# Moderations

## Create

`client.moderations.create(ModerationCreateParamsbody, RequestOptionsoptions?): ModerationCreateResponse`

**post** `/moderations`

Classifies if given messages are potentially harmful across several categories.

### Parameters

- **body:** `ModerationCreateParams`

  - **messages:** `Array<Message>`

    List of messages in the conversation.

    - `UserMessage`

    - `SystemMessage`

    - `ToolResponseMessage`

    - `CompletionMessage`

  - **model:** `string`

    Optional identifier of the model to use. Defaults to "Llama-Guard".

### Returns

- `ModerationCreateResponse`
  - **model:** `string`

  - **results:** `Array<Result>`

    - **flagged:** `boolean`

    - **flagged\_categories:** `Array<string>`

### Example

```typescript
import LlamaAPIClient from 'llama-api-client';

const client = new LlamaAPIClient({
  apiKey: 'My API Key',
});

const moderation = await client.moderations.create({ messages: [{ content: 'string', role: 'user' }] });

console.log(moderation.model);
```