tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-05 20:23:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #9361 from BerriAI/litellm_fix_azure_gpt_4o_pricing

Browse Source 
build(model_prices_and_context_window.json): fix azure gpt-4o pricing
This commit is contained in:
Krish Dholakia
2025-03-18 22:42:38 -07:00
committed by GitHub
parent c101fe9b5d 0194c18820
commit c83e19e8c7
2 changed files with 82 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+41 -6
View File
@@ -1385,16 +1385,33 @@
"supports_prompt_caching": true
},
"azure/gpt-4o": {
"max_tokens": 4096,
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.000015,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
},
"azure/global/gpt-4o-2024-11-20": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
@@ -1403,8 +1420,24 @@
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000275,
"output_cost_per_token": 0.000011,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
},
"azure/global/gpt-4o-2024-08-06": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
@@ -1421,12 +1454,14 @@
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000275,
"output_cost_per_token": 0.000011,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
},
"azure/us/gpt-4o-2024-11-20": {
model_prices_and_context_window.json
+41 -6
View File
@@ -1385,16 +1385,33 @@
"supports_prompt_caching": true
},
"azure/gpt-4o": {
"max_tokens": 4096,
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.000015,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
},
"azure/global/gpt-4o-2024-11-20": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
@@ -1403,8 +1420,24 @@
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000275,
"output_cost_per_token": 0.000011,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
},
"azure/global/gpt-4o-2024-08-06": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
@@ -1421,12 +1454,14 @@
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000275,
"output_cost_per_token": 0.000011,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
},
"azure/us/gpt-4o-2024-11-20": {