scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-14 23:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

fix(model_prices): absorb cerebras/inception PRs, fix vertex/openai/together/openrouter pricing

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-09-11 19:37:45 +00:00
parent 7b25c6a29e
commit 4ffd4ecc83
4 changed files with 761 additions and 124 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

421
litellm/model_prices_and_context_window_backup.json
View file

@ -13118,6 +13118,22 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"cerebras/qwen-3.8-27b": {
"input_cost_per_token": 9.9e-07,
"litellm_provider": "cerebras",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.49e-06,
"source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"chatdolphin": {
"input_cost_per_token": 5e-07,
"litellm_provider": "nlp_cloud",
@ -31328,8 +31344,6 @@
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
},
"gpt-5.5-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -31378,8 +31392,6 @@
"supports_low_reasoning_effort": false
},
"gpt-5.5-pro-2026-04-23": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -31532,8 +31544,6 @@
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -31583,8 +31593,6 @@
"output_cost_per_token_above_272k_tokens_flex": 0.000135
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -33891,6 +33899,20 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"inception/mercury-2.5": {
"input_cost_per_token": 2e-07,
"litellm_provider": "inception",
"max_input_tokens": 260000,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 7.5e-07,
"source": "https://docs.inceptionlabs.ai/get-started/models",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"text-completion-inception/mercury-edit-2": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 2.5e-07,
@ -39127,19 +39149,21 @@
"supports_tool_choice": true
},
"openrouter/deepseek/deepseek-chat-v3.1": {
"input_cost_per_token": 2e-07,
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_cache_hit": 2e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 8e-07,
"output_cost_per_token": 9.5e-07,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 1.3e-07,
"source": "https://openrouter.ai/deepseek/deepseek-chat-v3.1"
},
"openrouter/deepseek/deepseek-v3.2": {
"input_cost_per_token": 2.69e-07,
@ -39202,36 +39226,56 @@
"supports_tool_choice": true
},
"openrouter/deepseek/deepseek-v4-pro": {
"input_cost_per_token": 1.32e-06,
"input_cost_per_token": 8.59908e-07,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"output_cost_per_token": 1.719816e-06,
"source": "https://openrouter.ai/deepseek/deepseek-v4-pro",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 7.1659e-08
},
"openrouter/deepseek/deepseek-v4.1-flash": {
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 6e-07,
"cache_read_input_token_cost": 3e-09,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"source": "https://openrouter.ai/deepseek/deepseek-v4.1-flash",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": false,
"supports_prompt_caching": true
},
"openrouter/deepseek/deepseek-v4-pro-0813": {
"input_cost_per_token": 1.32e-06,
"input_cost_per_token": 5.7948e-07,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"output_cost_per_token": 1.73844e-06,
"source": "https://openrouter.ai/deepseek/deepseek-v4-pro-0813",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 1.9316e-08
},
"openrouter/google/gemini-2.0-flash-001": {
"deprecation_date": "2026-06-01",
@ -40010,6 +40054,28 @@
"supports_tool_choice": true,
"supports_vision": true
},
"openrouter/openai/gpt-5.6-sol-pro": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-5.6-sol-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-oss-120b": {
"input_cost_per_token": 3.7e-08,
"litellm_provider": "openrouter",
@ -40138,13 +40204,13 @@
"supports_tool_choice": true
},
"openrouter/qwen/qwen3-235b-a22b-2507": {
"input_cost_per_token": 8.75e-08,
"input_cost_per_token": 2.2e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3.5e-07,
"output_cost_per_token": 8.8e-07,
"source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507",
"supports_function_calling": true,
"supports_tool_choice": true
@ -40177,7 +40243,7 @@
"supports_vision": true
},
"openrouter/qwen/qwen3.5-35b-a3b": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token": 3.125e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
@ -40188,7 +40254,8 @@
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"cache_read_input_token_cost": 1.5625e-07
},
"openrouter/qwen/qwen3.5-27b": {
"input_cost_per_token": 1.95e-07,
@ -40205,13 +40272,13 @@
"supports_vision": true
},
"openrouter/qwen/qwen3.5-122b-a10b": {
"input_cost_per_token": 2.9e-07,
"input_cost_per_token": 2.6e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.4e-06,
"output_cost_per_token": 2.08e-06,
"source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b",
"supports_function_calling": true,
"supports_reasoning": true,
@ -40298,18 +40365,19 @@
"supports_web_search": true
},
"openrouter/z-ai/glm-4.6": {
"input_cost_per_token": 5.5e-07,
"input_cost_per_token": 4.3e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 202800,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 2.2e-06,
"output_cost_per_token": 1.75e-06,
"source": "https://openrouter.ai/z-ai/glm-4.6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 8e-08
},
"openrouter/z-ai/glm-4.6:exacto": {
"input_cost_per_token": 4.5e-07,
@ -43134,7 +43202,11 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 1.2e-06,
"max_input_tokens": 131072,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": {
"litellm_provider": "together_ai",
@ -43142,7 +43214,11 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 3e-07,
"max_input_tokens": 32768,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
"deprecation_date": "2026-07-10",
@ -43354,7 +43430,11 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"max_input_tokens": 32768,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
"deprecation_date": "2026-04-02",
@ -43362,7 +43442,11 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 3e-07,
"max_input_tokens": 32768,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": {
"deprecation_date": "2026-04-16",
@ -48093,27 +48177,29 @@
"supports_tool_choice": true
},
"vertex_ai/mistral-small-2503": {
"input_cost_per_token": 1e-06,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-mistral_models",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-06,
"output_cost_per_token": 3e-07,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"vertex_ai/mistral-small-2503@001": {
"input_cost_per_token": 1e-06,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-mistral_models",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"max_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 3e-06,
"output_cost_per_token": 3e-07,
"supports_function_calling": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"vertex_ai/mistral-ocr-2505": {
"litellm_provider": "vertex_ai",
@ -48163,15 +48249,16 @@
"supports_reasoning": true
},
"vertex_ai/openai/gpt-oss-20b-maas": {
"input_cost_per_token": 7.5e-08,
"input_cost_per_token": 7e-08,
"litellm_provider": "vertex_ai-openai_models",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 3e-07,
"source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas",
"supports_reasoning": true
"output_cost_per_token": 2.5e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supports_reasoning": true,
"cache_read_input_token_cost": 7e-09
},
"vertex_ai/xai/grok-4.1-fast-non-reasoning": {
"cache_read_input_token_cost": 5e-08,
@ -60695,6 +60782,113 @@
"output_cost_per_token": 4.7e-07,
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/moonshotai/Kimi-K2.6": {
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4.5e-06,
"cache_read_input_token_cost": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/moonshotai/Kimi-K2.5-fp4": {
"input_cost_per_token": 5e-07,
"output_cost_per_token": 2.8e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/MiniMaxAI/MiniMax-M2.7": {
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 6e-08,
"litellm_provider": "together_ai",
"max_input_tokens": 196608,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/zai-org/GLM-5": {
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 202752,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/zai-org/GLM-5.1": {
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"cache_read_input_token_cost": 2.6e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 202752,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-0528": {
"input_cost_per_token": 3e-06,
"output_cost_per_token": 7e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 163840,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-Coder-Next-FP8": {
"input_cost_per_token": 5e-07,
"output_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-VL-32B-Instruct": {
"input_cost_per_token": 5e-07,
"output_cost_per_token": 1.5e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-VL-8B-Instruct": {
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 6.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Ministral-3-14B-Instruct-2512": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
"input_cost_per_token": 6e-08,
"output_cost_per_token": 2.5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Mistral-7B-Instruct-v0.3": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/QwQ-32B": {
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"cerebras/gemma-4-31b": {
"input_cost_per_token": 9.9e-07,
"litellm_provider": "cerebras",
@ -62348,6 +62542,28 @@
"cache_read_input_token_cost": 2e-08,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-5.6-luna-pro": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 2e-08,
"cache_creation_input_token_cost": 2.5e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-5.6-luna-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-5.6-terra": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1.2e-05,
@ -62367,6 +62583,28 @@
"cache_read_input_token_cost": 2e-07,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-5.6-terra-pro": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1.2e-05,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-5.6-terra-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/o3": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 8e-06,
@ -62600,6 +62838,28 @@
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-6-astra-pro": {
"input_cost_per_token": 1e-05,
"output_cost_per_token": 5e-05,
"cache_read_input_token_cost": 1e-06,
"cache_creation_input_token_cost": 1.25e-05,
"input_cost_per_token_above_272k_tokens": 2e-05,
"output_cost_per_token_above_272k_tokens": 7.5e-05,
"cache_read_input_token_cost_above_272k_tokens": 2e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-6-astra-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/qwen/qwen3.8-flash": {
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 4.7e-07,
@ -62619,9 +62879,9 @@
"supports_prompt_caching": true
},
"openrouter/z-ai/glm-5.3-flash": {
"input_cost_per_token": 7.5e-08,
"output_cost_per_token": 2.5e-07,
"cache_read_input_token_cost": 1.5e-08,
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 5e-07,
"cache_read_input_token_cost": 3e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1310720,
"max_output_tokens": 131072,
@ -62736,6 +62996,25 @@
"supports_vision": true,
"supports_prompt_caching": true
},
"openrouter/qwen/qwen3.8-max-0902": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 6e-06,
"cache_read_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost": 2.5e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"source": "https://openrouter.ai/qwen/qwen3.8-max-0902",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": false,
"supports_prompt_caching": true
},
"openrouter/deepseek/deepseek-v4-flash-0731": {
"input_cost_per_token": 6.5e-08,
"output_cost_per_token": 1.8e-07,
@ -62807,9 +63086,9 @@
"supports_vision": false
},
"openrouter/moonshotai/kimi-k3": {
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 2.1e-06,
"output_cost_per_token": 1.053e-05,
"cache_read_input_token_cost": 2.35e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 943718,
@ -62906,9 +63185,9 @@
"supports_prompt_caching": true
},
"openrouter/z-ai/glm-5.2": {
"input_cost_per_token": 9.66e-07,
"output_cost_per_token": 3.036e-06,
"cache_read_input_token_cost": 1.932e-07,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 1.5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
@ -62939,9 +63218,9 @@
"supports_vision": false
},
"openrouter/moonshotai/kimi-k2.7-code": {
"input_cost_per_token": 6.6e-07,
"output_cost_per_token": 3.4e-06,
"cache_read_input_token_cost": 1.8e-07,
"input_cost_per_token": 7.1e-07,
"output_cost_per_token": 3.5e-06,
"cache_read_input_token_cost": 1.5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 235929,
@ -63189,10 +63468,28 @@
"supports_vision": true,
"supports_pdf_input": true
},
"openrouter/openai/gpt-chat-latest": {
"input_cost_per_token": 5e-06,
"output_cost_per_token": 3e-05,
"cache_read_input_token_cost": 5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-chat-latest",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": false,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/deepseek/deepseek-v4-flash": {
"input_cost_per_token": 8.778e-08,
"output_cost_per_token": 1.7556e-07,
"cache_read_input_token_cost": 1.7556e-08,
"input_cost_per_token": 8.54e-08,
"output_cost_per_token": 1.708e-07,
"cache_read_input_token_cost": 1.708e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
@ -63225,8 +63522,8 @@
"supports_prompt_caching": true
},
"openrouter/google/gemma-4-26b-a4b-it": {
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3.4e-07,
"input_cost_per_token": 4.2e-08,
"output_cost_per_token": 2.2e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 16384,
@ -63908,7 +64205,7 @@
"supports_vision": false
},
"openrouter/qwen/qwen3-next-80b-a3b-instruct": {
"input_cost_per_token": 1e-07,
"input_cost_per_token": 9e-08,
"output_cost_per_token": 1.1e-06,
"cache_read_input_token_cost": 7e-08,
"litellm_provider": "openrouter",
@ -64034,8 +64331,8 @@
"supports_vision": false
},
"openrouter/qwen/qwen3-30b-a3b-instruct-2507": {
"input_cost_per_token": 4.815e-08,
"output_cost_per_token": 1.9305e-07,
"input_cost_per_token": 9e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 32000,
@ -64233,8 +64530,8 @@
"supports_vision": false
},
"openrouter/qwen/qwen3-14b": {
"input_cost_per_token": 1.2e-07,
"output_cost_per_token": 2.4e-07,
"input_cost_per_token": 2.275e-07,
"output_cost_per_token": 9.1e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 131072,
"max_output_tokens": 16384,

421
model_prices_and_context_window.json
View file

@ -13118,6 +13118,22 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"cerebras/qwen-3.8-27b": {
"input_cost_per_token": 9.9e-07,
"litellm_provider": "cerebras",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.49e-06,
"source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"chatdolphin": {
"input_cost_per_token": 5e-07,
"litellm_provider": "nlp_cloud",
@ -31328,8 +31344,6 @@
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
},
"gpt-5.5-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -31378,8 +31392,6 @@
"supports_low_reasoning_effort": false
},
"gpt-5.5-pro-2026-04-23": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -31532,8 +31544,6 @@
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -31583,8 +31593,6 @@
"output_cost_per_token_above_272k_tokens_flex": 0.000135
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_flex": 1.5e-05,
@ -33891,6 +33899,20 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"inception/mercury-2.5": {
"input_cost_per_token": 2e-07,
"litellm_provider": "inception",
"max_input_tokens": 260000,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 7.5e-07,
"source": "https://docs.inceptionlabs.ai/get-started/models",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"text-completion-inception/mercury-edit-2": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 2.5e-07,
@ -39127,19 +39149,21 @@
"supports_tool_choice": true
},
"openrouter/deepseek/deepseek-chat-v3.1": {
"input_cost_per_token": 2e-07,
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_cache_hit": 2e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 8e-07,
"output_cost_per_token": 9.5e-07,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 1.3e-07,
"source": "https://openrouter.ai/deepseek/deepseek-chat-v3.1"
},
"openrouter/deepseek/deepseek-v3.2": {
"input_cost_per_token": 2.69e-07,
@ -39202,36 +39226,56 @@
"supports_tool_choice": true
},
"openrouter/deepseek/deepseek-v4-pro": {
"input_cost_per_token": 1.32e-06,
"input_cost_per_token": 8.59908e-07,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"output_cost_per_token": 1.719816e-06,
"source": "https://openrouter.ai/deepseek/deepseek-v4-pro",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 7.1659e-08
},
"openrouter/deepseek/deepseek-v4.1-flash": {
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 6e-07,
"cache_read_input_token_cost": 3e-09,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"source": "https://openrouter.ai/deepseek/deepseek-v4.1-flash",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": false,
"supports_prompt_caching": true
},
"openrouter/deepseek/deepseek-v4-pro-0813": {
"input_cost_per_token": 1.32e-06,
"input_cost_per_token": 5.7948e-07,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"output_cost_per_token": 1.73844e-06,
"source": "https://openrouter.ai/deepseek/deepseek-v4-pro-0813",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 1.9316e-08
},
"openrouter/google/gemini-2.0-flash-001": {
"deprecation_date": "2026-06-01",
@ -40010,6 +40054,28 @@
"supports_tool_choice": true,
"supports_vision": true
},
"openrouter/openai/gpt-5.6-sol-pro": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-5.6-sol-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-oss-120b": {
"input_cost_per_token": 3.7e-08,
"litellm_provider": "openrouter",
@ -40138,13 +40204,13 @@
"supports_tool_choice": true
},
"openrouter/qwen/qwen3-235b-a22b-2507": {
"input_cost_per_token": 8.75e-08,
"input_cost_per_token": 2.2e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3.5e-07,
"output_cost_per_token": 8.8e-07,
"source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507",
"supports_function_calling": true,
"supports_tool_choice": true
@ -40177,7 +40243,7 @@
"supports_vision": true
},
"openrouter/qwen/qwen3.5-35b-a3b": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token": 3.125e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
@ -40188,7 +40254,8 @@
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"cache_read_input_token_cost": 1.5625e-07
},
"openrouter/qwen/qwen3.5-27b": {
"input_cost_per_token": 1.95e-07,
@ -40205,13 +40272,13 @@
"supports_vision": true
},
"openrouter/qwen/qwen3.5-122b-a10b": {
"input_cost_per_token": 2.9e-07,
"input_cost_per_token": 2.6e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.4e-06,
"output_cost_per_token": 2.08e-06,
"source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b",
"supports_function_calling": true,
"supports_reasoning": true,
@ -40298,18 +40365,19 @@
"supports_web_search": true
},
"openrouter/z-ai/glm-4.6": {
"input_cost_per_token": 5.5e-07,
"input_cost_per_token": 4.3e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 202800,
"max_output_tokens": 131000,
"max_tokens": 131000,
"mode": "chat",
"output_cost_per_token": 2.2e-06,
"output_cost_per_token": 1.75e-06,
"source": "https://openrouter.ai/z-ai/glm-4.6",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 8e-08
},
"openrouter/z-ai/glm-4.6:exacto": {
"input_cost_per_token": 4.5e-07,
@ -43134,7 +43202,11 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 1.2e-06,
"max_input_tokens": 131072,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": {
"litellm_provider": "together_ai",
@ -43142,7 +43214,11 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 3e-07,
"max_input_tokens": 32768,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
"deprecation_date": "2026-07-10",
@ -43354,7 +43430,11 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"max_input_tokens": 32768,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
"deprecation_date": "2026-04-02",
@ -43362,7 +43442,11 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 3e-07,
"max_input_tokens": 32768,
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": {
"deprecation_date": "2026-04-16",
@ -48093,27 +48177,29 @@
"supports_tool_choice": true
},
"vertex_ai/mistral-small-2503": {
"input_cost_per_token": 1e-06,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-mistral_models",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-06,
"output_cost_per_token": 3e-07,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"vertex_ai/mistral-small-2503@001": {
"input_cost_per_token": 1e-06,
"input_cost_per_token": 1e-07,
"litellm_provider": "vertex_ai-mistral_models",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"max_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 3e-06,
"output_cost_per_token": 3e-07,
"supports_function_calling": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"vertex_ai/mistral-ocr-2505": {
"litellm_provider": "vertex_ai",
@ -48163,15 +48249,16 @@
"supports_reasoning": true
},
"vertex_ai/openai/gpt-oss-20b-maas": {
"input_cost_per_token": 7.5e-08,
"input_cost_per_token": 7e-08,
"litellm_provider": "vertex_ai-openai_models",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 3e-07,
"source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas",
"supports_reasoning": true
"output_cost_per_token": 2.5e-07,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supports_reasoning": true,
"cache_read_input_token_cost": 7e-09
},
"vertex_ai/xai/grok-4.1-fast-non-reasoning": {
"cache_read_input_token_cost": 5e-08,
@ -60695,6 +60782,113 @@
"output_cost_per_token": 4.7e-07,
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/moonshotai/Kimi-K2.6": {
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4.5e-06,
"cache_read_input_token_cost": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/moonshotai/Kimi-K2.5-fp4": {
"input_cost_per_token": 5e-07,
"output_cost_per_token": 2.8e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/MiniMaxAI/MiniMax-M2.7": {
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 6e-08,
"litellm_provider": "together_ai",
"max_input_tokens": 196608,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/zai-org/GLM-5": {
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 202752,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/zai-org/GLM-5.1": {
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"cache_read_input_token_cost": 2.6e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 202752,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-0528": {
"input_cost_per_token": 3e-06,
"output_cost_per_token": 7e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 163840,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-Coder-Next-FP8": {
"input_cost_per_token": 5e-07,
"output_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-VL-32B-Instruct": {
"input_cost_per_token": 5e-07,
"output_cost_per_token": 1.5e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/Qwen3-VL-8B-Instruct": {
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 6.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Ministral-3-14B-Instruct-2512": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
"input_cost_per_token": 6e-08,
"output_cost_per_token": 2.5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/mistralai/Mistral-7B-Instruct-v0.3": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"together_ai/Qwen/QwQ-32B": {
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"mode": "chat",
"source": "https://api.together.xyz/v1/models"
},
"cerebras/gemma-4-31b": {
"input_cost_per_token": 9.9e-07,
"litellm_provider": "cerebras",
@ -62348,6 +62542,28 @@
"cache_read_input_token_cost": 2e-08,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-5.6-luna-pro": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 1.2e-06,
"cache_read_input_token_cost": 2e-08,
"cache_creation_input_token_cost": 2.5e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-5.6-luna-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-5.6-terra": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1.2e-05,
@ -62367,6 +62583,28 @@
"cache_read_input_token_cost": 2e-07,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-5.6-terra-pro": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 1.2e-05,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-5.6-terra-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/o3": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 8e-06,
@ -62600,6 +62838,28 @@
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/openai/gpt-6-astra-pro": {
"input_cost_per_token": 1e-05,
"output_cost_per_token": 5e-05,
"cache_read_input_token_cost": 1e-06,
"cache_creation_input_token_cost": 1.25e-05,
"input_cost_per_token_above_272k_tokens": 2e-05,
"output_cost_per_token_above_272k_tokens": 7.5e-05,
"cache_read_input_token_cost_above_272k_tokens": 2e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-6-astra-pro",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/qwen/qwen3.8-flash": {
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 4.7e-07,
@ -62619,9 +62879,9 @@
"supports_prompt_caching": true
},
"openrouter/z-ai/glm-5.3-flash": {
"input_cost_per_token": 7.5e-08,
"output_cost_per_token": 2.5e-07,
"cache_read_input_token_cost": 1.5e-08,
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 5e-07,
"cache_read_input_token_cost": 3e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1310720,
"max_output_tokens": 131072,
@ -62736,6 +62996,25 @@
"supports_vision": true,
"supports_prompt_caching": true
},
"openrouter/qwen/qwen3.8-max-0902": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 6e-06,
"cache_read_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost": 2.5e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"source": "https://openrouter.ai/qwen/qwen3.8-max-0902",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": false,
"supports_prompt_caching": true
},
"openrouter/deepseek/deepseek-v4-flash-0731": {
"input_cost_per_token": 6.5e-08,
"output_cost_per_token": 1.8e-07,
@ -62807,9 +63086,9 @@
"supports_vision": false
},
"openrouter/moonshotai/kimi-k3": {
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 2.1e-06,
"output_cost_per_token": 1.053e-05,
"cache_read_input_token_cost": 2.35e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 943718,
@ -62906,9 +63185,9 @@
"supports_prompt_caching": true
},
"openrouter/z-ai/glm-5.2": {
"input_cost_per_token": 9.66e-07,
"output_cost_per_token": 3.036e-06,
"cache_read_input_token_cost": 1.932e-07,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 1.5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
@ -62939,9 +63218,9 @@
"supports_vision": false
},
"openrouter/moonshotai/kimi-k2.7-code": {
"input_cost_per_token": 6.6e-07,
"output_cost_per_token": 3.4e-06,
"cache_read_input_token_cost": 1.8e-07,
"input_cost_per_token": 7.1e-07,
"output_cost_per_token": 3.5e-06,
"cache_read_input_token_cost": 1.5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 235929,
@ -63189,10 +63468,28 @@
"supports_vision": true,
"supports_pdf_input": true
},
"openrouter/openai/gpt-chat-latest": {
"input_cost_per_token": 5e-06,
"output_cost_per_token": 3e-05,
"cache_read_input_token_cost": 5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"source": "https://openrouter.ai/openai/gpt-chat-latest",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": false,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true
},
"openrouter/deepseek/deepseek-v4-flash": {
"input_cost_per_token": 8.778e-08,
"output_cost_per_token": 1.7556e-07,
"cache_read_input_token_cost": 1.7556e-08,
"input_cost_per_token": 8.54e-08,
"output_cost_per_token": 1.708e-07,
"cache_read_input_token_cost": 1.708e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
@ -63225,8 +63522,8 @@
"supports_prompt_caching": true
},
"openrouter/google/gemma-4-26b-a4b-it": {
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3.4e-07,
"input_cost_per_token": 4.2e-08,
"output_cost_per_token": 2.2e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 16384,
@ -63908,7 +64205,7 @@
"supports_vision": false
},
"openrouter/qwen/qwen3-next-80b-a3b-instruct": {
"input_cost_per_token": 1e-07,
"input_cost_per_token": 9e-08,
"output_cost_per_token": 1.1e-06,
"cache_read_input_token_cost": 7e-08,
"litellm_provider": "openrouter",
@ -64034,8 +64331,8 @@
"supports_vision": false
},
"openrouter/qwen/qwen3-30b-a3b-instruct-2507": {
"input_cost_per_token": 4.815e-08,
"output_cost_per_token": 1.9305e-07,
"input_cost_per_token": 9e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 262144,
"max_output_tokens": 32000,
@ -64233,8 +64530,8 @@
"supports_vision": false
},
"openrouter/qwen/qwen3-14b": {
"input_cost_per_token": 1.2e-07,
"output_cost_per_token": 2.4e-07,
"input_cost_per_token": 2.275e-07,
"output_cost_per_token": 9.1e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 131072,
"max_output_tokens": 16384,

21
tests/test_litellm/llms/cerebras/test_cerebras_chat_transformation.py
View file

@ -1,3 +1,4 @@
import litellm
from litellm.llms.cerebras.chat import CerebrasConfig
@ -59,3 +60,23 @@ def test_map_openai_params_preserves_max_retries_zero_falsy() -> None:
assert "max_retries" in result and result["max_retries"] == 0, (
f"max_retries=0 (falsy) must not be silently omitted; got: {result!r}"
)
def test_qwen_3_8_27b_cost_and_tokens(monkeypatch) -> None:
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
model = "cerebras/qwen-3.8-27b"
prompt_cost, completion_cost = litellm.cost_per_token(
model=model,
prompt_tokens=1000,
completion_tokens=1000,
)
assert abs(prompt_cost - 0.00099) < 1e-9
assert abs(completion_cost - 0.00149) < 1e-9
model_info = litellm.get_model_info(model)
assert model_info["max_input_tokens"] == 65536
assert model_info["max_output_tokens"] == 32768
assert model_info["supports_vision"] is True
assert model_info["supports_reasoning"] is True
assert model_info["supports_parallel_function_calling"] is True

22
tests/test_litellm/llms/inception/test_inception_chat_transformation.py
View file

@ -238,6 +238,7 @@ def test_inception_model_list_populated(monkeypatch):
litellm.add_known_models()
assert "inception/mercury-2" in litellm.inception_models
assert "inception/mercury-2.5" in litellm.inception_models
for model in litellm.inception_models:
assert model.startswith("inception/")
@ -304,3 +305,24 @@ def test_inception_completion_targets_inception_endpoint():
assert captured["body"]["model"] == "mercury-2"
assert captured["body"]["tool_choice"] == "auto"
assert response.choices[0].message.content == "hi"
def test_inception_mercury_2_5_cost_and_tokens(monkeypatch):
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
model = "inception/mercury-2.5"
prompt_cost, completion_cost = litellm.cost_per_token(
model=model,
prompt_tokens=1000,
completion_tokens=500,
)
assert abs(prompt_cost - 0.0002) < 1e-9
assert abs(completion_cost - 0.000375) < 1e-9
model_info = litellm.get_model_info(model)
assert model_info["max_input_tokens"] == 260000
assert model_info["max_output_tokens"] == 65536
assert model_info["litellm_provider"] == "inception"
assert model_info["mode"] == "chat"
assert model_info["supports_function_calling"] is True
assert model_info["supports_response_schema"] is True