From b0e61152da2267606e55a5cc8c7dbb91a2fdc917 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Sat, 22 Mar 2025 16:58:48 -0700 Subject: [PATCH 1/3] fix model cost map --- ...odel_prices_and_context_window_backup.json | 60 +++++++++++-------- model_prices_and_context_window.json | 60 +++++++++++-------- 2 files changed, 72 insertions(+), 48 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 330fe890e4a..61f2703f55a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -80,32 +80,38 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.030, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.050 + } }, "gpt-4o-search-preview-2025-03-11": { "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.000010, - "input_cost_per_token_batches": 0.00000125, - "output_cost_per_token_batches": 0.00000500, - "cache_read_input_token_cost": 0.00000125, - "litellm_provider": "openai", - "mode": "chat", - "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_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.030, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.050 - } + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.000010, + "input_cost_per_token_batches": 0.00000125, + "output_cost_per_token_batches": 0.00000500, + "cache_read_input_token_cost": 0.00000125, + "litellm_provider": "openai", + "mode": "chat", + "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_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.030, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.050 + } }, "gpt-4o-search-preview": { "max_tokens": 16384, @@ -255,7 +261,13 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275, + "search_context_size_high": 0.030 + } }, "gpt-4o-mini-search-preview-2025-03-11":{ "max_tokens": 16384, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 330fe890e4a..61f2703f55a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -80,32 +80,38 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.030, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.050 + } }, "gpt-4o-search-preview-2025-03-11": { "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.000010, - "input_cost_per_token_batches": 0.00000125, - "output_cost_per_token_batches": 0.00000500, - "cache_read_input_token_cost": 0.00000125, - "litellm_provider": "openai", - "mode": "chat", - "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_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.030, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.050 - } + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.000010, + "input_cost_per_token_batches": 0.00000125, + "output_cost_per_token_batches": 0.00000500, + "cache_read_input_token_cost": 0.00000125, + "litellm_provider": "openai", + "mode": "chat", + "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_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.030, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.050 + } }, "gpt-4o-search-preview": { "max_tokens": 16384, @@ -255,7 +261,13 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275, + "search_context_size_high": 0.030 + } }, "gpt-4o-mini-search-preview-2025-03-11":{ "max_tokens": 16384, From 54208357ccd9833b60b7673dec2955dadd6ff426 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Sat, 22 Mar 2025 18:14:19 -0700 Subject: [PATCH 2/3] docs clarify /mcp endpoint readiness on litellm --- docs/my-website/docs/mcp.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/docs/my-website/docs/mcp.md b/docs/my-website/docs/mcp.md index 6ebbd7a1fa3..0706b9adea6 100644 --- a/docs/my-website/docs/mcp.md +++ b/docs/my-website/docs/mcp.md @@ -274,6 +274,13 @@ async with stdio_client(server_params) as (read, write): ## Advanced +:::info + +**This feature is not live as yet** this is a beta interface. Expect this to be live on litellm `v1.63.15` and above. + +::: + + ### Expose MCP tools on LiteLLM Proxy Server This allows you to define tools that can be called by any MCP compatible client. Define your mcp_tools with LiteLLM and all your clients can list and call available tools. From cdd6002b8961486e10af9c1334bf70cca11c6849 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Sat, 22 Mar 2025 18:18:47 -0700 Subject: [PATCH 3/3] docs - update this to upcoming features --- docs/my-website/docs/mcp.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/my-website/docs/mcp.md b/docs/my-website/docs/mcp.md index 0706b9adea6..9f3343e9cd3 100644 --- a/docs/my-website/docs/mcp.md +++ b/docs/my-website/docs/mcp.md @@ -272,7 +272,7 @@ async with stdio_client(server_params) as (read, write): -## Advanced +## Upcoming Features :::info