NadirRouter/NadirClaw

Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

50
/ 100
Established

This tool helps developers and teams using Large Language Models (LLMs) to automatically optimize their API costs. It intelligently routes simple prompts to cheaper, local models and complex prompts to premium models, saving 40-70% on AI expenses. You feed it your existing LLM requests, and it automatically manages which model handles them, providing cost savings and usage reports.

368 stars.

Use this if you are a developer, product manager, or engineering leader looking to significantly reduce the cost of your AI API calls without sacrificing performance on complex tasks.

Not ideal if you are not currently using LLMs, or if you only use open-source models that incur no API costs.

LLM-cost-optimization AI-API-management developer-tooling backend-engineering resource-management
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 18 / 25

How are scores calculated?

Stars

368

Forks

46

Language

Python

License

MIT

Last pushed

Mar 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/NadirRouter/NadirClaw"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.