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

# Handling Blocked Requests

> How to gracefully handle a 403 response in your application

When Krixai blocks a request in **blocking mode**, it returns a `403 Forbidden` status code. Your application should catch this error and handle it gracefully rather than crashing.

### Python Example (OpenAI SDK)

```python theme={null}
from openai import OpenAI, APIStatusError

client = OpenAI(
    api_key="sk-...",
    base_url="https://api.krixaisecurity.com/v1",
    default_headers={"X-Krixai-Key": "kx-live-..."}
)

try:
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": user_input}]
    )
    return response.choices[0].message.content

except APIStatusError as e:
    if e.status_code == 403:
        # Krixai blocked the request
        detection = e.body.get("error", {}).get("detection", {})
        print(f"Blocked: {detection.get('category')} "
              f"(confidence: {detection.get('confidence')})")
        
        # Show user a safe message
        return "Sorry, I couldn't process that request. Please rephrase."
    
    # Handle other API errors
    raise
```

### Node.js Example (OpenAI SDK)

```javascript theme={null}
try {
  const response = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: userInput }]
  });
  return response.choices[0].message.content;

} catch (error) {
  if (error.status === 403) {
    const detection = error.error?.detection;
    console.log(`Blocked: ${detection?.category} (${detection?.confidence})`);
    
    // Show user a safe message
    return "Sorry, I couldn't process that request. Please rephrase.";
  }
  
  // Handle other API errors
  throw error;
}
```