scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

fix(model_prices): azure gpt-5.6 cache writes, mistral missing models, together cache reads

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-08-26 19:20:14 +00:00
parent 0cc407a02d
commit 4456a4407f
3 changed files with 560 additions and 62 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

272
litellm/model_prices_and_context_window_backup.json
View file

@ -6592,6 +6592,9 @@
"supports_web_search": true
},
"azure/gpt-5.6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6642,6 +6645,9 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6693,6 +6699,9 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_priority": 4e-07,
@ -6744,6 +6753,9 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_priority": 4e-08,
@ -6795,12 +6807,15 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6808,7 +6823,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6842,13 +6857,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6856,7 +6874,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6890,13 +6908,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_priority": 5.5e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6904,7 +6925,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6938,13 +6959,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_priority": 5.5e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_priority": 5.5e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6952,7 +6976,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6986,12 +7010,15 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6999,7 +7026,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -7033,13 +7060,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -7047,7 +7077,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -7081,13 +7111,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_priority": 5.5e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -7095,7 +7128,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -7129,13 +7162,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_priority": 5.5e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_priority": 5.5e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -7143,7 +7179,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -30721,6 +30757,152 @@
"supports_response_schema": true,
"supports_tool_choice": true
},
"mistral/ministral-14b-2512": {
"input_cost_per_token": 2e-07,
"litellm_provider": "mistral",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://docs.mistral.ai/models/ministral-3-14b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/ministral-14b-latest": {
"input_cost_per_token": 2e-07,
"litellm_provider": "mistral",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://docs.mistral.ai/models/ministral-3-14b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/ministral-3b-2512": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://docs.mistral.ai/models/ministral-3-3b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/ministral-3b-latest": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://docs.mistral.ai/models/ministral-3-3b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/mistral-embed-2312": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"source": "https://docs.mistral.ai/models/mistral-embed-23-12"
},
"mistral/mistral-medium-3": {
"input_cost_per_token": 1.5e-06,
"litellm_provider": "mistral",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 7.5e-06,
"source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/voxtral-mini-transcribe-realtime-latest": {
"input_cost_per_second": 0.0001,
"litellm_provider": "mistral",
"mode": "audio_transcription",
"source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02",
"supported_endpoints": [
"/v1/audio/transcriptions"
],
"supported_modalities": [
"audio"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true
},
"mistral/voxtral-mini-tts-latest": {
"litellm_provider": "mistral",
"mode": "audio_speech",
"output_cost_per_character": 1.6e-05,
"source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03",
"supported_endpoints": [
"/v1/audio/speech"
],
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"audio"
],
"supports_audio_output": true
},
"mistral/voxtral-small-2507": {
"input_cost_per_second": 6.666666666666667e-05,
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4e-07,
"source": "https://docs.mistral.ai/models/voxtral-small-25-07",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"mistral/voxtral-small-latest": {
"input_cost_per_second": 6.666666666666667e-05,
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4e-07,
"source": "https://docs.mistral.ai/models/voxtral-small-25-07",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"mistral/zai-glm-5-2": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
@ -31191,9 +31373,9 @@
"mistral/ministral-3-3b-2512": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://mistral.ai/pricing",
@ -38342,6 +38524,7 @@
"supports_tool_choice": true
},
"together_ai/Qwen/Qwen3.5-397B-A17B": {
"cache_read_input_token_cost": 3.5e-07,
"deprecation_date": "2026-06-29",
"input_cost_per_token": 6e-07,
"litellm_provider": "together_ai",
@ -38351,10 +38534,12 @@
"source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/MiniMaxAI/MiniMax-M3": {
"cache_read_input_token_cost": 6e-08,
"input_cost_per_token": 3e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 524288,
@ -38365,6 +38550,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -38408,6 +38594,7 @@
"supports_reasoning": true
},
"together_ai/Qwen/Qwen3.7-Max": {
"cache_read_input_token_cost": 1.3e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1000000,
@ -38415,7 +38602,8 @@
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 3.75e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/Qwen/Qwen3.7-Plus": {
"input_cost_per_token": 3.2e-07,
@ -38428,6 +38616,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/Qwen/Qwen3.8-2.4T-A95B": {
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 2.5e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1010000,
@ -38435,7 +38624,8 @@
"max_tokens": 1010000,
"mode": "chat",
"output_cost_per_token": 6.25e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/arize-ai/qwen-2-1.5b-instruct": {
"input_cost_per_token": 1e-07,
@ -38448,6 +38638,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1.4e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -38458,10 +38649,12 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/deepseek-ai/DeepSeek-V4-Pro": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 1.74e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 512000,
@ -38472,11 +38665,13 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": {
"cache_read_input_token_cost": 1.3e-07,
"input_cost_per_token": 1.32e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -38487,6 +38682,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
@ -38538,6 +38734,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/meta-models/Muse-Glimmer-30B": {
"cache_read_input_token_cost": 4e-08,
"input_cost_per_token": 3.5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
@ -38545,9 +38742,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.5e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/moonshotai/Kimi-K2.7-Code": {
"cache_read_input_token_cost": 1.9e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
@ -38558,11 +38757,13 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"together_ai/moonshotai/Kimi-K3": {
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -38573,12 +38774,14 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"together_ai/nvidia/nemotron-3-ultra-550b-a55b": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 512288,
@ -38589,6 +38792,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -38604,6 +38808,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/thinkingmachines/Inkling": {
"cache_read_input_token_cost": 1.7e-07,
"input_cost_per_token": 1e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 524288,
@ -38614,10 +38819,12 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/thinkingmachines/Inkling-Small": {
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 524288,
@ -38625,9 +38832,11 @@
"max_tokens": 524288,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/zai-org/GLM-5.2": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1048575,
@ -38638,6 +38847,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true

272
model_prices_and_context_window.json
View file

@ -6592,6 +6592,9 @@
"supports_web_search": true
},
"azure/gpt-5.6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6642,6 +6645,9 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1e-06,
@ -6693,6 +6699,9 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_priority": 4e-07,
@ -6744,6 +6753,9 @@
"supports_minimal_reasoning_effort": false
},
"azure/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_priority": 4e-08,
@ -6795,12 +6807,15 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6808,7 +6823,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6842,13 +6857,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6856,7 +6874,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6890,13 +6908,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_priority": 5.5e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6904,7 +6925,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6938,13 +6959,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/us/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_priority": 5.5e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_priority": 5.5e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6952,7 +6976,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -6986,12 +7010,15 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -6999,7 +7026,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -7033,13 +7060,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
"cache_creation_input_token_cost_priority": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
"cache_read_input_token_cost_priority": 1.1e-06,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,
"input_cost_per_token_priority": 1.375e-05,
"input_cost_per_token_priority": 1.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -7047,7 +7077,7 @@
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"output_cost_per_token_above_272k_tokens": 4.95e-05,
"output_cost_per_token_priority": 8.25e-05,
"output_cost_per_token_priority": 6.6e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -7081,13 +7111,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-terra": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_creation_input_token_cost_priority": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_priority": 5.5e-06,
"input_cost_per_token_priority": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -7095,7 +7128,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-05,
"output_cost_per_token_above_272k_tokens": 1.98e-05,
"output_cost_per_token_priority": 3.3e-05,
"output_cost_per_token_priority": 2.64e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -7129,13 +7162,16 @@
"supports_minimal_reasoning_effort": false
},
"azure/eu/gpt-5.6-luna": {
"cache_creation_input_token_cost": 2.75e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_creation_input_token_cost_priority": 5.5e-07,
"cache_read_input_token_cost": 2.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
"cache_read_input_token_cost_priority": 5.5e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_priority": 5.5e-07,
"input_cost_per_token_priority": 4.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
@ -7143,7 +7179,7 @@
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"output_cost_per_token_above_272k_tokens": 1.98e-06,
"output_cost_per_token_priority": 3.3e-06,
"output_cost_per_token_priority": 2.64e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -30721,6 +30757,152 @@
"supports_response_schema": true,
"supports_tool_choice": true
},
"mistral/ministral-14b-2512": {
"input_cost_per_token": 2e-07,
"litellm_provider": "mistral",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://docs.mistral.ai/models/ministral-3-14b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/ministral-14b-latest": {
"input_cost_per_token": 2e-07,
"litellm_provider": "mistral",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://docs.mistral.ai/models/ministral-3-14b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/ministral-3b-2512": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://docs.mistral.ai/models/ministral-3-3b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/ministral-3b-latest": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://docs.mistral.ai/models/ministral-3-3b-25-12",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/mistral-embed-2312": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"source": "https://docs.mistral.ai/models/mistral-embed-23-12"
},
"mistral/mistral-medium-3": {
"input_cost_per_token": 1.5e-06,
"litellm_provider": "mistral",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 7.5e-06,
"source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"mistral/voxtral-mini-transcribe-realtime-latest": {
"input_cost_per_second": 0.0001,
"litellm_provider": "mistral",
"mode": "audio_transcription",
"source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02",
"supported_endpoints": [
"/v1/audio/transcriptions"
],
"supported_modalities": [
"audio"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true
},
"mistral/voxtral-mini-tts-latest": {
"litellm_provider": "mistral",
"mode": "audio_speech",
"output_cost_per_character": 1.6e-05,
"source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03",
"supported_endpoints": [
"/v1/audio/speech"
],
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"audio"
],
"supports_audio_output": true
},
"mistral/voxtral-small-2507": {
"input_cost_per_second": 6.666666666666667e-05,
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4e-07,
"source": "https://docs.mistral.ai/models/voxtral-small-25-07",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"mistral/voxtral-small-latest": {
"input_cost_per_second": 6.666666666666667e-05,
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 4e-07,
"source": "https://docs.mistral.ai/models/voxtral-small-25-07",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"mistral/zai-glm-5-2": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.4e-06,
@ -31191,9 +31373,9 @@
"mistral/ministral-3-3b-2512": {
"input_cost_per_token": 1e-07,
"litellm_provider": "mistral",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 1e-07,
"source": "https://mistral.ai/pricing",
@ -38342,6 +38524,7 @@
"supports_tool_choice": true
},
"together_ai/Qwen/Qwen3.5-397B-A17B": {
"cache_read_input_token_cost": 3.5e-07,
"deprecation_date": "2026-06-29",
"input_cost_per_token": 6e-07,
"litellm_provider": "together_ai",
@ -38351,10 +38534,12 @@
"source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/MiniMaxAI/MiniMax-M3": {
"cache_read_input_token_cost": 6e-08,
"input_cost_per_token": 3e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 524288,
@ -38365,6 +38550,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
@ -38408,6 +38594,7 @@
"supports_reasoning": true
},
"together_ai/Qwen/Qwen3.7-Max": {
"cache_read_input_token_cost": 1.3e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1000000,
@ -38415,7 +38602,8 @@
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 3.75e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/Qwen/Qwen3.7-Plus": {
"input_cost_per_token": 3.2e-07,
@ -38428,6 +38616,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/Qwen/Qwen3.8-2.4T-A95B": {
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 2.5e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1010000,
@ -38435,7 +38624,8 @@
"max_tokens": 1010000,
"mode": "chat",
"output_cost_per_token": 6.25e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/arize-ai/qwen-2-1.5b-instruct": {
"input_cost_per_token": 1e-07,
@ -38448,6 +38638,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1.4e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -38458,10 +38649,12 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/deepseek-ai/DeepSeek-V4-Pro": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 1.74e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 512000,
@ -38472,11 +38665,13 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": {
"cache_read_input_token_cost": 1.3e-07,
"input_cost_per_token": 1.32e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -38487,6 +38682,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
@ -38538,6 +38734,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/meta-models/Muse-Glimmer-30B": {
"cache_read_input_token_cost": 4e-08,
"input_cost_per_token": 3.5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
@ -38545,9 +38742,11 @@
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.5e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/moonshotai/Kimi-K2.7-Code": {
"cache_read_input_token_cost": 1.9e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 262144,
@ -38558,11 +38757,13 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"together_ai/moonshotai/Kimi-K3": {
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -38573,12 +38774,14 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"together_ai/nvidia/nemotron-3-ultra-550b-a55b": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 512288,
@ -38589,6 +38792,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
@ -38604,6 +38808,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/thinkingmachines/Inkling": {
"cache_read_input_token_cost": 1.7e-07,
"input_cost_per_token": 1e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 524288,
@ -38614,10 +38819,12 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"together_ai/thinkingmachines/Inkling-Small": {
"cache_read_input_token_cost": 1e-07,
"input_cost_per_token": 5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 524288,
@ -38625,9 +38832,11 @@
"max_tokens": 524288,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://docs.together.ai/docs/serverless-models"
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
"together_ai/zai-org/GLM-5.2": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1048575,
@ -38638,6 +38847,7 @@
"source": "https://docs.together.ai/docs/serverless-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true

78
tests/test_litellm/test_cost_calculator.py
View file

@ -1727,6 +1727,84 @@ def test_azure_ai_cache_cost_calculation(_local_model_cost_map):
), f"Output cost mismatch: got {output_cost}, expected {expected_output_cost}"
AZURE_GPT_5_6_MAP_KEYS = (
"azure/gpt-5.6",
"azure/gpt-5.6-sol",
"azure/gpt-5.6-terra",
"azure/gpt-5.6-luna",
"azure/us/gpt-5.6",
"azure/us/gpt-5.6-sol",
"azure/us/gpt-5.6-terra",
"azure/us/gpt-5.6-luna",
"azure/eu/gpt-5.6",
"azure/eu/gpt-5.6-sol",
"azure/eu/gpt-5.6-terra",
"azure/eu/gpt-5.6-luna",
)
def test_azure_gpt_5_6_cache_write_tokens_are_billed(_local_model_cost_map):
"""
Azure bills gpt-5.6 prompt cache writes at 1.25x the input rate, but the
azure entries carried no ``cache_creation_input_token_cost``, so
cache-write tokens were billed at the plain input rate instead.
"""
from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token
from litellm.types.utils import PromptTokensDetailsWrapper, Usage
usage = Usage(
completion_tokens=100,
prompt_tokens=2000,
total_tokens=2100,
prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=0, text_tokens=687),
cache_creation_input_tokens=1313,
)
input_cost, output_cost = generic_cost_per_token(
model="azure/gpt-5.6-luna", usage=usage, custom_llm_provider="azure"
)
assert input_cost == pytest.approx(687 * 2e-07 + 1313 * 2.5e-07)
assert output_cost == pytest.approx(100 * 1.2e-06)
@pytest.mark.parametrize("model", AZURE_GPT_5_6_MAP_KEYS)
def test_azure_gpt_5_6_rates_match_azure_price_page(_local_model_cost_map, model):
"""
Per the Azure retail price API (2026-08-26): cache writes cost 1.25x input
on every published gpt-5.6 meter, and Data Zone standard and priority
rates cost 1.1x Global (us/eu priority rates previously sat at 1.25x).
Azure publishes no long-context priority meters, so the
``*_above_272k_tokens_priority`` suffix is excluded.
"""
entry = litellm.model_cost[model]
input_keys = [
key
for key in entry
if key.startswith("input_cost_per_token")
and not key.endswith("_above_272k_tokens_priority")
]
assert input_keys
for key in input_keys:
suffix = key[len("input_cost_per_token") :]
assert entry["cache_creation_input_token_cost" + suffix] == pytest.approx(
entry[key] * 1.25
), key
zone = model.split("/")[1]
if zone in ("us", "eu"):
global_entry = litellm.model_cost["azure/" + model.split("/", 2)[2]]
prefixes = ("input_cost_per_token", "output_cost_per_token", "cache_read", "cache_creation")
token_cost_keys = [
key
for key in entry
if key.startswith(prefixes) and not key.endswith("_above_272k_tokens_priority")
]
assert len(token_cost_keys) >= 9
for key in token_cost_keys:
assert entry[key] == pytest.approx(global_entry[key] * 1.1), key
def test_vertex_regional_deployment_costs_uplift_over_global(monkeypatch):
"""
Regression for https://github.com/BerriAI/litellm/issues/34393: two Vertex