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

# Seedance 2.5 Flash Text-to-Video

> - Generate 4-30 second videos from a text prompt at 480p or 720p, with synchronized audio
- Aspect ratio `adaptive` (default) or 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; `duration: -1` lets the model pick the length
- Optional web search via `model_params.web_search`
- Asynchronous processing mode, use the returned task ID to query status with `GET /v1/tasks/{task_id}`
- Generated video links are valid for 24 hours, please save them promptly



## OpenAPI

````yaml en/api-manual/video-series/seedance2.5-flash/seedance-2.5-flash-text-to-video.json POST /v1/videos/generations
openapi: 3.1.0
info:
  title: Seedance 2.5 Flash Text-to-Video API
  description: >-
    Seedance 2.5 Flash text-to-video API: Generate 4-30 second videos from a text prompt at 480p or 720p
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://api.evolink.ai
    description: Production
security:
  - bearerAuth: []
tags:
  - name: Video Generation
    description: AI video generation endpoints
paths:
  /v1/videos/generations:
    post:
      tags:
        - Video Generation
      summary: Seedance 2.5 Flash Text-to-Video
      description: >-
        - Generate 4-30 second videos from a text prompt at 480p or 720p, with synchronized audio
        - Aspect ratio `adaptive` (default) or 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; `duration: -1` lets the model pick the length
        - Optional web search via `model_params.web_search`
        - Asynchronous processing mode, use the returned task ID to query status with `GET /v1/tasks/{task_id}`
        - Generated video links are valid for 24 hours, please save them promptly
      operationId: createSeedance25FlashTexttoVideo
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VideoGenerationRequest'
            examples:
              basic:
                summary: Basic text-to-video
                value:
                  model: seedance-2.5-flash-text-to-video
                  prompt: >-
                    A paper boat drifts down a rain-soaked city street at dusk, neon reflections ripple across the water, slow tracking shot
                  duration: 5
                  quality: 720p
                  aspect_ratio: adaptive
                  generate_audio: true
                  content_filter: true
      responses:
        '200':
          description: Video generation task created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoGenerationResponse'
        '400':
          description: >-
            Invalid request parameters (including fields this route does not
            accept)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                error:
                  code: invalid_parameter
                  message: Invalid request parameters
                  type: invalid_request_error
        '401':
          description: Unauthenticated, token invalid or expired
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '402':
          description: Insufficient quota, top-up required
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Rate limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    VideoGenerationRequest:
      type: object
      required:
        - model
        - prompt
      properties:
        model:
          type: string
          description: Video generation model name
          enum:
            - seedance-2.5-flash-text-to-video
          default: seedance-2.5-flash-text-to-video
          example: seedance-2.5-flash-text-to-video
        prompt:
          type: string
          description: >-
            Text prompt describing the desired video. Maximum prompt length: 10000 tokens
        duration:
          type: integer
          description: >-
            Output duration in seconds as a JSON integer, defaults to `5`. Any integer from `4` to `30`, or `-1` to let the model pick the best length (credits are reserved at the 30-second cap and settled on the actual output). Duration directly affects billing
          default: 5
          example: 5
        quality:
          type: string
          description: >-
            Video resolution, defaults to `720p`. `480p` costs less. `1080p` is not available and returns a 400 error
          enum:
            - 480p
            - 720p
          default: 720p
          example: 720p
        aspect_ratio:
          type: string
          description: >-
            Video aspect ratio, defaults to `adaptive` (the model picks a ratio from the prompt and references)
          enum:
            - adaptive
            - '16:9'
            - '9:16'
            - '1:1'
            - '4:3'
            - '3:4'
            - '21:9'
          default: adaptive
          example: adaptive
        generate_audio:
          type: boolean
          description: >-
            Whether to generate synchronized audio, defaults to `true`, at no additional charge. `false` outputs a silent video
          default: true
          example: true
        content_filter:
          type: boolean
          description: >-
            Keep the standard content filter enabled, defaults to `true`. `false` relaxes content restrictions (illegal and prohibited content is always blocked) and adds 10% to generation pricing. Cannot be combined with `model_params.web_search: true`
          default: true
          example: true
        output_format:
          type: string
          description: >-
            Output container format, defaults to `mp4`. `mov` (yuv444p + PCM) keeps higher color fidelity for editing workflows at no extra charge; browsers may not preview it
          enum:
            - mp4
            - mov
          default: mp4
          example: mp4
        model_params:
          type: object
          description: >-
            Optional model parameters
          properties:
            web_search:
              type: boolean
              description: >-
                Allow the model to search current web content when needed. Billed only when a search is triggered. Cannot be combined with `content_filter: false`
              default: false
        callback_url:
          type: string
          description: >-
            HTTPS callback URL for task completion. Triggered when the task is completed, failed, or cancelled. Only HTTPS is supported; private network addresses are rejected. Keep the task ID as a polling fallback
          format: uri
          example: https://your-domain.com/webhooks/video-task-completed
    VideoGenerationResponse:
      type: object
      properties:
        created:
          type: integer
          description: Task creation timestamp
          example: 1761313744
        id:
          type: string
          description: Task ID
          example: task-unified-1774857405-abc123
        model:
          type: string
          description: Actual model name used
          example: seedance-2.5-flash-text-to-video
        object:
          type: string
          enum:
            - video.generation.task
          description: Specific type of the task
        progress:
          type: integer
          description: Task progress percentage (0-100)
          minimum: 0
          maximum: 100
          example: 0
        status:
          type: string
          description: Task status
          enum:
            - pending
            - processing
            - completed
            - failed
          example: pending
    ErrorResponse:
      type: object
      properties:
        error:
          type: object
          properties:
            code:
              type: string
              description: Error code identifier
            message:
              type: string
              description: Error description message
            type:
              type: string
              description: Error type
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        All endpoints require Bearer Token authentication. Get your API key on
        the API Key Management Page (https://evolink.ai/dashboard/keys) and send
        it as `Authorization: Bearer YOUR_API_KEY`

````



# Query Task Status

> Query the status, progress, and result information of the asynchronous task by task ID

- Endpoint: `GET https://api.evolink.ai/v1/tasks/{task_id}`
- Header: `Authorization: Bearer YOUR_API_KEY`
- `status` is one of `pending`, `processing`, `completed`, `failed`
- When `status` is `completed`, `results` contains the video URL (valid for 24 hours)
- A task whose final status is `failed` is not charged
