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

# POST /v1/moderate/batch

> Moderate multiple texts in batch

## Endpoint

```
POST /v1/moderate/batch
```

Analyzes multiple texts in a single request. More efficient than making multiple individual requests.

## Request

### Body Parameters

<ParamField body="texts" type="array" required>
  Array of strings to moderate

  **Min items**: 1
  **Max items**: 100 (recommended)
  **Item type**: string
</ParamField>

### Request Example

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST "http://localhost:8000/v1/moderate/batch" \
    -H "Content-Type: application/json" \
    -d '{
      "texts": [
        "First text to moderate",
        "Second text to moderate",
        "Third text to moderate"
      ]
    }'
  ```

  ```python Python SDK theme={null}
  from guardian_api import GuardianClient

  client = GuardianClient(base_url="http://localhost:8000")
  texts = [
      "First text to moderate",
      "Second text to moderate",
      "Third text to moderate"
  ]
  results = client.moderate_batch(texts)
  print(results)
  ```

  ```javascript JavaScript SDK theme={null}
  const client = new GuardianClient({ baseUrl: 'http://localhost:8000' });

  const texts = [
    'First text to moderate',
    'Second text to moderate',
    'Third text to moderate'
  ];

  const results = await client.moderateBatch(texts);
  console.log(results);
  ```
</CodeGroup>

## Response

### Success Response (200)

```json theme={null}
{
  "results": [
    {
      "text": "First text to moderate",
      "label": { ... },
      "ensemble": { ... },
      "meta": { ... }
    },
    {
      "text": "Second text to moderate",
      "label": { ... },
      "ensemble": { ... },
      "meta": { ... }
    }
  ],
  "total_processed": 2,
  "processing_time_ms": 48
}
```

## Performance

| Metric                | Value                   |
| --------------------- | ----------------------- |
| **Avg Time Per Text** | 5-10ms (in batch)       |
| **Max Batch Size**    | 100 texts (recommended) |
| **Total Time**        | \~500ms for 100 texts   |

<Tip>
  Batch processing is 3-4x faster per text compared to individual requests due to model loading overhead amortization.
</Tip>