OpenRouter Setup
Get your OpenRouter API key to power N8N Insider's AI features.
What is OpenRouter?
OpenRouter is a unified API that gives you access to multiple AI models from various providers (OpenAI, Anthropic, Google, and more) through a single API key. N8N Insider uses OpenRouter to power its AI features.
Step 1: Create an OpenRouter Account
- Go to openrouter.ai
- Click "Sign In" or "Sign Up"
- Create an account using Google, GitHub, or email
Step 2: Add Credits (Optional for Free Tier)
OpenRouter offers some free models, but for the best experience with models like GPT-4 or Claude, you'll need to add credits:
- Go to your OpenRouter dashboard
- Click "Credits" in the sidebar
- Add credits via credit card or crypto
Tip: Start with $5-10 to test. Most AI requests cost fractions of a cent.
Step 3: Generate an API Key
- In your OpenRouter dashboard, click "Keys" in the sidebar
- Click "Create Key"
- Give your key a name (e.g., "N8N Insider")
- Copy the generated API key immediately - you won't see it again!
Important!
Copy your API key and store it securely. OpenRouter only shows the full key once. If you lose it, you'll need to create a new one.
Step 4: Add Key to N8N Insider
- Click the N8N Insider icon in your Chrome toolbar
- Open Settings (gear icon)
- Find the "OpenRouter API Key" field
- Paste your API key
- Click "Save" or "Test Connection"
Connected!
If you see a success message, your API key is working. You can now use N8N Insider's AI features.
Choosing AI Models
N8N Insider supports multiple AI models through OpenRouter. Here are our recommendations:
Claude 3.5 Sonnet (Recommended)
Best overall for code understanding and workflow help. Great balance of speed and quality.
GPT-4o
Excellent for complex reasoning and detailed explanations.
Claude 3 Haiku
Fastest and cheapest. Good for quick questions and simple tasks.
Troubleshooting
"Invalid API Key" error
Make sure you copied the entire key including the "sk-or-" prefix.
"Insufficient credits" error
Add more credits to your OpenRouter account or try a free model.
"Rate limited" error
Wait a moment and try again. You may be making too many requests too quickly.