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

# MiniMax-H3 Create Video (Unified Format)

> Create a MiniMax-H3 task in the unified video format with `POST /v1/video/create`.

# MiniMax-H3 Create Video (Unified Format)

Unified video format entry point. The request body fields, generation scenarios, and file limits are **identical** to [OpenAI-format Video Generation](./generation); only the creation path differs.

<Note>
  For full request/response field details and input file limits, refer to [Video Generation (OpenAI Format)](./generation). This page only provides the unified-format entry point and examples.
</Note>

## Method and Path

```http theme={null}
POST /v1/video/create
```

<RequestExample>
  ```bash Text-to-video (t2va) theme={null}
  curl -X POST https://zx1.deepwl.net/v1/video/create \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "MiniMax-H3",
      "prompt": "A boy playing basketball by the sea",
      "duration": 5,
      "size": "2K",
      "metadata": {
        "ratio": "16:9"
      }
    }'
  ```

  ```bash Image-to-video (i2va) theme={null}
  curl -X POST https://zx1.deepwl.net/v1/video/create \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "MiniMax-H3",
      "prompt": "Camera slowly pushes in, waves crashing against rocks and splashing",
      "duration": 5,
      "size": "2K",
      "image": "https://cdn.example.com/first-frame.jpg",
      "metadata": {
        "ratio": "adaptive"
      }
    }'
  ```

  ```bash Multimodal reference (r2va) theme={null}
  curl -X POST https://zx1.deepwl.net/v1/video/create \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "MiniMax-H3",
      "prompt": "Re-generate following the reference video motion and the reference audio mood",
      "duration": 5,
      "size": "2K",
      "metadata": {
        "ratio": "adaptive",
        "reference_video": "https://cdn.example.com/reference.mp4",
        "reference_audio": "https://cdn.example.com/bgm.wav"
      }
    }'
  ```
</RequestExample>

## Response Example

<ResponseExample>
  ```json 200 theme={null}
  {
    "id": "task_a1b2xxxxx5f6",
    "task_id": "task_a1b2xxxxx5f6",
    "object": "video",
    "model": "MiniMax-H3",
    "status": "queued",
    "progress": 0,
    "created_at": 1785125529
  }
  ```

  ```json 400 theme={null}
  {
    "code": "invalid_request",
    "message": "prompt is required",
    "data": null
  }
  ```
</ResponseExample>

Response fields match [Video Generation (OpenAI Format)](./generation).

## Error Codes

| HTTP Status | Description                      |
| ----------- | -------------------------------- |
| `400`       | Invalid request parameters       |
| `401`       | Authentication failed            |
| `402`       | Insufficient quota               |
| `422`       | Input contains sensitive content |
| `429`       | Rate limited                     |
| `500`       | Server error                     |

## Related Endpoints

* [MiniMax-H3 Video Overview](./overview)
* [Video Generation (OpenAI Format)](./generation)
* [2K Regeneration (Unified Format)](./unified-remix)
* [Query Task (Unified Format)](./unified-query)