> ## Documentation Index
> Fetch the complete documentation index at: https://docs.chat402.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# Best Practices

> Tips for integrating Chat402

## Security

### Protect Your API Key

```bash theme={null}
# Store in environment variables
export CHAT402_API_KEY="pp_your_key_here"

# Never commit to git
echo "CHAT402_API_KEY=*" >> .gitignore
```

## Cost Optimization

### Choose the Right Model

| Model             | Use Case        | Cost   |
| ----------------- | --------------- | ------ |
| GPT-3.5 or Gemini | Simple queries  | Lowest |
| Claude or GPT-4   | Complex tasks   | Higher |
| DeepSeek          | Code generation | Low    |

### Monitor Spending

```javascript theme={null}
let totalCost = 0;

async function trackedChat(prompt) {
  const result = await chat(prompt);
  totalCost += result.cost;
  console.log(`Session cost: $${totalCost.toFixed(6)}`);
  return result;
}
```

## Reliability

### Implement Retry Logic

```javascript theme={null}
async function chatWithRetry(prompt, maxRetries = 3) {
  for (let i = 0; i < maxRetries; i++) {
    try {
      return await chat(prompt);
    } catch (error) {
      if (error.response?.status === 402) {
        throw error; // Don't retry payment errors
      }
      if (i === maxRetries - 1) throw error;
      await new Promise(r => setTimeout(r, 1000 * (i + 1)));
    }
  }
}
```

## Rate Limits

Current limits:

* **Requests**: 100 per minute
* **Concurrent**: 10 requests
* **Burst**: 200 per minute

Contact us for higher limits.