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 gpt-4.1 pricing (#9990)

Browse source 
* build(model_prices_and_context_window.json): add gpt-4.1 pricing

* build(model_prices_and_context_window.json): add gpt-4.1-mini and gpt-4.1-nano model support
This commit is contained in:
Krish Dholakia 2025-04-14 12:14:46 -07:00 • committed by GitHub
parent 64bb89c70f
commit bbb7541c22
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 276 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

138
litellm/model_prices_and_context_window_backup.json
View file

@ -64,6 +64,144 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"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": 1e-6,
"litellm_provider": "openai",
"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
},
"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": 1e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-mini": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-mini-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-nano": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-nano-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"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
},
"gpt-4o": {
"max_tokens": 16384,
"max_input_tokens": 128000,

138
model_prices_and_context_window.json
View file

@ -64,6 +64,144 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"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": 1e-6,
"litellm_provider": "openai",
"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
},
"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": 1e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-mini": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-mini-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-nano": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"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
},
"gpt-4.1-nano-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"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
},
"gpt-4o": {
"max_tokens": 16384,
"max_input_tokens": 128000,