Skip to main content
Glama

LLM Gateway MCP Server

empirically_measured_model_speeds.json2.89 kB
{ "claude-3-5-haiku-20241022": { "total_time_s": 9.66, "output_tokens": 452, "output_tokens_per_second": 46.79 }, "claude-3-7-sonnet-20250219": { "total_time_s": 8.907, "output_tokens": 469, "output_tokens_per_second": 52.66 }, "claude-3-opus-20240229": { "total_time_s": 20.186, "output_tokens": 583, "output_tokens_per_second": 28.88 }, "claude-3-sonnet-20240229": { "total_time_s": 9.072, "output_tokens": 518, "output_tokens_per_second": 57.1 }, "deepseek-chat": { "total_time_s": 21.641, "output_tokens": 442, "output_tokens_per_second": 20.42 }, "deepseek-reasoner": { "total_time_s": 39.793, "output_tokens": 1097, "output_tokens_per_second": 27.57 }, "gemini-2.0-flash": { "total_time_s": 2.59, "output_tokens": 488, "output_tokens_per_second": 188.44 }, "gemini-2.0-flash-lite": { "total_time_s": 2.93, "output_tokens": 467, "output_tokens_per_second": 159.4 }, "gemini-2.0-flash-thinking-exp-01-21": { "total_time_s": 6.103, "output_tokens": 460, "output_tokens_per_second": 75.37 }, "gemini-2.5-pro-preview-03-25": { "total_time_s": 18.481, "output_tokens": 593, "output_tokens_per_second": 32.09 }, "gpt-4.1": { "total_time_s": 8.908, "output_tokens": 441, "output_tokens_per_second": 49.51 }, "gpt-4.1-mini": { "total_time_s": 6.184, "output_tokens": 506, "output_tokens_per_second": 81.82 }, "gpt-4.1-nano": { "total_time_s": 3.315, "output_tokens": 434, "output_tokens_per_second": 130.92 }, "gpt-4o": { "total_time_s": 10.358, "output_tokens": 446, "output_tokens_per_second": 43.06 }, "gpt-4o-mini": { "total_time_s": 6.086, "output_tokens": 416, "output_tokens_per_second": 68.36 }, "grok-3-fast-latest": { "total_time_s": 5.915, "output_tokens": 396, "output_tokens_per_second": 66.95 }, "grok-3-latest": { "total_time_s": 13.587, "output_tokens": 396, "output_tokens_per_second": 29.15 }, "grok-3-mini-fast-latest": { "total_time_s": 6.382, "output_tokens": 345, "output_tokens_per_second": 54.06 }, "grok-3-mini-latest": { "total_time_s": 9.32, "output_tokens": 366, "output_tokens_per_second": 39.27 }, "o1-preview": { "total_time_s": 19.538, "output_tokens": 1394, "output_tokens_per_second": 71.35 }, "o3-mini": { "total_time_s": 5.416, "output_tokens": 395, "output_tokens_per_second": 72.93 } }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Dicklesworthstone/llm_gateway_mcp_server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server