ypollak2/llm-router
by Various
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain keeps costs 70–85% lower.
MCP
ypollak2/llm-router
Added 1 June 2026
Overview
LLM Router is a Python-based tool that routes requests from AI coding assistants such as Claude Code, Cursor, and Copilot to different language models. It uses a free-first fallback chain that prioritizes cost-free options, reducing overall API costs by 70–85%.
Best for
Best for
Developers using multiple AI coding assistants who want to minimize API costs.
Use cases
- Directing coding queries to the cheapest available LLM
- Fallback routing when the primary model is unavailable or rate-limited
- Unifying multiple AI coding tools under a single routing layer
Notes
LLM Router is a Python-based tool that routes requests from AI coding assistants such as Claude Code, Cursor, and Copilot to different language models. It uses a free-first fallback chain that prioritizes cost-free options, reducing overall API costs by 70–85%.
27 stars on GitHub. Last updated 2026-06-01. Licensed MIT.
Use cases
- Directing coding queries to the cheapest available LLM
- Fallback routing when the primary model is unavailable or rate-limited
- Unifying multiple AI coding tools under a single routing layer
Pros
- Significant cost reduction with free-first fallback chain
- Compatible with a wide range of popular AI coding tools
- Open source and easy to integrate into existing workflows
Cons
- Low GitHub star count indicates limited community adoption and testing
- Requires manual configuration of fallback chains and API keys
- Performance depends on the availability and speed of free LLM endpoints
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Significant cost reduction with free-first fallback chain
- Compatible with a wide range of popular AI coding tools
- Open source and easy to integrate into existing workflows
Cons
- Low GitHub star count indicates limited community adoption and testing
- Requires manual configuration of fallback chains and API keys
- Performance depends on the availability and speed of free LLM endpoints
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Cursor
Anysphere
The AI-first code editor. Tab to autocomplete, Composer to multi-file refactor, Agents for the long-running stuff.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Cursor
Anysphere
The AI-first code editor. Tab to autocomplete, Composer to multi-file refactor, Agents for the long-running stuff.