A router that picks the cheapest capable model per request — and the engineers explaining why it costs more (github.com)
The tool is a drop-in proxy across Anthropic, OpenAI, Gemini and open models, scoring each request and routing accordingly, keys encrypted, fully self-hostable. The claim is 40–70% lower cost “with just an endpoint change.”
The objection is structural: agentic sessions live on prompt caching with a five-minute TTL, and the more distinct models you touch, the more cache misses you eat — so a one-planner, one-executor setup already captures the win without the churn.
Sign in to save