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.
Latest release v0.3.7 · 26 Oct 2026
2 files for Codex, OpenCode and Claude Code: xrouter-llm AGENTS.md, xrouter-llm CLAUDE.md — 6,964 tokens loaded in every session.
AGENTS.md A 6,961 tok CLAUDE.md A 3 tok These files are xorbitsai/xrouter-llm's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.