llm-router
llm-router is an MCP server, listed under model apis. Its repository has 119 GitHub stars and is licensed under MIT; we last read it on 2026-10-25.
llm-router routes AI coding tool requests to compatible LLMs including Claude Code, Cursor, Codex, Gemini CLI, Copilot, and others. It uses a free-first fallback chain to reduce costs by 35-80%.
Install
Read from llm-router’s own README, close to verbatim -- not written by us, and not guessed.
pip install llm-routing
What it reaches, and what it needs
What it connects to
Unverified means a mention in the server’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.
Maintenance
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
What llm-router can do
3 tools documented in its README. An AI client calls these by name.
status- No description in the README.
gain- No description in the README.
doctor- No description in the README.
Read from the README; names are kept only if the README contains them.
llm-router compared with similar servers
| Server | Reaches | Needs | Stars | Last update | Licence |
|---|---|---|---|---|---|
| llm-router (this page) | — | None listed | 119 | 2026-10-25 | MIT |
| wigolo | gemini, wigolo | GEMINI_API_KEY, WIGOLO_API_TOKEN, WIGOLO_GITHUB_TOKEN | 5,498 | 2026-10-22 | NOASSERTION |
| KiCAD-MCP-Server | — | None listed | 2,905 | 2026-10-01 | MIT |
| modelcontextprotocol | perplexity | PERPLEXITY_API_KEY | 2,589 | 2026-10-21 | MIT |
| paperbanana | atlascloud, google, openai | ATLASCLOUD_API_KEY, GOOGLE_API_KEY, OPENAI_API_KEY | 2,412 | 2026-09-17 | MIT |
| gemini-mcp-tool | — | None listed | 2,294 | 2026-07-21 | NOASSERTION |
Ranked by services in common with llm-router, then by stars. Figures are from each repository when we last read it.
Common questions about llm-router
- What does llm-router do?
- llm-router routes AI coding tool requests to compatible LLMs including Claude Code, Cursor, Codex, Gemini CLI, Copilot, and others. It uses a free-first fallback chain to reduce costs by 35-80%.
- How do I install llm-router?
- Its own README gives this command: pip install llm-routing. Run it where your MCP client can launch the server, and check the README for any settings it asks for.
- Which AI clients can use llm-router?
- Its own description mentions Claude Code, Cursor and Gemini CLI. That is a mention in its description, not a test we ran.
- Is llm-router official and is it maintained?
- We found nothing naming it as a vendor’s official server. Its repository has 119 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-25.
- What licence does llm-router use?
- The repository declares the MIT licence.
More MCP servers for model apis
- wigolo5,498 stars
- KiCAD-MCP-Server2,905 stars
- modelcontextprotocol2,589 stars
- paperbanana2,412 stars
- gemini-mcp-tool2,294 stars
- telegram-mcp1,879 stars