Wan 2.7 Video

Credit amounts are left out because they change. The lowest price is creditCost on GET /v1/models, and POST /v1/jobs answers with the exact creditCost of a request.

input fieldsCopy Anchor Link

Send the fields below inside the input object. A field you leave out takes its Default. Unknown field names are dropped without an error, so check the spelling if a setting seems to have no effect.

Rules by settingCopy Anchor Link

This model runs a different version depending on what you send. The rules below are checked before any credits move; a request that breaks one is refused with 400 and a message naming the field.

mode = text

• audio_setting is not used; any value sent is ignored.
• Takes no files in frames, edit_video, reference_images, reference_videos and reference_audios; a request that fills one is refused.
• prompt at least 1 characters.

mode = frames

• aspect_ratio and audio_setting are not used; any value sent is ignored.
• Takes no files in edit_video, reference_images, reference_videos and reference_audios; a request that fills one is refused.
• frames: required; up to 2 files; in order: the first file is the start frame, the second the end frame.
• prompt at least 1 characters.

mode = edit

• aspect_ratio is not used; any value sent is ignored.
• Takes no files in frames, reference_videos and reference_audios; a request that fills one is refused.
• edit_video: required; one file; at most 100 MB per file; each clip 2 to 10 seconds long; sides 240 to 4,096 px; width to height ratio 0.125 to 8.
• reference_images: one file; sides 240 to 8,000 px; width to height ratio 0.125 to 8.
• duration at most 10.
• duration may not be longer than the clip in edit_video.

mode = reference

• audio_setting is not used; any value sent is ignored.
• Takes no files in frames and edit_video; a request that fills one is refused.
• reference_images: up to 5 files.
• reference_videos: up to 5 files.
• reference_audios: one file; at most 15 MB per file; each clip 1 to 10 seconds long.
• duration at most 10.
• prompt at least 1 characters.
• At least one of reference_images or reference_videos has to hold a file.
• At most 5 files across reference_images and reference_videos.

Example requestCopy Anchor Link

{
  "modelSlug": "wan-2-7-video",
  "input": {
    "prompt": "The camera circles slowly around a steaming cup of coffee on a wooden table"
  }
}