AI Settings
Configure how the AI responds to your visitors.
Available Models
Hunch supports multiple AI models from different providers:
OpenAI
- GPT-4o: Latest GPT-4 model, best overall performance
- GPT-4o Mini: Cost-effective, fast responses
- GPT-4 Turbo: Powerful model for complex queries
Anthropic
- Claude 3.5 Sonnet: Excellent reasoning and helpful responses
- Claude 3.5 Haiku: Fast and cost-effective
- Claude 3 Opus: Most capable model for complex tasks
Google
- Gemini 1.5 Pro: Advanced multimodal model
- Gemini 1.5 Flash: Fast and efficient
Pricing
AI pricing is based on tokens (words and punctuation):
| Model | Input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|
| GPT-4o | $2.50 | $10.00 |
| GPT-4o Mini | $0.15 | $0.60 |
| Claude 3.5 Sonnet | $3.00 | $15.00 |
| Gemini 1.5 Flash | $0.075 | $0.30 |
System Prompt
The system prompt defines how the AI behaves. You can customize it to match your brand voice and business requirements.
Default Prompt
You are a helpful assistant for [Company Name].
Provide accurate and friendly responses to customer inquiries.
Always be concise and helpful.
Customizing the Prompt
In your dashboard settings, you can modify:
- Company name and description
- Tone (professional, friendly, casual)
- Response length preferences
- Specific knowledge about your products/services
Response Settings
Configure how the AI responds:
- Tone: Professional, Friendly, Casual
- Response Length: Short, Medium, Long
Usage Alerts
Set up usage alerts to monitor costs:
- Go to Settings in your dashboard
- Set a usage alert threshold (percentage of monthly budget)
- Receive notifications when approaching the limit
Cloudflare AI Gateway
For advanced users, you can configure Cloudflare AI Gateway for:
- Caching responses
- Rate limiting
- Analytics
- Cost control
tip
Start with GPT-4o Mini for the best balance of cost and quality. Upgrade to larger models if you need more sophisticated responses.