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

# Moderations

> Check whether text violates usage policies

## Introduction

Moderate text for policy violations, compatible with the OpenAI Moderations API. This endpoint is one compliance tool among others; it does not replace your own safety governance or upstream policies. Public-facing services should also have abuse reporting, auditing, and enforcement.

## Authentication

<ParamField header="Authorization" type="string" required>
  Bearer Token, e.g. `Bearer sk-xxxxxxxxxx`
</ParamField>

## Request parameters

<ParamField body="input" type="string | array" required>
  Text to moderate (string or array)
</ParamField>

<ParamField body="model" type="string">
  Moderation model, e.g. `text-moderation-latest`
</ParamField>

## Request example

```bash theme={null}
curl -X POST "https://api.gravitex.ai/v1/moderations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-moderation-latest",
    "input": "Text to check"
  }'
```

## Common parameters

* **input**: One or more strings to check
* **model**: Moderation model ID

Responses include `results` with `flagged` and per-category scores. See [OpenAI Moderations](https://platform.openai.com/docs/api-reference/moderations).