OpenRouter

WatchThatSite integrates with OpenRouter's API, providing access to dozens of AI models through a single interface.

Get Your API Key

1. Go to OpenRouter
2. Click Sign In and create account or log in
3. Go to API Keys
4. Click Create New Key
5. Name it (e.g., "WatchThatSite")
6. Set credit limit if desired
7. Click Create Key
8. Copy immediately (won't be shown again)

Add to WatchThatSite

1. Go to Settings > AI Providers
2. Click Add Provider Key
3. Select OpenRouter from the provider dropdown
4. Paste your API key
5. Optionally select specific models
6. Click Save

Recommended Models

Latest models with tool calling via OpenRouter:

• GPT-4o (OpenAI) — Latest multimodal
• Claude 3.5 Sonnet (Anthropic) — Latest, fast + capable
• Mixtral 8x7B (Mistral) — Open-source balance
• Llama 3.1 70B (Meta) — Large open model
• Grok-2 (xAI) — Advanced reasoning

Plus 100+ additional models from 20+ providers.

All Available Models

Your account has access to all OpenRouter models supporting tool calling:

1. Go to Settings > AI Providers
2. Click Add Provider Key or Edit existing
3. Models dropdown shows all available models
4. Select specific models to restrict, or leave empty for all

Browse all models on OpenRouter's model catalog.

Key Features

• Multi-provider access: Single API for many models
• Model comparison: Easy A/B testing between models
• Fallback routing: Automatic failover if model unavailable
• Usage tracking: Monitor spend per model
• Flexible pricing: Transparent per-token pricing

Pricing

OpenRouter uses per-token pricing:

• Input tokens: Price varies by model
• Output tokens: Price varies by model (typically higher)
• Routing fee: Small overhead when using fallback routing
• Free tier: Available with rate limits

Check OpenRouter pricing for exact rates per model.

Benefits

• Cost optimization: Compare models and pick best value
• Reliability: Automatic fallback to alternative models
• Flexibility: Switch models without code changes
• Easier migration: Compare providers side-by-side
• Consolidated billing: Single invoice for all models

Account Setup

Set Credit Limit

1. Go to Settings
2. Set Daily Credit Limit to control spending
3. Optionally set usage alerts

Check Usage

1. Go to Dashboard
2. View API usage and costs
3. Filter by model, date range, status
4. Download detailed usage reports

Model Selection Tips

• Fast responses: Use smaller models (Mistral, Llama 7B)
• Complex reasoning: Use larger models (Claude, GPT-4)
• Cost-effective: Mixtral 8x7B offers good balance
• Cutting edge: GPT-4o and Claude 3.5 Sonnet
• Cost per token: Compare on pricing page

Troubleshooting

"Invalid API Key"

• Verify complete key is pasted without spaces
• Ensure key hasn't been revoked
• Check key is active in OpenRouter account
• Regenerate if needed

"Model Not Found"

• Verify model ID is correct (use exact name from list)
• Check OpenRouter models for availability
• Some models may be in beta or region-restricted
• Model IDs are case-sensitive

"Insufficient Credits"

• Check credit balance in account dashboard
• Add payment method and billing info
• Set daily credit limit if needed
• Purchase credits if available

Rate Limits

For free tier:

• Rate limited to prevent abuse
• Upgrade account for higher limits
• Implement request queuing

For paid accounts:

• Contact OpenRouter support for quota increase
• Implement exponential backoff
• Use request batching

Fallback Routing Issues

If using fallback routing:

• Verify fallback model is available
• Check pricing for fallback model
• Ensure permissions allow fallback model
• Check model compatibility

Advanced Features

Fallback Models

Specify multiple models with automatic fallback:

model: "openai/gpt-4o,anthropic/claude-3-sonnet"

Uses GPT-4o, falls back to Claude if GPT-4o unavailable.

Provider Preferences

Filter by provider when listing models:

• Restrict to specific provider
• Compare provider offerings
• Manage vendor lock-in

Usage Analytics

Track spending by:

• Model
• Provider
• Date range
• Application