Skip to main content
POST
Seedance 2.5

Endpoint

Authentication

All API requests require a Bearer Token.

Important Notes

  • Image-to-Video (First Frame) and Image-to-Video (First & Last Frames) are mutually exclusive scenarios and cannot be used simultaneously.

Request Body

The request body must be JSON.

Top-level parameters

string
required
Must be bytedance/seedance-2-5.
object
required

Input Parameters

The input object contains the parameters used to generate the video.
string
Use prompt to describe the video you want to generate.Maximum length: 30000 characters.
string
Provide the URL of the image to be used as the first frame for video generation. The value must be an uploaded file URL, not the file content itself.Cannot be used simultaneously with reference_image_urls, reference_video_urls, or reference_audio_urls.
string
Provide the URL of the image to be used as the last frame for video generation. The value must be an uploaded file URL, not the file content itself.last_frame_url cannot be passed alone; first_frame_url must be provided together with it.
string[]
Enter the URL(s) of the reference image(s) to be used for video generation.Supported image formats:
  • jpeg
  • png
  • webp
  • bmp
  • tiff
  • gif
Maximum file size: 30 MB
Maximum number of files: The sum of the number of frames at the beginning and end must not exceed 30.
Width and height (px): (300, 6000)
Aspect ratio (width/height): 0.4 to 2.5
string[]
Enter the URL(s) of the reference video(s) to be used for video generation.Maximum reference videos : 10
Single video requirements
Supported image formats:
  • mp4
  • mov
Supported resolution:
  • 480p
  • 720p
Supported duration:
  • For single video duration beetween 2 and 30.
  • Total duration of all videos not exceeding 30 seconds.
Maximum size of single video : 200 MB.
Width and height (px): (300, 6000)
Aspect ratio (width/height): 0.4 to 2.5
Frame rate (FPS): [24, 60]
Total pixels: [640×640=409600, 834×1112=927408]
string[]
Enter the URL(s) of the reference audio(s) to be used for video generation.Maximum reference audios : 10
Single audio requirements
Supported audio formats:
  • wav
  • mp3
Supported duration:
  • For single audio duration beetween 2 and 30.
  • Total duration of all audios not exceeding 30 seconds.
Maximum size of single audio : 15 MB.
boolean
default:"true"
Whether to generate audio.Default: trueNote: Enabling audio will increase the generation cost
boolean
default:"false"
Whether to return the last frame of the video.Default: false
string
Specify the resolution of the generated video.Supported values:
  • 480p
  • 720p
  • 1080p
Default: 720p
string
default:"adaptive"
Video aspect ratio configuration.Supported values: 3:4, 4:3, 1:1, 16:9, 9:16, 21:9, adaptive. Default: adaptive
number
Generated video duration in seconds.

Special value: -1

Pass -1 for automatic duration selection — the model picks a suitable duration itself:
  • For video-editing tasks, it matches the input video’s length.
  • For other task types, it selects a duration within the valid range.
This allows you to let the model determine the duration instead of specifying an exact value.Type: integer
Supported range: 430, in one-second steps. Default: 5
string
default:"mp4"
Use output_format for the generated output video.Supported formats: Default: mp4
Use online search. Only available for text-to-video.Default: false

Example Request

Response

Successful Response

number
Response status code.
string
Response message. Contains the error description when the request fails.Example: success
object
required
The task data object containing task id.
string
required
The unique identifier for this task.Example: task_123456

Query Task Status

After submitting a task, use the unified query endpoint to check the task progress and retrieve the generated results.

Get Task Details

Check task status, monitor generation progress, and retrieve results.

Error Response

Response Codes