Wan 3.0 - Video Prime

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.

Parameters for Wan 3.0 video generation.

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	wan/3-0-video-prime is a high-speed model. The model name used to generate videos. This field is required. - This endpoint must be wan/3-0-video-prime Allowed values：wan/3-0-video-prime。 Example：wan/3-0-video-prime。
prompt	string	Yes	Prompt required by the ModelFold gateway; at most 2000 characters. Text prompt. Chinese and English are supported. Up to 20,000 characters. Required for text-to-video; for other modes, it is recommended to provide it together with media. In reference mode, use Image1/Video1/Audio1 to reference the provided materials. maxLength: 2000. Example：A kitten running across a rooftop under the moonlight, neon lights flickering in the distance, cinematic quality, with smooth camera movement.。
first_frame_url	string	No	URL of the first-frame image. Up to 1 image, used strictly as the first frame of the video. Used for first-frame-to-video or first-and-last-frame-to-video generation. Cannot be provided together with reference_*_urls. Formats: JPEG/JPG, PNG (transparency not supported), BMP, WEBP; each side [240, 8000] px; aspect ratio ≤ 8:1; ≤ 20MB.
last_frame_url	string	No	URL of the last-frame image. Use together with first_frame_url. Same format limits as first_frame_url.
reference_image_urls	array<string>	No	Reference images for all-purpose reference mode. Up to 10 images. Correspond to Image1, Image2, and so on in the prompt according to array order. Same specifications as first_frame_url. Cannot be provided together with the first-frame or last-frame image. maxItems: 10.
reference_video_urls	array<string>	No	Reference videos for all-purpose reference mode. Up to 5 videos. Each video must be 1–15s, with a combined duration of ≤ 15s. Correspond to Video1, Video2, and so on according to array order. Formats: mp4, mov; each side [240, 4096] px; aspect ratio ≤ 8:1; each file ≤ 100MB. There is an additional output-side limit: the input video duration plus duration cannot exceed 30 seconds. maxItems: 5.
reference_audio_urls	array<string>	No	Reference audio files for all-purpose reference mode. Up to 5 audio files. Each file must be 1–15s, with a combined duration of ≤ 15s. Correspond to Audio1, Audio2, and so on according to array order. Formats: wav, mp3; ≤ 15MB. Reference audio can be used as the only media input; pairing it with a reference image or video usually gives better results. maxItems: 5.
reference_file_urls	array<string>	No	File-to-video generation. Up to 1 file. Cannot be provided together with reference_link_urls, or with the first-frame/last-frame image. Formats: docx/doc/xlsx/xls/pptx/ppt/pdf/txt/key/pages/numbers/md; ≤ 100MB; pdf/docx/ppt/key/pages, etc. ≤ 50 pages. maxItems: 1.
reference_link_urls	array<string>	No	Link-to-video generation. Up to 1 publicly accessible webpage that does not require login. Cannot be provided together with reference_file_urls, or with the first-frame/last-frame image. maxItems: 1.
resolution	string	No	Output resolution level. Default: 1080P. Default："1080P"。 Allowed values：480P / 720P / 1080P。 Example：1080P。
aspect_ratio	string	No	Output aspect ratio. adaptive (default) automatically selects the aspect ratio based on the input materials and intent. Default："adaptive"。 Allowed values：adaptive / 16:9 / 4:3 / 1:1 / 3:4 / 9:16。 Example：adaptive。
duration	integer	No	Output video duration in seconds. Default: 5. When there is no video input, the value must be within [2, 30]. When reference videos are provided: input video duration plus output duration ≤ 30. Pass -1 to use an intelligent duration determined by the model. ModelFold minimum: 2 seconds; -1 is not supported. Default：5。 Example：5。
audio	boolean	No	Whether the output video includes an audio track. Default: true. Default：true。 Example：true。
seed	integer	No	Random seed used to reproduce results. If omitted, a random seed is used. minimum: 0. maximum: 2147483647.
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": "wan/3-0-video-prime",
  "prompt": "A kitten running across a rooftop under the moonlight, neon lights flickering in the distance, cinematic quality, with smooth camera movement.",
  "resolution": "1080P",
  "aspect_ratio": "adaptive",
  "duration": 5,
  "audio": true
}'

{
  "model": "wan/3-0-video-prime",
  "prompt": "A kitten running across a rooftop under the moonlight, neon lights flickering in the distance, cinematic quality, with smooth camera movement.",
  "resolution": "1080P",
  "aspect_ratio": "adaptive",
  "duration": 5,
  "audio": true
}

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": {}
}