Bytedance Seedance 2.5

Endpoint

POST /videos/generations

Full URL: https://modelfold.ai/v1/videos/generations

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

Send model parameters directly in the JSON body. Do not wrap them in input. This request waits for generation to finish and returns data[].url; supported media models also offer async jobs, polling and callbacks. Replace example media URLs with your own publicly accessible files. See API gateway for billing and errors.

Input parameters for the generation task

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	The model name to use for generation. Required field. - Must be bytedance/seedance-2-5 for this endpoint Default："bytedance/seedance-2-5"。 Allowed values：bytedance/seedance-2-5。 Example：bytedance/seedance-2-5。
prompt	string	Yes	Prompt required by the ModelFold gateway; at most 2000 characters. The text prompt used to generate the video.. ( Max length: 20480 characters) maxLength: 2000. Example：A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky。
first_frame_url	string	No	First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) Cannot be used simultaneously with reference_image_urls, reference_video_urls, or reference_audio_urls.
last_frame_url	string	No	End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) last_frame_url cannot be passed alone; first_frame_url must be provided together with it.
reference_image_urls	array<string>	No	Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single image requirements: Format: jpeg, png, webp. Aspect ratio (width/height): (0.4, 2.5) Width and height (px): (300, 6000) Size: Single image less than 30 MB. Up to 30 images. Mutually exclusive with the first/last-frame scenario; maxItems: 30.
reference_video_urls	array<string>	No	Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) . Single video requirements: Video format: mp4, mov, mkv. Resolution: 480p, 720p Dimensions: Aspect ratio (width/height): [0.4, 2.5] Width/height (px): [300, 6000] Total pixels: [640×640=409600, 834×1112=927408], i.e., the product of width and height must meet the range requirement of [409600, 927408]. Size: Single video not exceeding 200 MB. Frame rate (FPS): [24, 60] Single video duration: [2, 30] seconds; Mutually exclusive with the first/last-frame scenario; Total duration of reference videos must not exceed 30 seconds. maxItems: 10.
reference_audio_urls	array<string>	No	Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) . Single audio requirements: Format: wav, mp3, aac, ogg Size: Single audio file size not exceeding 15 MB. Single audio duration: [2, 30] seconds; mutually exclusive with first/last frames; total duration of reference audio must not exceed 30 seconds. maxItems: 10.
return_last_frame	boolean	No	Whether to also return the last frame of the generated video as a JPEG (in resultJson.lastFrameUrl). Default false. Default：false。 Example：false。
generate_audio	boolean	No	Whether to generate audio synchronized with the video. Default: true. Default：true。 Example：false。
resolution	string	No	Video resolution - 480p for faster generation, 720p for balance. Default："720p"。 Allowed values：480p / 720p / 1080p。 Example：720p。
aspect_ratio	string	No	Video aspect ratio configuration. Default："adaptive"。 Allowed values：1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 21:9 / adaptive。 Example：adaptive。
duration	integer	No	Video duration in 4-30 seconds. Special values -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 within the valid range), instead of you specifying an exact value. ModelFold minimum: 4 seconds; -1 is not supported. Default：5。 Example：5。
output_format	string	No	Video output format. Default："mp4"。 Allowed values：mp4 / mov。 Example：mp4。
web_search	boolean	No	Enable online search.
draft	boolean	No	Enable draft mode. When enabled, only 480p resolution is allowed. Draft task ID is valid for 7 days from draft creation. Default：false。 Example：false。
nsfw_checker	boolean	No	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

Request Example

curl -X POST "https://modelfold.ai/v1/videos/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-2-5",
  "prompt": "A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky",
  "return_last_frame": false,
  "generate_audio": true,
  "resolution": "720p",
  "aspect_ratio": "adaptive",
  "duration": 5,
  "output_format": "mp4",
  "draft": false
}'

{
  "model": "bytedance/seedance-2-5",
  "prompt": "A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky",
  "return_last_frame": false,
  "generate_audio": true,
  "resolution": "720p",
  "aspect_ratio": "adaptive",
  "duration": 5,
  "output_format": "mp4",
  "draft": false
}

Response

200 — Generation completed. usage contains actual billing details; result URLs are illustrative.

{
  "ok": true,
  "created": 1792134000,
  "data": [
    {
      "url": "https://modelfold.ai/uploads/outputs/result.mp4"
    }
  ],
  "usage": {}
}