# 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.**
[](https://www.npmjs.com/package/9router)
[](https://www.npmjs.com/package/9router)
[](https://hub.docker.com/r/decolua/9router)
[](https://github.com/decolua/9router/pkgs/container/9router)
[](https://github.com/decolua/9router/blob/main/LICENSE)
[🚀 Quick Start](#-quick-start) • [💡 Features](#-key-features) • [📖 Setup](#-setup-guide) • [🌐 Website](https://9router.com)
[🇻🇳 Tiếng Việt](./i18n/README.vi.md) • [🇨🇳 中文](./i18n/README.zh-CN.md) • [🇯🇵 日本語](./i18n/README.ja-JP.md) • [🇷🇺 Русский](./i18n/README.ru.md) • [🇹🇭 ไทย](./i18n/README.th.md) • [🇮🇷 فارسی](./i18n/README.fa_IR.md) • [🇮🇩 Indonesia](./i18n/README.id-ID.md)
---
## 🤔 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:**
```bash
npm install 9router
9router
```
🎉 Dashboard opens at `http://localhost:20128`
**2. Connect a FREE provider (no signup needed):**
Dashboard → Providers → Connect **Kiro AI** (~50 credits/month free: Claude 4.5 + GLM-5 + MiniMax) 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.
**Alternative: run from source (this repository):**
This repository package is private (`9router-app`), so source/Docker execution is the expected local development path.
```bash
cp .env.example .env
npm install
PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
```
Production mode:
```bash
npm run build
PORT=20128 HOSTNAME=0.0.0.0 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run start
```
Default URLs:
- Dashboard: `http://localhost:20128/dashboard`
- OpenAI-compatible API: `http://localhost:20128/v1`
---
## Video Guides
### 🏠 Self-hosted Providers
For speech and embeddings served from **your own** machine — whisper.cpp,
faster-whisper, Speaches, Kokoro-FastAPI, openedai-speech, llama.cpp/llama-server,
vLLM, Infinity, text-embeddings-inference, or anything else that speaks the OpenAI
shape.
| Provider | Endpoint used | Typical server |
| --- | --- | --- |
| **Self-hosted STT** | `/v1/audio/transcriptions` | whisper.cpp, faster-whisper |
| **Self-hosted TTS** | `/v1/audio/speech` | Kokoro-FastAPI, openedai-speech |
| **Self-hosted Embedding** | `/v1/embeddings` | llama-server, vLLM, Infinity |
Every other speech provider is a named cloud service with a fixed endpoint. These
three read their address from **each connection**, so one provider can front
several machines and load-balance across them like any other.
Set it on the connection as `providerSpecificData.baseUrl`:
| Provider | Give it | Result |
| --- | --- | --- |
| Self-hosted STT | the full URL — `http://host:8080/v1/audio/transcriptions` | used as-is |
| Self-hosted TTS | the server root — `http://host:8880` | `+ /v1/audio/speech` |
| Self-hosted Embedding | the **OpenAI base**, `/v1` included — `http://host:8080/v1` | `+ /embeddings` |
> **Mind the `/v1` on embeddings.** The adapter appends `/embeddings`, so
> `http://host:8080` resolves to `http://host:8080/embeddings` and misses the
> OpenAI route — llama-server answers **501**. Give it the same base URL an OpenAI
> client would use. A full `.../v1/embeddings` is also accepted, so a value pasted
> from a `curl` example works too.
The API key is not checked by most local servers, but the field must be non-empty:
it is what gives the connection a credentials record, and `baseUrl` lives there.
Any placeholder works.
Self-hosted Embedding has **no cloud fallback by design** — a connection saved
without a `baseUrl` is reported as a configuration error rather than quietly
falling back to `api.openai.com`, which would send your input text and API key to
a third party under a provider named "Self-hosted".
---
## 💡 Key Features
| Feature | What It Does | Why It Matters |
| --------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | ------------------------------------------------- |
| 🚀 **RTK Token Saver** ([RTK](https://github.com/rtk-ai/rtk) ⭐40K) | Compress tool outputs (`git diff`, `grep`, `ls`, `tree`...) before sending to LLM | Save **20-40% input tokens** per request |
| 🧠 **Headroom Token Saver** ([Headroom](https://github.com/chopratejas/headroom)) | Optional external `/v1/compress` proxy before provider routing | Save more context tokens without changing clients |
| 🪨 **Caveman Mode** ([Caveman](https://github.com/JuliusBrussee/caveman) ⭐52K) | Inject caveman-speak prompt → LLM replies terse, technical substance preserved | Save **up to 65% output tokens** |
| 🐴 **Ponytail** ([Ponytail](https://github.com/DietrichGebert/ponytail)) | Inject "lazy senior dev" prompt → LLM writes minimal, YAGNI-first code (Lite/Full/Ultra) | **Fewer output tokens, less refactoring** |
| 🎯 **Smart 3-Tier Fallback** | Auto-route: Subscription → Cheap → Free | Never stop coding, zero downtime |
| 📊 **Real-Time Quota Tracking** | Live token count + reset countdown | Maximize subscription value |
| 🔄 **Format Translation** | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro ↔ Vertex | Works with any CLI tool |
| 👥 **Multi-Account Support** | Multiple accounts per provider | Load balancing + redundancy |
| 🔄 **Auto Token Refresh** | OAuth tokens refresh automatically | No manual re-login needed |
| 🎨 **Custom Combos** | Create unlimited model combinations | Tailor fallback to your needs |
| 📝 **Request Logging** | Debug mode with full request/response logs | Troubleshoot issues easily |
| 💾 **Cloud Sync** | Sync config across devices | Same setup everywhere |
| 📊 **Usage Analytics** | Track tokens, cost, trends over time | Optimize spending |
| 🌐 **Deploy Anywhere** | Localhost, VPS, Docker, Cloudflare Workers | Flexible deployment options |
Set `X-9Router-Token-Saver: off` to bypass all token savers for one chat request.
