From 4daa76aa61aa17d0ab2bec0797428c2ee73f218e Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Mon, 14 Apr 2025 12:12:40 -0700 Subject: [PATCH] build(model_prices_and_context_window.json): add gpt-4.1-mini and gpt-4.1-nano model support --- ...odel_prices_and_context_window_backup.json | 98 ++++++++++++++++++- model_prices_and_context_window.json | 98 ++++++++++++++++++- 2 files changed, 192 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 762984dec9..09217ee04a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -84,7 +84,8 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_native_streaming": true }, "gpt-4.1-2025-04-14": { "max_tokens": 32768, @@ -106,7 +107,100 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": 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, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 762984dec9..09217ee04a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -84,7 +84,8 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_native_streaming": true }, "gpt-4.1-2025-04-14": { "max_tokens": 32768, @@ -106,7 +107,100 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": 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,