AcademyResourcesDevelopment

llm-router

Engineering teams that want to keep their Claude subscription quota for the harder coding work.

  • Recommendedour rating
  • 96repository stars
  • MITlicence
  • todaylast update
git clone https://github.com/ypollak2/llm-router.git
README.md

Loading the file...

What it does

llm-router runs locally next to Claude Code, Codex and Gemini CLI. It reads each prompt and sends it to the cheapest model that can handle it, compresses tokens, and falls back to another provider when one fails. Routed answers are advisory by default, so Claude still takes the turn unless you change the setting.

Use cases

  1. 01Send simple questions to a free or local model
  2. 02Fall back to another provider when one is unavailable
  3. 03Reduce token use in long coding sessions

Questions about
llm-router.

What is llm-router used for?

Engineering teams that want to keep their Claude subscription quota for the harder coding work. llm-router runs locally next to Claude Code, Codex and Gemini CLI. It reads each prompt and sends it to the cheapest model that can handle it, compresses tokens, and falls back to another provider when one fails. Routed answers are advisory by default, so Claude still takes the turn unless you change the setting.

How do I install llm-router?

Run this in your terminal: git clone https://github.com/ypollak2/llm-router.git

Is llm-router open source?

Yes. The code is on GitHub (ypollak2/llm-router) under the MIT licence.

Is llm-router safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.