> ## Documentation Index
> Fetch the complete documentation index at: https://help.tokener.jeekmind.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Seedance 2.5

> 使用 JSON 提交异步视频任务。视频选项字段名为 matadata；resolution 缺省为 720p。

提交后，使用返回的 `id` [查询视频任务](https://help.tokener.jeekmind.com/api-reference/videos/retrieve.md)，完成后[下载视频](https://help.tokener.jeekmind.com/api-reference/videos/content.md)。


## OpenAPI

````yaml api-reference/gxc/seedance25.openapi.json POST /v1/videos
openapi: 3.1.0
info:
  title: GXC Seedance 2.5
  version: 0.1.0
  description: Schema 导出预览，仅描述正常响应，错误响应暂未建模。
servers:
  - url: https://tokener.jeekmind.com
security:
  - bearerAuth: []
paths:
  /v1/videos:
    post:
      tags:
        - GXC 视频
      summary: Seedance 2.5 视频生成
      description: 使用 JSON 提交异步视频任务。视频选项字段名为 matadata；resolution 缺省为 720p。
      operationId: createGxcSeedance25
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Seedance25Request'
            examples:
              Seedance25Request:
                summary: gxc-doubao-seedance-2-5-260628
                value:
                  model: gxc-doubao-seedance-2-5-260628
                  prompt: 清晨湖面，一只纸船缓缓漂行
                  seconds: 4
                  resolution: 720p
                  aspect_ratio: '16:9'
      responses:
        '200':
          description: 视频任务对象
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTask'
components:
  schemas:
    Seedance25Request:
      title: Seedance 2.5
      type: object
      additionalProperties: false
      required:
        - model
        - prompt
      properties:
        model:
          type: string
          description: 模型调用名
          minLength: 1
          pattern: \S
          const: gxc-doubao-seedance-2-5-260628
        prompt:
          type: string
          minLength: 1
          pattern: \S
          description: 非空且不能仅包含空白字符的视频描述
        seconds:
          type: integer
          minimum: 4
          description: 输出视频时长，单位为秒
          maximum: 30
        resolution:
          type: string
          description: 输出视频分辨率
          enum:
            - 720p
            - 1080p
          default: 720p
        aspect_ratio:
          type: string
          enum:
            - '16:9'
            - '9:16'
            - '1:1'
            - '21:9'
            - '4:3'
            - '3:4'
          description: 画面比例
        image_references:
          type: array
          items:
            type: string
            format: uri
            pattern: ^https?://
            description: 生成期间持续可访问的 HTTP(S) URL
          description: 参考图片 URL
          maxItems: 30
        video_references:
          type: array
          items:
            type: string
            format: uri
            pattern: ^https?://
            description: 生成期间持续可访问的 HTTP(S) URL
          description: 参考视频 URL
          maxItems: 10
        audio_references:
          type: array
          items:
            type: string
            format: uri
            pattern: ^https?://
            description: 生成期间持续可访问的 HTTP(S) URL
          description: 参考音频 URL
          maxItems: 10
        matadata:
          type: object
          additionalProperties: false
          description: 视频生成选项
          properties:
            return_last_frame:
              type: boolean
              description: 是否返回最后一帧
            watermark:
              type: boolean
              description: 是否添加水印
            generate_audio:
              type: boolean
              description: 是否生成音频
    VideoTask:
      title: OpenAIVideoResponse
      description: 标准视频任务对象。保存 id，用于查询任务和下载视频。
      type: object
      required:
        - id
        - object
        - model
        - status
        - progress
        - created_at
      properties:
        id:
          type: string
          description: 网关公开任务 ID，用于后续查询和下载
        object:
          const: video
          type: string
        model:
          type: string
          description: 客户端请求的模型名称
        status:
          type: string
          enum:
            - queued
            - in_progress
            - completed
            - failed
            - unknown
        progress:
          type: integer
          description: 宿主将内部进度字符串转换为整数，解析失败时为 0
        created_at:
          type: integer
          description: 任务创建时间，Unix 秒级时间戳
        completed_at:
          type: integer
          description: 完成时间，Unix 秒级时间戳；创建响应中未完成时省略
      additionalProperties: true
      examples:
        - id: video_example
          object: video
          model: gxc-doubao-seedance-2-5-260628
          status: queued
          progress: 0
          created_at: 1793851200
        - id: video_example
          object: video
          model: gxc-doubao-seedance-2-5-260628
          status: completed
          progress: 100
          created_at: 1793851200
          completed_at: 1793851260
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 技元 API 密钥

````

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