A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.
Instructions file CodexOpenCode
AGENTS.md instructions for xorbitsai/xrouter-llm, covering xrouter-llm agent notes, routing objective, current data strategy, benchmark profiles and model registry (hand-authored yaml).
Instructions file
Claude Code instructions for xorbitsai/xrouter-llm, a project described as: A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.