Intelligent LLM router that reduces AI API costs by up to 60% through smart model selection and caching. FastAPI service with multi-provider support (Gemini, Claude, OpenRouter) and Claude Desktop MCP integration.
python api caching machine-learning ai mcp gemini claude cost-optimization multi-provider fastapi llm cost-reduction openrouter api-optimization claude-desktop intelligent-routing model-routing ai-router prompt-routing
-
Updated
Nov 25, 2025 - Python