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

# Use Content Rating

> Enable default or custom content classification on generated images.

Use the `rating` option when you want generated images to include a classification result. It is optional and omitted by default.

## Enable default rating

The simplest form is `rating: true`, which enables the built-in `sfw` / `nsfw` scale:

```ts theme={"theme":"kanagawa-dragon"}
const task = await mynth.image.generate({
  prompt: "Fantasy character concept art",
  model: "google/gemini-3.1-flash-image",
  rating: true,
});
```

You can also be explicit with `mode: "nsfw_sfw"`:

```ts theme={"theme":"kanagawa-dragon"}
const task = await mynth.image.generate({
  prompt: "Fantasy character concept art",
  model: "google/gemini-3.1-flash-image",
  rating: { mode: "nsfw_sfw" },
});
```

Successful images then include a `rating` object:

```json theme={"theme":"kanagawa-dragon"}
{
  "rating": {
    "status": "success",
    "level": "sfw"
  }
}
```

If the rating step itself fails, the `rating` field is simply omitted from the image — the image is still returned normally.

## Use custom rating levels

Provide `mode: "custom"` with your own levels to replace the default scale:

```ts theme={"theme":"kanagawa-dragon"}
rating: {
  mode: "custom",
  levels: [
    { value: "safe", description: "Safe for all audiences" },
    { value: "sensitive", description: "Contains mature or suggestive content" }
  ]
}
```

Constraints:

* 2 to 7 levels
* `value` length: 1 to 24 characters
* `description` length: 1 to 150 characters

When you provide custom levels, Mynth returns the chosen custom `level`.

### Choosing effective levels

Content rating is performed by a vision language model (LLM). Because LLM inference is non-deterministic, results for borderline images may occasionally vary between requests.

This feature is designed for high-level, coarse-grained content classification — not fine-grained tagging. Scales with broad, clearly separated categories perform reliably:

* `sfw` / `nsfw`
* `safe` / `suggestive` / `explicit`
* `safe-for-children` / `safe-for-adults` / `nsfw`
* `blood` / `no-blood`

Scales that rely on subtle visual distinctions — for example `subtle-nudity` vs `artistic-nudity` vs `explicit-nudity` — are outside the intended scope of this feature and may produce inconsistent results. If you need that level of granularity, test thoroughly before relying on the output in production.