locallama-mcp
27
LocaLLama MCP Server is designed to optimize coding task efficiency by dynamically routing them between local and paid AI APIs. It features cost and token monitoring, a decision engine, and a configurable API interface. The server supports integration with various models and includes tools for robust error handling and performance benchmarking.
clear_openrouter_tracking
Clear OpenRouter tracking data and force update
benchmark_free_models
Performance benchmarking of OpenRouter's free model
get_free_models
Search free model list from OpenRouter