scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

feat(models): add Azure Foundry model pricing

Browse source
This commit is contained in:
Yujong Lee 2026-08-31 09:56:48 -07:00
parent d6cce13308
commit 701ddd90c5
2 changed files with 108 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
litellm/model_prices_and_context_window_backup.json
View file

@ -9858,7 +9858,7 @@
"max_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 1.68e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -9873,7 +9873,7 @@
"max_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 1.68e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -9889,7 +9889,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 5.4e-06,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_reasoning": true,
"supports_tool_choice": true
},
@ -9901,7 +9901,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 4.56e-06,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_tool_choice": true
},
"azure_ai/deepseek-v3-0324": {
@ -9913,7 +9913,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 4.56e-06,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -9932,6 +9932,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-pro": {
"cache_read_input_token_cost": 1.45e-07,
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
@ -9942,10 +9943,12 @@
"output_cost_per_token": 3.48e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"cache_read_input_token_cost": 2.8e-08,
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
@ -9956,6 +9959,7 @@
"output_cost_per_token": 5.1e-07,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
@ -10164,6 +10168,7 @@
"supports_tool_choice": true
},
"azure_ai/kimi-k2.5": {
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2027-01-26",
"input_cost_per_token": 6e-07,
"litellm_provider": "azure_ai",
@ -10172,13 +10177,15 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true,
"supports_video_input": true,
"supports_vision": true
},
"azure_ai/kimi-k2.6": {
"cache_read_input_token_cost": 1.6e-07,
"deprecation_date": "2027-04-16",
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
@ -10187,7 +10194,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
@ -10196,6 +10203,7 @@
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
@ -10306,6 +10314,45 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/DeepSeek-V4-Flash-0731": {
"cache_read_input_token_cost": 2.8e-08,
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 5.1e-07,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"babbage-002": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 4e-07,

61
model_prices_and_context_window.json
View file

@ -9858,7 +9858,7 @@
"max_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 1.68e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -9873,7 +9873,7 @@
"max_tokens": 163840,
"mode": "chat",
"output_cost_per_token": 1.68e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -9889,7 +9889,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 5.4e-06,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_reasoning": true,
"supports_tool_choice": true
},
@ -9901,7 +9901,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 4.56e-06,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_tool_choice": true
},
"azure_ai/deepseek-v3-0324": {
@ -9913,7 +9913,7 @@
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 4.56e-06,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_tool_choice": true
},
@ -9932,6 +9932,7 @@
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-pro": {
"cache_read_input_token_cost": 1.45e-07,
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.74e-06,
"litellm_provider": "azure_ai",
@ -9942,10 +9943,12 @@
"output_cost_per_token": 3.48e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-flash": {
"cache_read_input_token_cost": 2.8e-08,
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
@ -9956,6 +9959,7 @@
"output_cost_per_token": 5.1e-07,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
@ -10164,6 +10168,7 @@
"supports_tool_choice": true
},
"azure_ai/kimi-k2.5": {
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2027-01-26",
"input_cost_per_token": 6e-07,
"litellm_provider": "azure_ai",
@ -10172,13 +10177,15 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true,
"supports_video_input": true,
"supports_vision": true
},
"azure_ai/kimi-k2.6": {
"cache_read_input_token_cost": 1.6e-07,
"deprecation_date": "2027-04-16",
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
@ -10187,7 +10194,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
@ -10196,6 +10203,7 @@
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
@ -10306,6 +10314,45 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/DeepSeek-V4-Flash-0731": {
"cache_read_input_token_cost": 2.8e-08,
"deprecation_date": "2028-02-20",
"input_cost_per_token": 1.9e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 5.1e-07,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"babbage-002": {
"deprecation_date": "2026-09-28",
"input_cost_per_token": 4e-07,