-06,
"litellm_provider": "vertex_ai",
"mode": "audio_transcription",
"output_cost_per_token": 1.2e-05,
@ -56716,6 +56931,27 @@
],
"supports_audio_input": true
},
"vertex_ai/gemini-3.5-live-translate-preview": {
"input_cost_per_audio_token": 3.5e-06,
"input_cost_per_token": 3.5e-06,
"litellm_provider": "vertex_ai",
"mode": "realtime",
"output_cost_per_audio_token": 2.1e-05,
"output_cost_per_token": 2.1e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"audio"
],
"supported_output_modalities": [
"audio",
"text"
],
"supports_audio_input": true,
"supports_audio_output": true
},
"perplexity/pplx-embed-context-v1-0.6b": {
"input_cost_per_token": 8e-09,
"litellm_provider": "perplexity",
@ -59407,6 +59643,73 @@
"image"
]
},
"xai/grok-imagine-video": {
"input_cost_per_image": 0.002,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.05,
"output_cost_per_second_480p": 0.05,
"source": "https://docs.x.ai/docs/models/grok-imagine-video",
"supported_modalities": [
"text",
"image",
"video"
],
"supported_output_modalities": [
"video"
]
},
"xai/grok-imagine-video-1.5": {
"input_cost_per_image": 0.01,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.08,
"output_cost_per_second_1080p": 0.25,
"output_cost_per_second_480p": 0.08,
"source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"video"
]
},
"xai/grok-imagine-video-1.5-2026-05-30": {
"input_cost_per_image": 0.01,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.08,
"output_cost_per_second_1080p": 0.25,
"output_cost_per_second_480p": 0.08,
"source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"video"
]
},
"xai/grok-imagine-video-1.5-preview": {
"input_cost_per_image": 0.01,
"litellm_provider": "xai",
"mode": "video_generation",
"output_cost_per_second": 0.08,
"output_cost_per_second_1080p": 0.25,
"output_cost_per_second_480p": 0.08,
"source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
"supported_modalities": [
"text",
"image",
"audio"
],
"supported_output_modalities": [
"video"
]
},
"low/1024-x-1024/grok-imagine-image-2.0": {
"input_cost_per_image": 0.04,
"litellm_provider": "xai",
@ -60674,6 +60977,7 @@
"litellm_provider": "cloudflare",
"mode": "audio_transcription",
"output_cost_per_second": 0.0,
"rpm": 720,
"source": "https://developers.cloudflare.com/workers-ai/models/whisper/",
"supported_endpoints": [
"/v1/audio/transcriptions"
@ -60684,6 +60988,7 @@
"litellm_provider": "cloudflare",
"mode": "audio_transcription",
"output_cost_per_second": 0.0,
"rpm": 720,
"source": "https://developers.cloudflare.com/workers-ai/models/whisper-large-v3-turbo/",
"supported_endpoints": [
"/v1/audio/transcriptions"
@ -60739,6 +61044,31 @@
"supports_web_search": false,
"output_cost_per_image": 0.08
},
"gemini/lyria-3.5": {
"input_cost_per_token": 0,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 0,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"audio"
],
"supports_audio_input": false,
"supports_audio_output": true,
"supports_function_calling": false,
"supports_prompt_caching": false,
"supports_response_schema": false,
"supports_system_messages": false,
"supports_vision": false,
"supports_web_search": false,
"output_cost_per_image": 0.08
},
"perplexity/anthropic/claude-fable-5": {
"litellm_provider": "perplexity",
"mode": "responses",

63
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py
View file

@ -1,5 +1,6 @@
import os
import json
from collections.abc import Mapping, Sequence
from pathlib import Path
import pytest
@ -11,8 +12,6 @@ from litellm.types.llms.openai import FileSearchTool, ResponsesAPIResponse, WebS
from litellm.types.utils import ModelResponse, StandardBuiltInToolsParams
def test_web_search_cost_low():
web_search_options = WebSearchOptions(search_context_size="low")
model_info = litellm.get_model_info("gpt-4o-search-preview")
@ -683,12 +682,13 @@ def test_web_search_provider_prefix_fallback_does_not_misprice_non_gemini_model(
def _openai_responses_with_web_search_calls(model, num_calls):
from litellm.types.llms.openai import ResponsesAPIResponse
from openai.types.responses.response_function_web_search import (
ActionSearch,
ResponseFunctionWebSearch,
)
from litellm.types.llms.openai import ResponsesAPIResponse
output = [
ResponseFunctionWebSearch(
id=f"ws_{i}",
@ -859,11 +859,62 @@ def test_dated_search_preview_entries_carry_search_pricing(local_model_cost_map)
custom_llm_provider="openai",
standard_built_in_tools_params=None,
)
assert cost == pytest.approx(0.035), (
f"dated search-preview id must bill the $0.035 search fee, got ${cost}"
assert cost == pytest.approx(0.025), (
f"dated search-preview id must bill the $0.025 search fee, got ${cost}"
)
@pytest.mark.parametrize(
"web_search_options",
[
None,
WebSearchOptions(search_context_size="low"),
WebSearchOptions(search_context_size="medium"),
WebSearchOptions(search_context_size="high"),
],
)
def test_gpt_4o_mini_snapshot_bills_web_search_like_its_alias(
web_search_options: WebSearchOptions | None, local_model_cost_map: None
) -> None:
alias_info = litellm.get_model_info("gpt-4o-mini")
snapshot_info = litellm.get_model_info("gpt-4o-mini-2024-07-18")
assert snapshot_info["supports_web_search"] is True
assert alias_info["supports_web_search"] is True
snapshot_cost = StandardBuiltInToolCostTracking.get_cost_for_web_search(
web_search_options=web_search_options, model_info=snapshot_info
)
alias_cost = StandardBuiltInToolCostTracking.get_cost_for_web_search(
web_search_options=web_search_options, model_info=alias_info
)
assert snapshot_cost == alias_cost == 0.025
def test_gpt_4o_mini_web_search_price_matches_in_both_cost_maps():
repo_root = Path(__file__).parents[4]
cost_maps = tuple(
json.loads((repo_root / path).read_text(encoding="utf-8"))
for path in (
"model_prices_and_context_window.json",
"litellm/model_prices_and_context_window_backup.json",
)
)
canonical, backup = cost_maps
expected_search_price = {
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025,
"search_context_size_high": 0.025,
}
for model_name in ("gpt-4o-mini", "gpt-4o-mini-2024-07-18"):
canonical_entry = canonical[model_name]
backup_entry = backup[model_name]
assert canonical_entry["search_context_cost_per_query"] == expected_search_price
assert backup_entry["search_context_cost_per_query"] == expected_search_price
assert canonical_entry == backup_entry
# Note: File search integration test removed due to complex annotation detection logic
# The unit tests in test_azure_assistant_cost_tracking.py provide comprehensive coverage

55
tests/test_litellm/llms/chatgpt/responses/test_chatgpt_responses_transformation.py
View file

@ -10,18 +10,23 @@ from unittest.mock import MagicMock, patch
import httpx
import pytest
import litellm
from litellm.llms.chatgpt.responses.transformation import ChatGPTResponsesAPIConfig
from litellm.llms.openai.common_utils import OpenAIError
from litellm.main import responses_api_bridge_check
from litellm.types.router import GenericLiteLLMParams
from litellm.types.utils import LlmProviders
from litellm.utils import ProviderConfigManager
from litellm.llms.chatgpt.responses.transformation import ChatGPTResponsesAPIConfig
class TestChatGPTResponsesAPITransformation:
@pytest.mark.parametrize(
"model_name",
[
"chatgpt/gpt-5.5",
"chatgpt/gpt-5.6-luna",
"chatgpt/gpt-5.6-sol",
"chatgpt/gpt-5.6-terra",
"chatgpt/gpt-5.4",
"chatgpt/gpt-5.4-pro",
"chatgpt/gpt-5.3-chat-latest",
@ -40,6 +45,52 @@ class TestChatGPTResponsesAPITransformation:
assert isinstance(config, ChatGPTResponsesAPIConfig)
assert config.custom_llm_provider == LlmProviders.CHATGPT
@pytest.mark.parametrize(
"model_name",
[
"chatgpt/gpt-5.5",
"chatgpt/gpt-5.6-luna",
"chatgpt/gpt-5.6-sol",
"chatgpt/gpt-5.6-terra",
],
)
def test_chatgpt_responses_model_metadata(self, model_name: str, local_model_cost_map: None) -> None:
model_info = litellm.get_model_info(model_name)
assert model_info["litellm_provider"] == "chatgpt"
assert model_info["mode"] == "responses"
assert model_info["supported_endpoints"] == [
"/v1/chat/completions",
"/v1/responses",
]
assert model_info["max_input_tokens"] == 1050000
assert model_info["max_output_tokens"] == 128000
@pytest.mark.parametrize(
"model_name",
[
"gpt-5.5",
"gpt-5.6-luna",
"gpt-5.6-sol",
"gpt-5.6-terra",
],
)
def test_chatgpt_models_bridge_chat_completions_to_responses(
self, model_name: str, local_model_cost_map: None
) -> None:
"""A chat completions request for these models must take the Responses bridge.
`gpt-5.6-*` also exists as an openai chat model, so an unregistered
chatgpt model resolves to mode "chat" here and never reaches the bridge.
"""
model_info, resolved_model = responses_api_bridge_check(
model=model_name,
custom_llm_provider="chatgpt",
)
assert model_info["mode"] == "responses"
assert resolved_model == model_name
@patch("litellm.llms.chatgpt.responses.transformation.Authenticator")
def test_chatgpt_responses_endpoint_url(self, mock_authenticator_class):
mock_auth_instance = MagicMock()

4
tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_gemini_transcribe_transformation.py
View file

@ -322,8 +322,8 @@ class TestModelCostEntry:
entry = json.load(f)["vertex_ai/gemini-3.5-transcribe-preview"]
assert entry["mode"] == "audio_transcription"
assert entry["litellm_provider"] == "vertex_ai"
assert entry["input_cost_per_audio_token"] == pytest.approx(2.5e-06)
assert entry["input_cost_per_token"] == pytest.approx(2.5e-06)
assert entry["input_cost_per_audio_token"] == pytest.approx(2e-06)
assert entry["input_cost_per_token"] == pytest.approx(2e-06)
assert entry["output_cost_per_token"] == pytest.approx(1.2e-05)
assert entry["supported_endpoints"] == ["/v1/audio/transcriptions"]

6
tests/test_litellm/test_utils.py
View file

@ -54,6 +54,12 @@ from litellm.utils import (
# Adds the parent directory to the system path
def test_cloudflare_model_info_includes_rpm(local_model_cost_map: None) -> None:
assert litellm.get_model_info("cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8")["rpm"] == 300
assert litellm.get_model_info("cloudflare/@cf/moonshotai/kimi-k2.6")["rpm"] == 20
assert litellm.get_model_info("cloudflare/@cf/openai/whisper-large-v3-turbo")["rpm"] == 720
def test_get_utc_datetime_returns_current_aware_utc_time() -> None:
before: Final = datetime.now(timezone.utc)
result: Final = litellm.utils.get_utc_datetime()