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

build(model_prices_and_context_window.json): add azure gpt-4.1 pricing

Browse source 
ensures cost tracking for gpt-4.1 works
This commit is contained in:
Krrish Dholakia 2025-04-17 20:09:05 -07:00
parent 3c71a81100
commit 614d80cb1b
3 changed files with 119 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

58
litellm/model_prices_and_context_window_backup.json
View file

@ -1471,6 +1471,64 @@
"litellm_provider": "openai",
"supported_endpoints": ["/v1/audio/speech"]
},
"azure/gpt-4.1": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 0.5e-6,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 30e-3,
"search_context_size_medium": 35e-3,
"search_context_size_high": 50e-3
}
},
"azure/gpt-4.1-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 0.5e-6,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 30e-3,
"search_context_size_medium": 35e-3,
"search_context_size_high": 50e-3
}
},
"azure/gpt-4o-mini-realtime-preview-2024-12-17": {
"max_tokens": 4096,
"max_input_tokens": 128000,

7
litellm/proxy/_new_secret_config.yaml
View file

@ -21,13 +21,12 @@ model_list:
model: databricks/databricks-claude-3-7-sonnet
api_key: os.environ/DATABRICKS_API_KEY
api_base: os.environ/DATABRICKS_API_BASE
- model_name: "gpt-4o-realtime-preview"
- model_name: "gpt-4.1"
litellm_params:
model: azure/gpt-4o-realtime-preview-2
model: azure/gpt-4.1
api_key: os.environ/AZURE_API_KEY_REALTIME
api_base: https://krris-m2f9a9i7-eastus2.openai.azure.com/
model_info:
base_model: azure/gpt-4o-realtime-preview-2024-10-01
litellm_settings:

58
model_prices_and_context_window.json
View file

@ -1471,6 +1471,64 @@
"litellm_provider": "openai",
"supported_endpoints": ["/v1/audio/speech"]
},
"azure/gpt-4.1": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 0.5e-6,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 30e-3,
"search_context_size_medium": 35e-3,
"search_context_size_high": 50e-3
}
},
"azure/gpt-4.1-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 0.5e-6,
"litellm_provider": "azure",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 30e-3,
"search_context_size_medium": 35e-3,
"search_context_size_high": 50e-3
}
},
"azure/gpt-4o-mini-realtime-preview-2024-12-17": {
"max_tokens": 4096,
"max_input_tokens": 128000,