## Create

`moderations.create(ModerationCreateParams**kwargs)  -> ModerationCreateResponse`

**post** `/moderations`

Classifies if given messages are potentially harmful across several categories.

### Parameters

- **messages:** `Iterable[MessageParam]`

  List of messages in the conversation.

  - `UserMessage`

  - `SystemMessage`

  - `ToolResponseMessage`

  - `CompletionMessage`

- **model:** `str`

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

### Returns

- `class ModerationCreateResponse`

  - **model:** `str`

  - **results:** `List[Result]`

    - **flagged:** `bool`

    - **flagged\_categories:** `List[str]`

### Example

```python
from llama_api_client import LlamaAPIClient

client = LlamaAPIClient(
    api_key="My API Key",
)
moderation = client.moderations.create(
    messages=[{
        "content": "string",
        "role": "user",
    }],
)
print(moderation.model)
```