Wan 3 Video
Alibaba video model for 2 to 30-second clips across Standard and Prime tiers, featuring built-in audio and multi-modal media references.
| Property | Value |
|---|---|
modelSlug | wan-3-video |
| Kind | Video |
| Maker | Alibaba |
Copies per request (variations) | 1 to 5 |
| How the cost is counted | per second of output (from duration), at a rate that depends on tier and resolution; plus the length of the clips in reference_videos when filled |
| Over MCP | yes, with the generate tool |
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 fields
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.
| Field | Type | Required | Default | Rules |
|---|---|---|---|---|
prompt | string | yes | – | Up to 20,000 characters |
tier | string (one of) | – | standard | standard, prime |
frames | string[] (image upload ids) | – | – | Start and end frames. Up to 2 files |
reference_images | string[] (image upload ids) | – | – | Reference images. Up to 10 files |
reference_videos | string[] (video upload ids) | – | – | Reference videos. Up to 5 files |
reference_audios | string[] (audio upload ids) | – | – | Reference audio. Up to 5 files |
aspect_ratio | string (one of) | – | adaptive | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 |
resolution | string (one of) | – | 720p | 480p, 720p, 1080p |
duration | integer | – | 5 | 2 to 30 |
generate_audio | boolean | – | true | – |
Rules by setting
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.
tier = standard and frames holds a file
- Takes no files in
reference_images,reference_videosandreference_audios; a request that fills one is refused. frames: up to 2 files; in order: the first file is the start frame, the second the end frame; at most 20 MB per file; sides 240 to 8,000 px; width to height ratio 0.125 to 8.
tier = standard
- Takes no files in
frames; a request that fills one is refused. reference_images: up to 10 files; at most 20 MB per file; sides 240 to 8,000 px; width to height ratio 0.125 to 8.reference_videos: up to 5 files; at most 100 MB per file; each clip 1 to 15 seconds long; at most 15 seconds in total; sides 240 to 4,096 px; width to height ratio 0.125 to 8.reference_audios: up to 5 files; at most 15 MB per file; each clip 1 to 15 seconds long; at most 15 seconds in total.durationplus the length of every clip inreference_videosmay not pass 30 seconds.
tier = prime and frames holds a file
- Takes no files in
reference_images,reference_videosandreference_audios; a request that fills one is refused. frames: up to 2 files; in order: the first file is the start frame, the second the end frame; at most 20 MB per file; sides 240 to 8,000 px; width to height ratio 0.125 to 8.
tier = prime
- Takes no files in
frames; a request that fills one is refused. reference_images: up to 10 files; at most 20 MB per file; sides 240 to 8,000 px; width to height ratio 0.125 to 8.reference_videos: up to 5 files; at most 100 MB per file; each clip 1 to 15 seconds long; at most 15 seconds in total; sides 240 to 4,096 px; width to height ratio 0.125 to 8.reference_audios: up to 5 files; at most 15 MB per file; each clip 1 to 15 seconds long; at most 15 seconds in total.durationplus the length of every clip inreference_videosmay not pass 30 seconds.
Example request
{
"modelSlug": "wan-3-video",
"input": {
"prompt": "The camera circles slowly around a steaming cup of coffee on a wooden table"
}
}