9router - Unlimited FREE AI coding.

[robi]

9Router - FREE AI Router & Token Saver

Never stop coding. Save 20-40% tokens with RTK + auto-fallback to FREE & cheap AI models.

Connect All AI Code Tools (Claude Code, Cursor, Antigravity, Copilot, Codex, Gemini, OpenCode, Cline, OpenClaw...) to 40+ AI Providers & 100+ Models.

Quick Start • Features • Setup • Website

Tiếng Việt • 中文 • 日本語 • Русский

---

Why 9Router?

Stop wasting money, tokens and hitting limits:

• Subscription quota expires unused every month
• Rate limits stop you mid-coding
• Tool outputs (git diff, grep, ls...) burn tokens fast
• Expensive APIs ($20-50/month per provider)
• Manual switching between providers

9Router solves this:

• RTK Token Saver - Auto-compress tool_result content, save 20-40% tokens per request
• Maximize subscriptions - Track quota, use every bit before reset
• Auto fallback - Subscription → Cheap → Free, zero downtime
• Multi-account - Round-robin between accounts per provider
• Universal - Works with Claude Code, Codex, Cursor, Cline, any CLI tool

---

How It Works

┌─────────────┐
│  Your CLI   │  (Claude Code, Codex, OpenClaw, Cursor, Cline...)
│   Tool      │
└──────┬──────┘
       │ http://localhost:20128/v1
       ↓
┌─────────────────────────────────────────────┐
│           9Router (Smart Router)            │
│  • RTK Token Saver (cut tool_result tokens) │
│  • Format translation (OpenAI ↔ Claude)     │
│  • Quota tracking                           │
│  • Auto token refresh                       │
└──────┬──────────────────────────────────────┘
       │
       ├─→ [Tier 1: SUBSCRIPTION] Claude Code, Codex, GitHub Copilot
       │   ↓ quota exhausted
       ├─→ [Tier 2: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
       │   ↓ budget limit
       └─→ [Tier 3: FREE] Kiro, OpenCode Free, Vertex ($300 credits)

Result: Never stop coding, minimal cost + 20-40% token savings via RTK

---

Quick Start

1. Install globally:

npm install -g 9router
9router

Dashboard opens at http://localhost:20128

2. Connect a FREE provider (no signup needed):

Dashboard → Providers → Connect Kiro AI (free Claude unlimited) or OpenCode Free (no auth) → Done!

3. Use in your CLI tool:

Claude Code/Codex/OpenClaw/Cursor/Cline Settings:
  Endpoint: http://localhost:20128/v1
  API Key: [copy from dashboard]
  Model: kr/claude-sonnet-4.5

That's it! Start coding with FREE AI models.

[robi]

Cloudron package ready for testing!

The Cloudron community package is now available for installation and feedback.

Installation:

1. Add the custom versions URL in your Cloudron App Store:
   https://raw.githubusercontent.com/vRobM/9router-cloudron/main/CloudronVersions.json

2. Or install from CLI:
   cloudron install --location 9router --versions-url https://raw.githubusercontent.com/vRobM/9router-cloudron/main/CloudronVersions.json

What's included:

• 9Router v0.5.20 (latest upstream)
• better-sqlite3 for persistent data
• SQLite storage at /app/data/db/data.sqlite
• Auto-ping scheduler for provider health
• Healthcheck on port 20128

Post-install:
Open https://<your-app-domain>/ — default password is 123456 (change it immediately, or it may ask you to do it).

Known notes:

• Requires Cloudron box version 9.1.0+ (for icon support)
• First build takes ~15 minutes on-server (compiling native modules)
• Data persists across updates via Cloudron's localstorage addon
  Repo: https://github.com/vRobM/9router-cloudron

Feedback welcome — bugs, feature requests, or just let me know if it works for you.

UPDATE v0.2.0:

• OIDC
• MITM server for additional free models

[joseph]

Beautiful. Trying to understand - is this a replacement for OpenWebUI and librechat?

[luckow]

@joseph Nope. This is your LLM proxy for all models and providers/companies. Instead of adding a bunch of endpoints to OpenWebUI, LibreChat, or any other app that lets you specify an OpenAI-compatible endpoint, you just link to one proxy. There are plenty of alternatives out there, but 9router looks really interesting in terms of features.

New kid on the block: https://otari.ai/

[marcusquinn]

@robi you looked at the fork? https://github.com/diegosouzapw/OmniRoute

[robi]

@marcusquinn wow no, that's even more bang for the buck.

Want to sponsor me to package it?

[marcusquinn]

@robi i'd just run it locally

[timconsidine]

@marcusquinn said:

i'd just run it locally

Yes, it's the fastest initially to understand the app. And if most usage is on e.g. your dev device, then having Omniroute locally works well.

I think 'core' omniroute functions can be packaged for Cloudron, but some of the more advanced/sophisticated features may prove complex.