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

# AI Content Moderation API

> Classify content safety and filter user-generated text using Llama Guard 4. Build a moderation pipeline with curl, Python, and TypeScript examples.

export const RuncrateStyles = () => {
  if (typeof document !== 'undefined' && !document.getElementById('runcrate-overrides')) {
    const s = document.createElement('style');
    s.id = 'runcrate-overrides';
    s.textContent = `
      /* Match Runcrate's rounding scale (--radius: 0.75rem) */
      .rounded-sm { border-radius: 0.5rem !important; }   /* 8px */
      .rounded-md { border-radius: 0.625rem !important; } /* 10px */
      .rounded-lg { border-radius: 0.75rem !important; }  /* 12px */
      .rounded-l-sm { border-top-left-radius: 0.5rem !important; border-bottom-left-radius: 0.5rem !important; }
      .rounded-r-sm { border-top-right-radius: 0.5rem !important; border-bottom-right-radius: 0.5rem !important; }
      .rounded-l-md { border-top-left-radius: 0.625rem !important; border-bottom-left-radius: 0.625rem !important; }
      .rounded-r-md { border-top-right-radius: 0.625rem !important; border-bottom-right-radius: 0.625rem !important; }
      .rounded-l-lg { border-top-left-radius: 0.75rem !important; border-bottom-left-radius: 0.75rem !important; }
      .rounded-r-lg { border-top-right-radius: 0.75rem !important; border-bottom-right-radius: 0.75rem !important; }

      /* Cards: never pure white in light mode */
      .card { background-color: #fcfcfc !important; border-radius: 0.75rem !important; }
      html.dark .card { background-color: #141414 !important; }

      /* Docs hero box */
      .rc-hero { background-color: #fcfcfc; border: 1px solid #e0e0e0; }
      html.dark .rc-hero { background-color: #141414; border-color: #242424; }
      html.dark .rc-hero h1 { color: #f5f5f5; }

      /* Runcrate scrollbar — thin, transparent track, hide-until-hover thumb */
      ::-webkit-scrollbar { width: 6px; height: 6px; background-color: transparent; }
      ::-webkit-scrollbar-track { background-color: transparent; }
      ::-webkit-scrollbar-thumb { background-color: rgba(155, 155, 155, 0.5); border-radius: 10px; transition: opacity 0.3s ease; opacity: 0; }
      ::-webkit-scrollbar-thumb:hover { background-color: rgba(155, 155, 155, 0.7); }
      *:hover::-webkit-scrollbar-thumb,
      *:focus::-webkit-scrollbar-thumb,
      *:active::-webkit-scrollbar-thumb { opacity: 1; }
      * { scrollbar-width: thin; scrollbar-color: rgba(155, 155, 155, 0.5) transparent; }
    `;
    document.head.appendChild(s);
  }
  return null;
};

<RuncrateStyles />

Use Llama Guard 4 to classify user-generated content for safety before it reaches your product. The model returns structured safety labels — no manual prompt engineering, no regex rules, no third-party moderation service.

## Model

| Model                          | Parameters | Output                               |
| ------------------------------ | ---------- | ------------------------------------ |
| `meta-llama/Llama-Guard-4-12B` | 12B        | `safe` or `unsafe` + category labels |

Llama Guard 4 evaluates text against a predefined taxonomy of unsafe content categories: violence, sexual content, hate speech, self-harm, criminal activity, and more. It returns a structured verdict you can use for automated decisions.

***

## Classify a single message

<CodeGroup>
  ```bash curl theme={"theme":"github-dark"}
  curl https://api.runcrate.ai/v1/chat/completions \
    -H "Authorization: Bearer rc_live_YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "meta-llama/Llama-Guard-4-12B",
      "messages": [
        {"role": "user", "content": "How do I make a birthday cake for my daughter?"}
      ],
      "max_tokens": 64
    }'
  ```

  ```python Python theme={"theme":"github-dark"}
  from openai import OpenAI

  client = OpenAI(
      base_url="https://api.runcrate.ai/v1",
      api_key="rc_live_YOUR_API_KEY",
  )

  response = client.chat.completions.create(
      model="meta-llama/Llama-Guard-4-12B",
      messages=[{"role": "user", "content": "How do I make a birthday cake for my daughter?"}],
      max_tokens=64,
  )

  verdict = response.choices[0].message.content.strip()
  print(verdict)  # "safe"
  ```

  ```typescript TypeScript theme={"theme":"github-dark"}
  import OpenAI from "openai";

  const client = new OpenAI({
    baseURL: "https://api.runcrate.ai/v1",
    apiKey: "rc_live_YOUR_API_KEY",
  });

  const response = await client.chat.completions.create({
    model: "meta-llama/Llama-Guard-4-12B",
    messages: [{ role: "user", content: "How do I make a birthday cake for my daughter?" }],
    max_tokens: 64,
  });

  const verdict = response.choices[0].message.content?.trim();
  console.log(verdict); // "safe"
  ```
</CodeGroup>

The model responds with `safe` or `unsafe` followed by the violated category (e.g., `unsafe\nS1` for violence-related content).

***

## Moderation middleware

Build a reusable moderation function for your app:

```python theme={"theme":"github-dark"}
from openai import OpenAI

client = OpenAI(
    base_url="https://api.runcrate.ai/v1",
    api_key="rc_live_YOUR_API_KEY",
)

def moderate(text: str) -> dict:
    """Check if text is safe. Returns {"safe": bool, "categories": list}."""
    response = client.chat.completions.create(
        model="meta-llama/Llama-Guard-4-12B",
        messages=[{"role": "user", "content": text}],
        max_tokens=64,
    )
    result = response.choices[0].message.content.strip()
    lines = result.split("\n")
    is_safe = lines[0].lower() == "safe"
    categories = lines[1:] if not is_safe else []
    return {"safe": is_safe, "categories": categories}

# Use it as middleware before processing user input
user_message = "Tell me how to bake sourdough bread."
check = moderate(user_message)

if check["safe"]:
    # Proceed with normal processing
    print("Content is safe — processing request.")
else:
    print(f"Content blocked. Categories: {check['categories']}")
```

***

## Next steps

* [Route between AI models](/examples/multi-model-routing) — run moderation with Llama Guard, then route safe content to a generation model.
* [Build an AI SaaS backend](/examples/ai-saas-backend) — full production backend with moderation, chat, and structured output.
* [Model catalog](/models/model-catalog) — browse all available models.