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

# Hailuo 2.3

> 文生视频，可选首帧引导

> [!TIP]
>
> 1. 提交后会返回 `task_id`。如果提供了 `callback_url`，当任务状态变为 `finished` 或 `failed` 时，系统会向 `callback_url` 发送 POST 请求。
> 2. 无论是否提供 `callback_url`，都可以通过统一的[查询任务状态](https://docs.vidgo.ai/zh/api-manual/task-management/status.md)接口获取结果。

`hailuo-2.3` 支持纯提示词生成，以及可选的首帧引导生成。

## 模型

* **hailuo-2.3** - 文生视频，可选 `start_image_url`

## 必填参数

* **prompt**：视频生成的文本提示词

## 可选参数

* **duration**：`6` 或 `10`。默认为 `6`
* **resolution**：`768p` 或 `1080p`。默认为 `768p`
* **start\_image\_url**：可选的首帧图像
* **prompt\_optimizer**：可选的布尔开关

## 工作流程 ID

现有 ID 仍可继续使用。新接入可以选择专用的工作流程：

* [minimax/hailuo-2.3/standard/text-to-video](https://docs.vidgo.ai/zh/api-manual/video-series/minimax-hailuo-2-3-standard-text-to-video.md)
* [minimax/hailuo-2.3/standard/image-to-video](https://docs.vidgo.ai/zh/api-manual/video-series/minimax-hailuo-2-3-standard-image-to-video.md)
* [minimax/hailuo-2.3/pro/text-to-video](https://docs.vidgo.ai/zh/api-manual/video-series/minimax-hailuo-2-3-pro-text-to-video.md)
* [minimax/hailuo-2.3/pro/image-to-video](https://docs.vidgo.ai/zh/api-manual/video-series/minimax-hailuo-2-3-pro-image-to-video.md)

## 注意事项

* `1080p` 仅支持 `duration=6`


## OpenAPI

````yaml zh/api-manual/video-series/hailuo-2-3.json POST /api/generate/submit
openapi: 3.0.0
info:
  title: Vidgo API - Hailuo 2.3 API
  description: 文生视频，可选首帧引导
  version: 1.0.0
servers:
  - url: https://api.vidgo.ai
    description: 生产环境
security:
  - BearerAuth: []
paths:
  /api/generate/submit:
    post:
      tags:
        - Hailuo 2.3
      summary: 提交 Hailuo 2.3 任务
      description: 使用 Hailuo 2.3 生成视频
      operationId: submitHailuo23Task
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SubmitRequest'
            examples:
              hailuo-2-3:
                summary: Hailuo 2.3
                value:
                  model: hailuo-2.3
                  callback_url: https://your-domain.com/callback
                  input:
                    prompt: >-
                      a tiktok dancer is dancing on a small drone, doing flips
                      and tricks
                    duration: 6
                    resolution: 768p
                    prompt_optimizer: true
      responses:
        '200':
          description: 任务提交成功
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SubmitResponse'
components:
  schemas:
    SubmitRequest:
      type: object
      required:
        - model
        - input
      properties:
        model:
          type: string
          example: hailuo-2.3
        callback_url:
          type: string
          format: uri
          description: 接收结果通知的 Webhook 回调 URL
          example: https://your-domain.com/callback
        input:
          type: object
          required:
            - prompt
          properties:
            prompt:
              type: string
              description: 用于生成的文本提示词
              example: >-
                a tiktok dancer is dancing on a small drone, doing flips and
                tricks
            duration:
              type: integer
              description: 输出时长（秒）
              enum:
                - 6
                - 10
              default: 6
              example: 6
            resolution:
              type: string
              description: 输出分辨率
              enum:
                - 768p
                - 1080p
              default: 768p
              example: 768p
            start_image_url:
              type: string
              format: uri
              description: 可选的首帧图像 URL
              example: https://cdn.vidgo.ai/temp/start-image.png
            prompt_optimizer:
              type: boolean
              description: 可选的提示词优化开关
              example: true
    SubmitResponse:
      type: object
      required:
        - code
        - data
      properties:
        code:
          type: integer
          example: 200
        data:
          type: object
          required:
            - task_id
            - status
            - created_time
          properties:
            task_id:
              type: string
              example: task-unified-1757165031-uyujaw3d
            status:
              type: string
              enum:
                - not_started
              example: not_started
            created_time:
              type: string
              format: date-time
              example: '2025-11-12T10:30:00'
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: >-
        所有 API 接口都需要 Bearer Token 认证


        获取 API Key：


        进入 **仪表盘 → API 密钥**（[API Key
        管理页面](https://vidgo.ai/apis/dashboard/api-key)）获取 API Key


        在请求头中添加：


        ```

        Authorization: Bearer VIDGO_API_KEY

        ```

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.