9Router - FREE AI Coding + Cheap Backups

9Router - FREE AI Coding + Cheap Backups

Use Claude, Codex, Gemini for FREE • Ultra-cheap alternatives from $0.20/1M tokens

🚀 Quick Start • 💰 Pricing • 📖 Setup • 🌐 Website

Why 9Router?

Stop wasting your AI subscriptions and paying full price:

❌ Subscription quota expires unused every month
❌ Rate limits stop you mid-coding
❌ Expensive APIs ($20-50/month per provider)
❌ Manual switching between providers

9Router maximizes value:

✅ Maximize Subscriptions - Claude Code, Codex, Gemini, Copilot quota tracking
✅ FREE Available - iFlow, Qwen, Kiro when needed, via CLI
✅ Ultra-Cheap Backup - GLM ($0.6/1M), MiniMax M2.1 ($0.20/1M)
✅ Smart Fallback - Subscription → Cheap → Free, automatic switching

⚡ Quick Start

Install globally:

npm install -g 9router
9router

🎉 Dashboard opens → Connect Claude Code → Start coding!

Use in Cursor/Cline:

Endpoint: http://localhost:20128/v1
API Key: [from dashboard]
Model: cc/claude-opus-4-5-20251101

💰 Pricing Strategy

📅 MAXIMIZE SUBSCRIPTIONS (Primary)

Already paying? Get full value with quota tracking:

Provider	What You Get	Quota Reset	Monthly Cost
Claude Code (Pro/Max)	Claude 4.5 Opus/Sonnet/Haiku	5-hour + Weekly	$20-100
OpenAI Codex (Plus/Pro)	GPT 5.2 Codex, GPT 5.1 Codex Max	5-hour + Weekly	$20-200
Gemini CLI (FREE tier!)	180K completions/month, 1K/day	Daily/Monthly	$0
GitHub Copilot	GPT-5, Claude 4.5, Gemini 3	Monthly (1st)	$10-19
Antigravity (Google)	Gemini 3 Pro, Claude Sonnet 4.5	Similar to Gemini	$0

Value: Use every bit of your subscription quota before it resets!

💰 ULTRA CHEAP (Backup)

When subscription quota runs out, pay pennies:

Provider	Pricing (per 1M tokens)	Quota Reset	Cost for 10M
GLM-4.7	$0.60 input / $2.20 output	Daily 10:00 AM	~$6-22
MiniMax M2.1	$0.20 input / $1.00 output	5-hour rolling	~$2-10
Kimi K2	$9/month (10M tokens)	Monthly	$9 flat

Value: ~90% cheaper than ChatGPT API ($20/1M)!

🆓 FREE FOREVER (Fallback)

No API key needed, unlimited:

Provider	Top Models	Notes
iFlow	Kimi K2, Qwen3 Coder Plus, GLM 4.7, MiniMax M2	8 models via OAuth
Qwen	Qwen3 Coder Plus/Flash, Vision	3 models via OAuth
Kiro	Claude Sonnet 4.5, Haiku 4.5	AWS Builder ID

Value: Emergency backup when everything else is quota-limited!

✨ Key Features

🔄 Smart 3-Tier Fallback

Setup once, never stop coding:

Tier 1 (SUBSCRIPTION): Claude Code → Codex → Gemini
  ↓ quota exhausted
Tier 2 (CHEAP): GLM-4.7 → MiniMax M2.1 → Kimi
  ↓ budget limit
Tier 3 (FREE): iFlow → Qwen → Kiro

→ Automatic switching, zero downtime!

📊 Quota Tracking

Real-time token consumption
Reset countdown per provider
Cost estimation (paid tiers)
Monthly spending reports

🎯 Universal CLI Support

✅ Cursor • Cline • Claude Desktop • Codex • RooCode • Continue • Any tool with custom OpenAI endpoint

🌐 Deploy Options

💻 Localhost • ☁️ VPS/Cloud • 🐳 Docker • 🚀 Cloudflare Workers

📖 Setup Guide

Subscription Providers (Maximize Value)

Claude Code (Pro/Max)

Dashboard → Providers → Connect Claude Code
→ OAuth login → Auto token refresh
→ 5-hour + weekly quota tracking

Use: cc/claude-opus-4-5-20251101
     cc/claude-sonnet-4-5-20250929

Pro Tip: Use Opus for complex tasks, Sonnet for speed. 9Router tracks quota per model!

OpenAI Codex (Plus/Pro)

Dashboard → Providers → Connect Codex
→ OAuth login (port 1455)
→ 5-hour + weekly reset

Use: cx/gpt-5.2-codex
     cx/gpt-5.1-codex-max

Gemini CLI (FREE 180K/month!)

Dashboard → Providers → Connect Gemini CLI
→ Google OAuth
→ 180K completions/month + 1K/day

Use: gc/gemini-3-flash-preview
     gc/gemini-2.5-pro

Best Value: Huge free tier! Use this before paid tiers.

GitHub Copilot

Dashboard → Providers → Connect GitHub
→ OAuth via GitHub
→ Monthly reset (1st of month)

Use: gh/gpt-5
     gh/claude-4.5-sonnet

Cheap Providers (Backup)

GLM-4.7 (Daily reset, $0.6/1M)

Sign up: Zhipu AI
Get API key from Coding Plan
Dashboard → Add API Key:
- Provider: glm
- API Key: your-key

Use: glm/glm-4.7

Pro Tip: Coding Plan offers 3× quota at 1/7 cost! Reset daily 10:00 AM.

MiniMax M2.1 (5h reset, $0.20/1M)

Sign up: MiniMax
Get API key
Dashboard → Add API Key:
- Provider: minimax
- API Key: your-key

Use: minimax/MiniMax-M2.1

Pro Tip: 5-hour rolling window. Cheapest option for long context (1M tokens)!

Kimi K2 ($9/month flat)

Subscribe: Moonshot AI
Get API key
Dashboard → Add API Key:
- Provider: kimi
- API Key: your-key

Use: kimi/kimi-latest

Pro Tip: Fixed $9/month for 10M tokens = $0.90/1M effective cost!

FREE Providers (Emergency Backup)

iFlow (8 FREE models)

Dashboard → Connect iFlow
→ iFlow OAuth login
→ Unlimited usage

Use: if/kimi-k2-thinking
     if/qwen3-coder-plus
     if/glm-4.7
     if/minimax-m2

Qwen (3 FREE models)

Dashboard → Connect Qwen
→ Device code authorization
→ Unlimited usage

Use: qw/qwen3-coder-plus
     qw/qwen3-coder-flash

Kiro (Claude FREE)

Dashboard → Connect Kiro
→ AWS Builder ID or Google/GitHub
→ Unlimited usage

Use: kr/claude-sonnet-4.5
     kr/claude-haiku-4.5

Combo Examples

Example 1: Maximize Subscription → Cheap Backup

Dashboard → Combos → Create New

Name: premium-coding
Models:
  1. cc/claude-opus-4-5-20251101 (Subscription primary)
  2. glm/glm-4.7 (Cheap backup, $0.6/1M)
  3. minimax/MiniMax-M2.1 (Cheapest fallback, $0.20/1M)

Use in CLI: premium-coding

Monthly cost example (100M tokens):
  80M via Claude (subscription): $0 extra
  15M via GLM: $9
  5M via MiniMax: $1
  Total: $10 + your subscription

Example 2: Budget-First with Free Fallback

Name: budget-combo
Models:
  1. glm/glm-4.7 (Daily quota, cheap)
  2. minimax/MiniMax-M2.1 (5h quota, cheapest)
  3. if/kimi-k2-thinking (FREE unlimited)

Monthly cost (100M tokens):
  70M via GLM: $42
  20M via MiniMax: $4
  10M via iFlow: $0
  Total: ~$46 vs $2000 on ChatGPT API!

Example 3: Free-Only (Zero Cost)

Name: free-combo
Models:
  1. if/kimi-k2-thinking
  2. qw/qwen3-coder-plus
  3. kr/claude-sonnet-4.5

Cost: $0 forever!

CLI Integration

Cursor IDE

Settings → Models → Advanced:
  OpenAI API Base URL: http://localhost:20128/v1
  OpenAI API Key: [from 9router dashboard]
  Model: cc/claude-opus-4-5-20251101

Or use combo: premium-coding

Claude Desktop (Claude Code)

Edit ~/.claude/config.json:

{
  "anthropic_api_base": "http://localhost:20128/v1",
  "anthropic_api_key": "your-9router-api-key"
}

Models: cc/claude-opus-4-5, glm/glm-4.7, or combo name

Codex CLI

export OPENAI_BASE_URL="http://localhost:20128"
export OPENAI_API_KEY="your-9router-api-key"

codex "your prompt"

Models: cx/gpt-5.2-codex, glm/glm-4.7, or combo

Cline / Continue / RooCode

Provider: OpenAI Compatible
Base URL: http://localhost:20128/v1
API Key: [from dashboard]
Model: cc/claude-opus-4-5-20251101

Deployment

VPS Deployment

# Clone and install
git clone https://github.com/decolua/9router.git
cd 9router/app
npm install
npm run build

# Configure
export JWT_SECRET="your-secure-secret-change-this"
export INITIAL_PASSWORD="your-password"
export DATA_DIR="/var/lib/9router"
export NODE_ENV="production"

# Start
npm run start

# Or use PM2
npm install -g pm2
pm2 start npm --name 9router -- start
pm2 save
pm2 startup

Docker

docker build -t 9router .
docker run -d \
  -p 3000:3000 \
  -e JWT_SECRET="your-secure-secret" \
  -e INITIAL_PASSWORD="your-password" \
  -v 9router-data:/app/data \
  9router

Environment Variables

Variable	Default	Description
`JWT_SECRET`	Auto-generated	MUST change in production!
`DATA_DIR`	`~/.9router`	Database storage path
`INITIAL_PASSWORD`	`123456`	Dashboard login password
`NODE_ENV`	`development`	Set to `production` for deploy
`ENABLE_REQUEST_LOGS`	`false`	Debug request/response logs

Reverse Proxy (Nginx)

server {
    listen 80;
    server_name your-domain.com;

    location / {
        proxy_pass http://localhost:3000;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection 'upgrade';
        proxy_set_header Host $host;
        
        # SSE support
        proxy_buffering off;
        proxy_read_timeout 86400;
    }
}

💡 Cost Optimization Tips

Monthly Budget: $10-20/month

Strategy:
1. Use Gemini CLI free tier (180K/month) for quick tasks
2. Use Claude Code subscription quota fully (you already pay)
3. Fallback to GLM ($0.6/1M) when quota out
4. Emergency: MiniMax M2.1 ($0.20/1M) or iFlow (free)

Real example (100M tokens/month):
  60M via Gemini CLI: $0 (free tier)
  30M via Claude Code: $0 (subscription you already have)
  8M via GLM: $4.80
  2M via MiniMax: $0.40
  Total: $5.20/month + existing subscriptions

Quota Reset Strategy

Daily routine:
1. Morning: Fresh Claude Code quota (5h reset)
2. Afternoon: Switch to Gemini CLI (1K/day)
3. Evening: GLM daily quota (reset 10AM next day)
4. Late night: MiniMax (5h rolling) or iFlow (free)

→ Code 24/7 with minimal extra cost!

Model Selection Guide

Task	Best Model	Cost	Why
Complex reasoning	`cc/claude-opus-4-5`	Subscription	Best quality
Fast coding	`cx/gpt-5.2-codex`	Subscription	Fastest Codex
Budget coding	`glm/glm-4.7`	$0.6/1M	Daily quota
Long context	`minimax/MiniMax-M2.1`	$0.20/1M	1M context cheap
Emergency backup	`if/kimi-k2-thinking`	FREE	Unlimited

📊 Available Models

Subscription Models (Maximize First)

Claude Code (cc/) - Pro/Max:

cc/claude-opus-4-5-20251101 - Claude 4.5 Opus
cc/claude-sonnet-4-5-20250929 - Claude 4.5 Sonnet
cc/claude-haiku-4-5-20251001 - Claude 4.5 Haiku

Codex (cx/) - Plus/Pro:

cx/gpt-5.2-codex - GPT 5.2 Codex
cx/gpt-5.2 - GPT 5.2
cx/gpt-5.1-codex-max - GPT 5.1 Codex Max
cx/gpt-5.1-codex - GPT 5.1 Codex

Gemini CLI (gc/) - FREE 180K/month:

gc/gemini-3-flash-preview - Gemini 3 Flash Preview
gc/gemini-3-pro-preview - Gemini 3 Pro Preview
gc/gemini-2.5-pro - Gemini 2.5 Pro
gc/gemini-2.5-flash - Gemini 2.5 Flash

GitHub Copilot (gh/) - Subscription:

gh/gpt-5 - GPT-5
gh/gpt-5.1-codex-max - GPT-5.1 Codex Max
gh/claude-4.5-sonnet - Claude 4.5 Sonnet
gh/gemini-3-pro - Gemini 3 Pro

Antigravity (ag/) - Google account:

ag/gemini-3-pro-high - Gemini 3 Pro High
ag/claude-sonnet-4-5 - Claude Sonnet 4.5
ag/claude-opus-4-5-thinking - Claude Opus 4.5

Cheap Models (Backup)

GLM (glm/) - $0.6/$2.2 per 1M:

glm/glm-4.7 - GLM 4.7 (daily reset 10AM)
glm/glm-4.6v - GLM 4.6V Vision

MiniMax (minimax/) - $0.20/$1.00 per 1M:

minimax/MiniMax-M2.1 - MiniMax M2.1 (5h reset)

Kimi (kimi/) - $9/month (10M tokens):

kimi/kimi-latest - Kimi Latest

OpenRouter (openrouter/) - Passthrough pricing:

openrouter/auto - Auto (Best Available)
Any OpenRouter model ID supported

FREE Models (Emergency)

iFlow (if/) - 8 models FREE:

if/kimi-k2-thinking - Kimi K2 Thinking
if/kimi-k2 - Kimi K2
if/qwen3-coder-plus - Qwen3 Coder Plus
if/glm-4.7 - GLM 4.7
if/minimax-m2 - MiniMax M2
if/deepseek-r1 - DeepSeek R1
if/deepseek-v3.2-chat - DeepSeek V3.2 Chat
if/deepseek-v3.2-reasoner - DeepSeek V3.2 Reasoner

Qwen (qw/) - 3 models FREE:

qw/qwen3-coder-plus - Qwen3 Coder Plus
qw/qwen3-coder-flash - Qwen3 Coder Flash
qw/vision-model - Qwen3 Vision

Kiro (kr/) - 2 models FREE:

kr/claude-sonnet-4.5 - Claude Sonnet 4.5
kr/claude-haiku-4.5 - Claude Haiku 4.5

🐛 Troubleshooting

"Language model did not provide messages"

Provider quota exhausted → Check dashboard quota tracker
Solution: Use combo fallback or switch to cheaper tier

Rate limiting

Subscription quota out → Fallback to GLM/MiniMax
Add combo: cc/claude-opus → glm/glm-4.7 → minimax/MiniMax-M2.1

OAuth token expired

Auto-refreshed by 9Router
If issues persist: Dashboard → Provider → Reconnect

High costs

Check usage stats in Dashboard
Switch primary model to GLM/MiniMax
Use free tier (Gemini CLI, iFlow) for non-critical tasks

🛠️ Tech Stack

Runtime: Node.js 20+
Framework: Next.js 15
UI: React 19 + Tailwind CSS 4
Database: LowDB (JSON file-based)
Streaming: Server-Sent Events (SSE)
Auth: OAuth 2.0 (PKCE) + JWT + API Keys

📝 API Reference

Chat Completions

POST http://localhost:20128/v1/chat/completions
Authorization: Bearer your-api-key
Content-Type: application/json

{
  "model": "cc/claude-opus-4-5-20251101",
  "messages": [
    {"role": "user", "content": "Write a function to..."}
  ],
  "stream": true
}

List Models

GET http://localhost:20128/v1/models
Authorization: Bearer your-api-key

→ Returns all models + combos in OpenAI format

Responses API (Codex)

POST http://localhost:20128/v1/responses
POST http://localhost:20128/codex/responses

🤝 Contributing

Fork → Branch → Commit → Push → PR
See CONTRIBUTING.md

📧 Support

Website: 9router.com
GitHub: github.com/decolua/9router
Issues: github.com/decolua/9router/issues

🙏 Acknowledgments

Special thanks to CLIProxyAPI - the original Go implementation that inspired this JavaScript port.

📄 License

MIT License - see LICENSE for details.

_{Built with ❤️ for developers maximizing AI value}

Name		Name	Last commit message	Last commit date
Latest commit History 62 Commits
.vscode		.vscode
images		images
open-sse		open-sse
public		public
src		src
tester/translator		tester/translator
.gitignore		.gitignore
.npmignore		.npmignore
CHANGELOG.md		CHANGELOG.md
README.md		README.md
eslint.config.mjs		eslint.config.mjs
jsconfig.json		jsconfig.json
next.config.mjs		next.config.mjs
package.json		package.json
postcss.config.mjs		postcss.config.mjs

decolua/9router

Folders and files

Latest commit

History

Repository files navigation

9Router - FREE AI Coding + Cheap Backups

Why 9Router?

⚡ Quick Start

💰 Pricing Strategy

📅 MAXIMIZE SUBSCRIPTIONS (Primary)

💰 ULTRA CHEAP (Backup)

🆓 FREE FOREVER (Fallback)

✨ Key Features

🔄 Smart 3-Tier Fallback

📊 Quota Tracking

🎯 Universal CLI Support

🌐 Deploy Options

📖 Setup Guide

Claude Code (Pro/Max)

OpenAI Codex (Plus/Pro)

Gemini CLI (FREE 180K/month!)

GitHub Copilot

GLM-4.7 (Daily reset, $0.6/1M)

MiniMax M2.1 (5h reset, $0.20/1M)

Kimi K2 ($9/month flat)

iFlow (8 FREE models)

Qwen (3 FREE models)

Kiro (Claude FREE)

Example 1: Maximize Subscription → Cheap Backup

Example 2: Budget-First with Free Fallback

Example 3: Free-Only (Zero Cost)

Cursor IDE

Claude Desktop (Claude Code)

Codex CLI

Cline / Continue / RooCode

VPS Deployment

Docker

Environment Variables

Reverse Proxy (Nginx)

💡 Cost Optimization Tips

Monthly Budget: $10-20/month

Quota Reset Strategy

Model Selection Guide

📊 Available Models

🐛 Troubleshooting

🛠️ Tech Stack

📝 API Reference

Chat Completions

List Models

Responses API (Codex)

🤝 Contributing

📧 Support

🙏 Acknowledgments

📄 License

About

Topics

Resources

Uh oh!

Stars

Watchers

Forks

Releases 5

Packages 0

Contributors 3

Languages

Packages