### Example: Connect iFlow

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Specific steps to connect iFlow.

```text
1. Click "Connect iFlow"
2. Login with iFlow account
3. Authorize
4. ✅ Done! Use 8 models: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, etc.
```

--------------------------------

### API Key Format Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/zh-CN/getting-started/installation.md

Example format of an API key.

```text
9r_1234567890abcdef1234567890abcdef
```

--------------------------------

### Cost Optimization Strategy Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

A real-world example of optimizing costs for 100M tokens per month using a combination of free, subscription, cheap, and emergency models.

```text
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
```

--------------------------------

### Start 9Router (Local)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Command to start 9Router after local installation using npx.

```bash
npx 9router
```

--------------------------------

### MiniMax M2.1 Setup: Get API Key

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

Steps to get an API key from MiniMax.

```bash
Dashboard 				→ API Management 				→ Create Key
				→ Copy API key
```

--------------------------------

### Example: Connect GLM-4.7

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Specific steps to connect GLM-4.7 using an API key.

```text
1. Sign up at [Zhipu AI](https://open.bigmodel.cn/)
2. Get API key from Coding Plan
3. Dashboard → Add API Key → Provider: `glm` → Paste key
4. ✅ Done! Use model: `glm/glm-4.7`
```

--------------------------------

### Installation and Start

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/index.md

Commands to install 9Router globally using npm and start the service, which automatically opens a dashboard.

```bash
# Install globally
npm install -g 9router

# Start (dashboard opens automatically)
9router
```

--------------------------------

### Example: Connect Claude Code

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Specific steps to connect Claude Code using OAuth.

```text
1. Click "Connect Claude Code"
2. Login with your Claude account
3. Authorize 9Router
4. ✅ Done! Use model: `cc/claude-opus-4-5-20251101`
```

--------------------------------

### Kimi K2 Setup - Step 4: Use in CLI

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Example CLI command to specify the Kimi model.

```bash
Model: kimi/kimi-latest
```

--------------------------------

### Kimi K2 Setup: Get API Key

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

Steps to get an API key from Moonshot AI for Kimi.

```bash
Dashboard 				→ API Keys 				→ Create New
				→ Copy API key
```

--------------------------------

### MiniMax M2.1 Setup - Step 4: Use in CLI

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Example CLI command to specify the MiniMax model.

```bash
Model: minimax/MiniMax-M2.1
```

--------------------------------

### Example 1: Student/Learner (Zero Budget)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/es/providers/free.md

Configuration and cost breakdown for a zero-budget setup ideal for students.

```text
Configuración:
1. kr/claude-sonnet-4.5 (Mejor calidad)
2. if/kimi-k2-thinking (Razonamiento complejo)
3. qw/qwen3-coder-plus (Codificación rápida)

Costo mensual: $0
Uso: Ilimitado

Perfecto para:
- Aprender a programar
- Proyectos personales
- Tareas/asignaciones
```

--------------------------------

### VPS/Cloud Server Installation and Configuration

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Install, configure environment variables, and start 9router on a server using PM2.

```bash
# Install
npm install -g 9router

# Configure
export JWT_SECRET="your-secure-secret"
export INITIAL_PASSWORD="your-password"
export NODE_ENV="production"

# Start with PM2
npm install -g pm2
pm2 start 9router --name 9router
pm2 save
pm2 startup
```

--------------------------------

### Deploy to VPS

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/faq.md

Steps to clone the repository, install dependencies, build the project, and start the application on a VPS.

```bash
git clone https://github.com/decolua/9router.git
cd 9router/app
npm install && npm run build
npm start
```

--------------------------------

### Install 9Router Globally

Source: https://github.com/decolua/9router/blob/master/README.md

Install the 9Router CLI tool globally using npm. After installation, simply run '9router' to start the dashboard.

```bash
npm install -g 9router
9router
```

--------------------------------

### MiniMax M2.1 Setup - Step 2: Get API Key

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Instructions to obtain an API key from the MiniMax dashboard.

```bash
Dashboard → API Management → Create Key
→ Copy API key
```

--------------------------------

### Headroom Proxy Setup

Source: https://github.com/decolua/9router/blob/master/README.md

Provides instructions for setting up the Headroom proxy for token saving. This involves installing the library and running the proxy service.

```bash
pip install "headroom-ai[proxy]"
headroom proxy --port 8787
```

--------------------------------

### GLM-4.7 Setup: Get API Key

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

Steps to get an API key from Zhipu AI.

```bash
Dashboard 				→ API Keys 				→ Create New
				→ Copy API key (starts with "zhipu-")
```

--------------------------------

### Installation from Source

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Steps to clone the repository, build, and run 9Router from source.

```bash
git clone https://github.com/decolua/9router.git
cd 9router/app
npm install
npm run build
npm start
```

--------------------------------

### Environment Variables for Configuration

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Example environment variables for configuring 9Router, including security, storage, server, and logging settings.

```bash
# Security (REQUIRED in production)
export JWT_SECRET="your-secure-secret-change-this"
export INITIAL_PASSWORD="your-password"

# Storage
export DATA_DIR="~/.9router"

# Server
export PORT="20128"
export NODE_ENV="production"

# Logging
export ENABLE_REQUEST_LOGS="false"
```

--------------------------------

### Setup PM2 Startup Script

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/cloud.md

Configures PM2 to start automatically when the system boots.

```bash
pm2 startup
```

--------------------------------

### GLM-4.7 Setup - Step 4: Use in CLI

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Example CLI commands to specify GLM models.

```bash
Model: glm/glm-4.7
       glm/glm-4.6v (vision)
```

--------------------------------

### Kimi K2 Setup - Step 2: Get API Key

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Instructions to obtain an API key from the Moonshot AI dashboard.

```bash
Dashboard → API Keys → Create New
→ Copy API key
```

--------------------------------

### Restart Server (Manual)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Commands to stop and start the 9router server manually.

```bash
# Stop
pkill -f 9router

# Start
9router
```

--------------------------------

### Run 9Router from Source (Development)

Source: https://github.com/decolua/9router/blob/master/README.md

Set up and run 9Router locally from its source code for development. This involves copying the environment file, installing dependencies, and starting the development server.

```bash
cp .env.example .env
npm install
PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
```

--------------------------------

### Real-World Example: Freelancer (Budget-Conscious)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/free.md

Recommended AI model setup for freelancers balancing cost and performance, utilizing free tiers and cheap backups.

```yaml
Setup:
1. gc/gemini-3-flash-preview (FREE 180K/month)
2. glm/glm-4.7 (Cheap backup, $0.6/1M)
3. if/kimi-k2-thinking (FREE fallback)

Monthly cost: $5-10
Usage: 100M+ tokens

Perfect for:
- Client projects (paid tier)
- Testing (free tier)
- Emergency backup
```

--------------------------------

### Kimi K2 Quota Reset Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

An example illustrating the monthly token refresh for Kimi.

```bash
Monthly reset: 1st of each month
				→ 10M tokens refresh

Example monthly usage:
Week 1: 3M tokens
Week 2: 2M tokens
Week 3: 3M tokens
Week 4: 2M tokens
Total: 10M tokens = $9 flat
```

--------------------------------

### Setup SSL with Let's Encrypt

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/cloud.md

Commands to install Certbot, obtain an SSL certificate, and test auto-renewal.

```bash
# Install certbot
sudo apt install certbot python3-certbot-nginx

# Obtain SSL certificate
sudo certbot --nginx -d your-domain.com

# Auto-renewal is configured automatically
# Test renewal
sudo certbot renew --dry-run
```

--------------------------------

### GLM-4.7 Setup - Step 2: Get API Key

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Instructions to obtain an API key from the Zhipu AI dashboard.

```bash
Dashboard → API Keys → Create New
→ Copy API key (starts with "zhipu-")
```

--------------------------------

### Connect Free Providers

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Steps to connect free providers like iFlow, Qwen, and Kiro using Device code or OAuth.

```text
Dashboard → Providers → Connect [Free Provider]
→ Device code or OAuth
→ Unlimited usage
```

--------------------------------

### Configuration Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/integration/cline.md

An example of how the Cline settings should appear after configuration.

```text
API Provider: Ollama
Base URL: http://localhost:20128/v1
API Key: sk-9router-xxxxxxxxxxxxx
Model: gpt-4
```

--------------------------------

### Real-World Example: Heavy User (Maximize Everything)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/free.md

Recommended AI model setup for heavy users aiming to maximize performance and features by combining free, subscription, and cheap tiers.

```yaml
Setup:
1. gc/gemini-3-flash-preview (FREE 180K/month)
2. cc/claude-opus-4-5 (Subscription $20-100)
3. cx/gpt-5.2-codex (Subscription $20-200)
4. glm/glm-4.7 (Cheap $0.6/1M)
5. minimax/MiniMax-M2.1 (Cheapest $0.2/1M)
6. if/kimi-k2-thinking (FREE unlimited)
7. kr/claude-sonnet-4.5 (FREE quality)

Monthly cost: $40-320 (subscriptions) + $10-20 (cheap tier)
Usage: 500M+ tokens

Perfect for:
- Professional development
- Team projects
- 24/7 coding
```

--------------------------------

### Combo Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/es/features/combos.md

Example of a custom combo configuration.

```text
Combo Name: premium-coding
Models:
  1. cc/claude-opus-4-5-20251101 (try first)
  2. glm/glm-4.7 (if #1 is out of quota)
  3. minimax/MiniMax-M2.1 (if #2 is out of quota)
```

--------------------------------

### Real-World Example: Student/Learner (Zero Budget)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/free.md

Recommended AI model setup for students or learners with a zero budget, focusing on free, high-quality models.

```yaml
Setup:
1. kr/claude-sonnet-4.5 (Best quality)
2. if/kimi-k2-thinking (Complex reasoning)
3. qw/qwen3-coder-plus (Fast coding)

Monthly cost: $0
Usage: Unlimited

Perfect for:
- Learning to code
- Personal projects
- Homework/assignments
```

--------------------------------

### Start Application

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/cloud.md

Starts the 9Router application.

```bash
npm run start
```

--------------------------------

### Local Development Installation

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Install and run 9router locally for development.

```bash
npm install -g 9router
9router
```

--------------------------------

### Create Combo Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/subscription.md

Example of creating a new combo with multiple models.

```bash
Dashboard → Combos → Create New

Name: premium-coding
Models:
  1. gc/gemini-3-flash-preview (FREE, use first)
  2. cc/claude-opus-4-5-20251101 (Subscription)
  3. cx/gpt-5.2-codex (Subscription backup)

Use in CLI: premium-coding
```

--------------------------------

### 9router VPS Deployment

Source: https://github.com/decolua/9router/blob/master/README.md

Steps to clone, install, configure, and start the 9router application on a Virtual Private Server (VPS). Essential environment variables are provided for production deployment.

```bash
# Clone and install
git clone https://github.com/decolua/9router.git
cd 9router
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 PORT="20128"
export HOSTNAME="0.0.0.0"
export NODE_ENV="production"
export NEXT_PUBLIC_BASE_URL="http://localhost:20128"
export NEXT_PUBLIC_CLOUD_URL="https://9router.com"
export API_KEY_SECRET="endpoint-proxy-api-key-secret"
export MACHINE_ID_SALT="endpoint-proxy-salt"

# Start
npm run start

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

--------------------------------

### Local Installation

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Steps to install 9Router locally within a project directory.

```bash
mkdir my-9router
cd my-9router
npm install 9router
```

--------------------------------

### Install Nginx

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/cloud.md

Installs the Nginx web server on Ubuntu.

```bash
sudo apt update
sudo apt install nginx
```

--------------------------------

### Cursor Settings Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/integration/cursor.md

An example of how the Cursor IDE settings should look after configuring 9Router integration.

```text
OpenAI API: ✓ Enabled
Base URL: https://9router.com
API Key: sk-9router-xxxxxxxxxxxxx
Custom Models: gpt-4, claude-opus-4-5, gemini-2.0-flash
```

--------------------------------

### Troubleshooting Application Start Issues

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/cloud.md

Commands to troubleshoot why the application might not be starting, including checking logs, ports, and environment variables.

```bash
# Check logs
pm2 logs 9router

# Check if ports are in use
sudo lsof -i :3000
sudo lsof -i :20128

# Check environment variables
pm2 env 9router
```

--------------------------------

### MiniMax M2.1 Quota Reset Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

An example illustrating the 5-hour rolling quota reset for MiniMax.

```bash
5-hour rolling window:
				→ Use quota 				→ Wait 5 hours 				→ Fresh quota

Example:
10:00 AM - Use 5M tokens
3:00 PM - Fresh quota available
8:00 PM - Fresh quota available
```

--------------------------------

### Install and run 9Router via npm

Source: https://github.com/decolua/9router/blob/master/cli/README.md

Instructions for installing the 9Router CLI globally using npm and running it, including an alternative using npx.

```bash
npm install -g 9router
9router

# Or run directly with npx
npx 9router
```

--------------------------------

### Creating a Combination

Source: https://github.com/decolua/9router/blob/master/gitbook/content/zh-CN/providers/cheap.md

Example of setting up a 'cheap-backup' combination in 9Router.

```bash
Dashboard → Combinations → New

Name: cheap-backup
Models:
  1. cc/claude-opus-4-5 (Primary Subscription)
  2. glm/glm-4.7 (Low-cost fallback, daily reset)
  3. minimax/MiniMax-M2.1 (Cheapest fallback)
  4. if/kimi-k2-thinking (Free emergency)

Usage in CLI: cheap-backup
```

--------------------------------

### Check Node.js and npm Versions

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Commands to verify that the installed Node.js and npm versions meet the requirements.

```bash
node --version
# Should show v20.x.x or higher

npm --version
# Should show 10.x.x or higher
```

--------------------------------

### Run 9Router in Production Mode

Source: https://github.com/decolua/9router/blob/master/README.md

Build and start 9Router in production mode. This includes building the application and then starting the production server with specified ports and base URL.

```bash
npm run build
PORT=20128 HOSTNAME=0.0.0.0 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run start
```

--------------------------------

### Troubleshooting: Permission Denied

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Instructions to fix npm permissions to resolve permission denied errors during global installation.

```bash
# Fix npm permissions (recommended)
mkdir ~/.npm-global
npm config set prefix '~/.npm-global'
echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.bashrc
source ~/.bashrc

# Then install again
npm install -g 9router
```

--------------------------------

### Update 9Router via Local Install

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/faq.md

Steps to update 9Router when it was installed locally, involving pulling the latest changes, installing dependencies, building, and starting.

```bash
cd 9router/app
git pull origin main
npm install
npm run build
npm start
```

--------------------------------

### Best Practice: Create Smart Combos

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/subscription.md

Example of a smart combo configuration.

```bash
Example combo:
1. gc/gemini-3-flash-preview (FREE primary)
2. cc/claude-opus-4-5 (Complex tasks)
3. glm/glm-4.7 (Cheap backup)
4. if/kimi-k2-thinking (FREE fallback)
```

--------------------------------

### Configure Claude Desktop

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Configuration for Claude Desktop to use 9Router.

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

--------------------------------

### Configure Codex CLI

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Environment variables to set for Codex CLI to use 9Router.

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

codex "your prompt"
```

--------------------------------

### Configure Cline / Continue / RooCode

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Settings for Cline, Continue, or RooCode to use 9Router.

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

--------------------------------

### Create Smart Combos

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Steps to create a smart combo for automatic fallback between models in the dashboard.

```text
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. if/kimi-k2-thinking (Free fallback)

Use in CLI: premium-coding
```

--------------------------------

### Kimi K2 Setup - Step 3: Add to 9Router

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Configuration to add the Kimi provider API key to 9Router.

```bash
9router
# Dashboard → Providers → Add API Key

Provider: kimi
API Key: your-kimi-api-key
```

--------------------------------

### Configure Cursor IDE

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Settings for Cursor IDE to use 9Router as an OpenAI compatible endpoint.

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

--------------------------------

### Setup

Source: https://github.com/decolua/9router/blob/master/tests/README.md

Vitest must be installed globally or in /tmp/node_modules (due to npm workspace hoisting from the root Next.js project).

```bash
cd /tmp && npm install vitest
```

--------------------------------

### Create a Combo (Recommended)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Example of creating a 'combo' in 9Router to chain multiple providers for fallback.

```bash
Dashboard → Combos → Create New

Name: cheap-backup
Models:
  1. cc/claude-opus-4-5 (prefer subscription)
  2. glm/glm-4.7 (low-cost backup, daily reset)
  3. minimax/MiniMax-M2.1 (cheapest fallback)
  4. if/kimi-k2-thinking (free emergency)

Use in CLI: cheap-backup
```

--------------------------------

### 9router Docker Quick Start

Source: https://github.com/decolua/9router/blob/master/README.md

Run the 9router application using a pre-built Docker image. This command sets up a container with persistent data storage and exposes the default port.

```bash
docker run -d \
  --name 9router \
  -p 20128:20128 \
  -v "$HOME/.9router:/app/data" \
  -e DATA_DIR=/app/data \
  decolua/9router:latest
```

--------------------------------

### Example 2: Budget Combo Configuration

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/features/combos.md

Configuration details for the 'budget-combo'.

```text
Dashboard → Combos → Create New

Name: budget-combo
Models:
  1. glm/glm-4.7
  2. minimax/MiniMax-M2.1
  3. if/kimi-k2-thinking
```

--------------------------------

### Example 3: Freelancer (Variable Usage)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

Cost examples for a freelancer with variable monthly LLM usage, showing calculations for light and heavy months.

```text
Light month (20M tokens):
- 15M via subscription: $0
- 5M via GLM: $3
Total: $3

Heavy month (150M tokens):
- 60M via subscription: $0
- 60M via GLM: $36
- 30M via MiniMax: $6
Total: $42

Average: $22.50/month
vs $3400 on ChatGPT API!
```

--------------------------------

### Minimize Costs

Source: https://github.com/decolua/9router/blob/master/gitbook/content/es/features/combos.md

Example combo starting with the cheapest paid option and falling back to even cheaper or free models.

```text
glm/glm-4.7 → minimax/MiniMax-M2.1 → if/kimi-k2-thinking

→ Start with the cheapest paid option ($0.60/1M)
→ Fallback to an even cheaper one ($0.20/1M)
→ Free emergency tier
→ Total cost: ~$5-10/month vs $2000 on ChatGPT API
```

--------------------------------

### Kimi K2 Setup: Add to 9Router

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

How to add the Kimi provider API key to 9Router.

```bash
9router
# Dashboard 				→ Providers 				→ Add API Key

Provider: kimi
API Key: your-kimi-api-key
```

--------------------------------

### Minimize Costs Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/features/combos.md

A combo strategy to start with the cheapest paid models and fall back to free tiers.

```text
glm/glm-4.7 → minimax/MiniMax-M2.1 → if/kimi-k2-thinking

→ Start with cheapest paid option ($0.60/1M)
→ Fallback to even cheaper ($0.20/1M)
→ Emergency free tier
→ Total cost: ~$5-10/month vs $2000 on ChatGPT API
```

--------------------------------

### List Models API Request

Source: https://github.com/decolua/9router/blob/master/README.md

Example of how to make a GET request to the models endpoint to retrieve a list of available models. The response is in OpenAI format.

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

→ Returns all models + combos in OpenAI format
```

--------------------------------

### Best Practice 3: Combine with Free Tier

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

Setting up a model combo that prioritizes free tiers for cost minimization and uptime maximization.

```text
Combo:
1. gc/gemini-3-flash (FREE primary)
2. glm/glm-4.7 (cheap backup)
3. minimax/MiniMax-M2.1 (cheapest)
4. if/kimi-k2-thinking (FREE emergency)

Result: Minimize costs, maximize uptime
```

--------------------------------

### Cost Optimization Strategy 2: Budget Prioritization

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

An example of allocating a monthly budget across different providers to maximize token usage.

```bash
Monthly Budget Setup: $20

Allocation:
- $9 Kimi K2 (10M tokens fixed)
- $6 GLM daily quota (10M tokens)
- $5 MiniMax overflow (25M tokens)

Total: 45M tokens for $20
vs 1M tokens for $20 with ChatGPT API!
```

--------------------------------

### Create a Combo (Recommended)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/free.md

Example of creating a combo with multiple free providers for redundancy and quality.

```bash
Dashboard → Combos → Create New

Name: free-combo
Models:
  1. if/kimi-k2-thinking (iFlowプライマリ)
  2. qw/qwen3-coder-plus (Qwenバックアップ)
  3. kr/claude-sonnet-4.5 (Kiro品質)

CLIで使用: free-combo
```

--------------------------------

### Daily Quota Reset Strategy

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

A daily routine for managing different AI model quotas to ensure continuous usage with minimal cost.

```text
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!
```

--------------------------------

### Example 2: Budget Coder ($10/month)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

A cost breakdown for a budget-conscious user spending $10 per month on LLM tokens.

```text
Strategy:
- $9 Kimi K2 (10M tokens)
- $1 MiniMax overflow (5M tokens)

Total: 15M tokens for $10
vs 0.5M tokens for $10 on ChatGPT API!

30× more tokens!
```

--------------------------------

### MiniMax M2.1 Setup - Step 3: Add to 9Router

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Configuration to add the MiniMax provider API key to 9Router.

```bash
9router
# Dashboard → Providers → Add API Key

Provider: minimax
API Key: your-minimax-api-key
```

--------------------------------

### Connect Providers via API Key

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Steps to connect providers like GLM, MiniMax, Kimi, and OpenRouter by adding an API key through the dashboard.

```text
Dashboard → Providers → Add API Key
→ Select provider
→ Paste API key
→ Save
```

--------------------------------

### MiniMax M2.1 Setup: Add to 9Router

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

How to add the MiniMax provider API key to 9Router.

```bash
9router
# Dashboard 				→ Providers 				→ Add API Key

Provider: minimax
API Key: your-minimax-api-key
```

--------------------------------

### Connect Providers via OAuth

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/quick-start.md

Steps to connect subscription providers like Claude Code, Codex, Gemini CLI, and GitHub Copilot using OAuth through the dashboard.

```text
Dashboard → Providers → Connect [Provider]
→ OAuth login → Auto token refresh
→ Quota tracking enabled
```

--------------------------------

### Cursor IDE Setup

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

Configuration for Cursor IDE to use a local 9router instance for model access.

```text
Settings 
Models 
Advanced:
  OpenAI API Base URL: http://localhost:20128/v1
  OpenAI API Key: [from 9router dashboard]
  Model: glm/glm-4.7
```

--------------------------------

### Example 1: Heavy Coding Month (100M tokens)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

A real-world example of cost breakdown for a heavy coding month using a mix of subscription and cheap providers.

```text
Breakdown:
- 60M via subscription (Claude/Codex): $0 extra
- 30M via GLM-4.7: $18
- 10M via MiniMax M2.1: $2

Total: $20/month
vs $2000 on ChatGPT API!

Savings: 99% cheaper!
```

--------------------------------

### Remove Global Installation

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Command to uninstall the globally installed 9router package.

```bash
npm uninstall -g 9router
```

--------------------------------

### Environment Variables Setup

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/integration/other-tools.md

Demonstrates how to store API keys and base URLs in a .env file for secure credential management.

```bash
# .env file
ROUTER_API_KEY=your-api-key-from-dashboard
ROUTER_BASE_URL=http://localhost:20128/v1
ROUTER_MODEL=cc/claude-sonnet-4-20250514
```

--------------------------------

### Kimi K2 API Key Setup

Source: https://github.com/decolua/9router/blob/master/gitbook/content/zh-CN/providers/cheap.md

Steps to obtain and add the Kimi K2 API Key to 9Router.

```bash
Dashboard → API Keys → Create New Key
→ Copy API key
```

```bash
9router
# Dashboard → Providers → Add API Key

Provider: kimi
API Key: your-kimi-api-key
```

--------------------------------

### Create Combo (Recommended)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/cheap.md

Example of creating a model combo in the 9router dashboard for tiered fallback strategies.

```text
Dashboard 
Combos 
Create New

Name: cheap-backup
Models:
  1. cc/claude-opus-4-5 (Subscription primary)
  2. glm/glm-4.7 (Cheap backup, daily reset)
  3. minimax/MiniMax-M2.1 (Cheapest fallback)
  4. if/kimi-k2-thinking (FREE emergency)

Use in CLI: cheap-backup
```

--------------------------------

### Cursor IDE Setup

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/providers/free.md

Configuration for using free providers with Cursor IDE.

```yaml
Settings → Models → Advanced:
  OpenAI API Base URL: http://localhost:20128/v1
  OpenAI API Key: [from 9router dashboard]
  Model: if/kimi-k2-thinking
```

--------------------------------

### Install Dependencies

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/cloud.md

Installs the necessary Node.js dependencies for the application.

```bash
npm install
```

--------------------------------

### Verify key format

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/troubleshooting.md

Example of correct and incorrect API key formats.

```text
Correct: 9r_xxxxxxxxxxxxxxxxxxxxxxxx
Wrong: Missing 9r_ prefix
```

--------------------------------

### Tavily Example

Source: https://github.com/decolua/9router/blob/master/skills/9router-web-fetch/SKILL.md

Example of fetching content using Tavily.

```bash
curl -X POST $NINEROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tavily","url":"https://example.com","format":"markdown","max_characters":0}'
```

--------------------------------

### Firecrawl Example

Source: https://github.com/decolua/9router/blob/master/skills/9router-web-fetch/SKILL.md

Example of fetching content using Firecrawl.

```bash
curl -X POST $NINEROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"firecrawl","url":"https://example.com","format":"markdown","max_characters":0}'
```

--------------------------------

### Exa Example

Source: https://github.com/decolua/9router/blob/master/skills/9router-web-fetch/SKILL.md

Example of fetching content using Exa.

```bash
curl -X POST $NINEROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"exa","url":"https://example.com","format":"markdown","max_characters":0}'
```

--------------------------------

### MiniMax M2.1 API Key Setup

Source: https://github.com/decolua/9router/blob/master/gitbook/content/zh-CN/providers/cheap.md

Steps to obtain and add the MiniMax M2.1 API Key to 9Router.

```bash
Dashboard → API Management → Create Key
→ Copy API key
```

```bash
9router
# Dashboard → Providers → Add API Key

Provider: minimax
API Key: your-minimax-api-key
```

--------------------------------

### Complex Reasoning Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/integration/roo.md

Example of a complex reasoning query.

```text
Ask Roo: "Analyze the trade-offs between microservices and monolithic architecture"
Model: cx/deepseek-reasoner
```

--------------------------------

### Code Generation Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/integration/roo.md

Example of a code generation query.

```text
Ask Roo: "Write a Python function to calculate Fibonacci numbers"
Model: cx/deepseek-chat
```

--------------------------------

### Basic Chat Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/integration/roo.md

Example of a basic chat query.

```text
Ask Roo: "Explain quantum computing in simple terms"
Model: cc/claude-sonnet-4-20250514
```

--------------------------------

### Best Practice: Create Multiple Combos

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/features/combos.md

Examples of combo names for different use cases.

```text
premium-coding: For complex tasks
budget-combo: For simple tasks
free-combo: For experimentation
quality-first: For production code
```

--------------------------------

### Settings File Example

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/integration/claude-code.md

Example of the Claude Code settings.json file.

```json
{
  "baseUrl": "http://localhost:20128/v1",
  "defaultModel": "sonnet"
}
```

--------------------------------

### Restart Server (PM2)

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/getting-started/installation.md

Commands to install PM2 and manage the 9router process for auto-restart.

```bash
npm install -g pm2
pm2 start 9router --name 9router
pm2 save
```

--------------------------------

### Install PM2

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/cloud.md

Installs PM2, a process manager for Node.js applications, globally.

```bash
npm install -g pm2
```

--------------------------------

### Cursor IDE Setup

Source: https://github.com/decolua/9router/blob/master/gitbook/content/ja/providers/cheap.md

Configuration for Cursor IDE to use 9Router providers.

```yaml
Settings → Models → Advanced:
  OpenAI API Base URL: http://localhost:20128/v1
  OpenAI API Key: [Get from 9router dashboard]
  Model: glm/glm-4.7
```

--------------------------------

### Install 9Router globally

Source: https://github.com/decolua/9router/blob/master/gitbook/content/en/deployment/localhost.md

Installs the 9Router application globally using npm.

```bash
npm install -g 9router
```