Generate video with Wan 3.0
Alibaba Wan 3.0 — all-in-one video generation up to 30 seconds at 30fps. Text-to-video; image-to-video (first + optional last frame); and reference-to-video mixing up to 10 reference images, up to 5 reference video clips (15s combined) for editing/replication/extension, and up to 5 reference audio clips (15s combined). In reference mode the prompt can address assets by order (“Image 1”, “Video 1”). Reference media can’t be combined with start/end frames. 480p/720p/1080p, priced per OUTPUT second by resolution (input media is free — see resolution_pricing in GET /v1/models); any duration 2-30 seconds (input video + output ≤ 30s); optional audio.
Asynchronous. Returns a job id (the video is not in this response). Poll GET /v1/videos/{id} until status is succeeded — the video URL is in that response’s video_url.
Authorizations
API key as a bearer token: Authorization: Bearer bpx_live_xxx
Body
Text description of the video, or the edit instruction when reference videos are supplied. In reference mode, address assets by order: "Image 1", "Video 1", "Audio 1".
Aspect ratio for text-to-video. With any image/video/audio input the frame adapts to the inputs and this is ignored.
16:9, 9:16, 1:1, 4:3, 3:4 Optional last frame, used together with image (the first frame) to interpolate the video between the two frames. Same input forms as image.
Generate audio with the video (default true; no price impact).
Optional first frame for image-to-video. Provide a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-video. Can't be combined with reference media.
Output video length in seconds (2-30). With reference videos, input duration + output length must not exceed 30 seconds.
2 <= x <= 30Optional reference audio clips (up to 5; each 2-15s, 15s combined; WAV/MP3) that guide sound/voice. Free. Each item is a public audio URL or an uploaded-file URL from POST /v1/uploads. Can't be combined with image/end_image.
5Optional reference images (up to 10, free) that guide identity/style/scene in reference-to-video mode. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Can't be combined with image/end_image.
10Optional reference video clips (up to 5; each 2-15s, 15s combined; MP4/MOV, ≤50MB each) for editing, effect/camera replication, and extension. Each item is a public video URL or an uploaded-file URL from POST /v1/uploads (videos are passed by URL, not inlined). Free — only OUTPUT seconds are billed — but input video duration + length_seconds must not exceed 30. Can't be combined with image/end_image.
5Output resolution. Pricing varies by resolution — see resolution_pricing in GET /v1/models.
480p, 720p, 1080p Seed for reproducible generation. Omit for random.