🔗
OpenRouter
Model Aggregation AI Models & RoutingInstall Command
npx clawhub@latest install openrouter
Installation Guide
1
Check Environment
Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.
2
Run Installation
Run the install command above in your terminal. ClawHub will automatically download and install OpenRouter to the ~/.openclaw/skills/ directory.
3
Verify Installation
Run openclaw skills list to check your installed skills and confirm OpenRouter appears in the list.
4
Configure (Optional)
Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.
Manual Installation: Copy the Skill folder to
~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
200+ Models
Unified Interface
Pay-Per-Use
Detailed Description
The OpenRouter skill lets OpenClaw access over 200 AI models through the OpenRouter platform with a single unified configuration, eliminating the need to configure each provider separately.
Core Features
- Unified Access: One API Key for Claude, GPT-4, Gemini, Llama, Mixtral, and more
- Model Switching: Switch between different models at any time to pick the best fit
- Pay-Per-Use: Pay by token usage with no monthly fees or prepayment required
- Model Comparison: Send the same question to multiple models and compare answer quality
- Auto Fallback: Automatically switch to alternative models when one is unavailable
Configuration
{
skills: {
openrouter: {
apiKey: "sk-or-xxx",
defaultModel: "anthropic/claude-sonnet-4",
fallbackModel: "google/gemini-pro"
}
}
}
Use Cases
- Quickly try and compare different AI model capabilities
- For users who don't want to register with multiple AI providers separately
- Rapid model switching during development and testing
- As a model provider source for ClawRouter