Mistral

WatchThatSite integrates with Mistral's API, offering efficient and high-performance language models.

Get Your API Key

1. Go to Mistral Console
2. Sign up or log in with your account
3. Navigate to API Keys
4. Click Create new API key
5. Name it (e.g., "WatchThatSite")
6. Click Create
7. Copy the API key immediately (won't be shown again)

Add to WatchThatSite

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

Recommended Models

Latest Mistral models with tool calling:

• Mistral Large — Most capable, complex reasoning
• Mistral Medium — Balance of capability + speed
• Mistral Small — Fast + efficient

All Available Models

Your account has access to all Mistral 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

Key Features

• Open-source roots: Models based on proven architectures
• Efficient: Fast inference, lower latency
• Cost-effective: Competitive pricing
• Multilingual: Strong support for multiple languages
• Function calling: Built-in tool use
• Guardrails: Safety features included

Pricing

Mistral charges per 1M tokens:

• Input tokens: Price per 1M input tokens
• Output tokens: Price per 1M output tokens

Pricing is competitive, especially for smaller models. Check Mistral pricing for current rates.

Use Cases

Mistral works well for:

• Cost-sensitive applications: Low-cost inference
• Multilingual tasks: Good multilingual support
• Fast responses: Efficient model execution
• General-purpose: Good across many tasks

Troubleshooting

"Invalid API Key"

• Verify complete key is pasted without spaces
• Ensure key is active (not revoked)
• Check in Mistral console the key is still valid

"Model Not Found"

• Verify model name is correct
• Check available models in Mistral console
• Some models may be in beta or require approval
• Model names are case-sensitive

Rate Limits

For rate limit issues:

• Implement exponential backoff
• Space requests appropriately
• Contact Mistral for quota increase
• Upgrade your plan for higher limits

High Latency

To reduce latency:

• Use smaller models (Small, Tiny)
• Disable or reduce output length
• Use streaming for incremental results
• Check network conditions

Integration Tips

• Streaming: Enable streaming for real-time token generation
• Temperature: Lower temperature (0.0-0.5) for consistent outputs
• Max tokens: Set appropriate limits to control costs
• Stop sequences: Use to truncate irrelevant outputs