phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 078e17b2f2 into b82af5b826

Browse source
This commit is contained in:
Emerson Gomes 2025-04-24 00:55:34 -07:00 • committed by GitHub
commit 82e6c97d44
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 37 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

37
model_prices_and_context_window.json
View file

@ -2924,6 +2924,17 @@
"supports_tool_choice": true,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438"
},
"azure_ai/deepseek-v3-0324": {
"max_tokens": 8192,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000114,
"output_cost_per_token": 0.00000456,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_tool_choice": true,
"source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438"
},
"azure_ai/jamba-instruct": {
"max_tokens": 4096,
"max_input_tokens": 70000,
@ -3040,6 +3051,32 @@
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview",
"supports_tool_choice": true
},
"azure_ai/Llama-4-Scout-17B-16E-Instruct": {
"max_tokens": 16384,
"max_input_tokens": 10000000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.00000078,
"litellm_provider": "azure_ai",
"supports_function_calling": true,
"supports_vision": true,
"mode": "chat",
"source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/",
"supports_tool_choice": true
},
"azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": {
"max_tokens": 16384,
"max_input_tokens": 1000000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000141,
"output_cost_per_token": 0.00000035,
"litellm_provider": "azure_ai",
"supports_function_calling": true,
"supports_vision": true,
"mode": "chat",
"source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/",
"supports_tool_choice": true
},
"azure_ai/Llama-3.2-90B-Vision-Instruct": {
"max_tokens": 2048,
"max_input_tokens": 128000,