Wan 3.0

Alibaba Wan 3.0 generates coherent videos from text, first and optional last frames, or multimodal image, video, and audio references with native audio.


Model id	`wan-3.0-fal`
Media	video
Submit to	`POST /v1/videos`
Price	varies by tier and settings; `GET /v1/models/wan-3.0-fal/estimate` quotes it

Text → Video

Generate a video from a required text prompt with adaptive or fixed framing and optional generated audio. Select it with "mode": "text_to_video", or leave mode out and the inputs decide. Required: prompt, duration_seconds
Optional: aspect_ratio, generate_audio Resolution tiers: 480p, 720p, 1080p (send as tier).

{
  "model": "wan-3.0-fal",
  "prompt": "A slow aerial shot over a misty pine forest at dawn",
  "mode": "text_to_video",
  "aspect_ratio": "adaptive",
  "duration_seconds": 5,
  "generate_audio": true,
  "tier": "1080p"
}

Field	Allowed	Default
`aspect_ratio`	`adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"adaptive"`
`duration_seconds`	2.0 – 30.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`

Image → Video

Animate a required first frame, with an optional last frame and motion prompt. Select it with "mode": "image_to_video", or leave mode out and the inputs decide. Required: first_frame, duration_seconds
Optional: last_frame, aspect_ratio, generate_audio Resolution tiers: 480p, 720p, 1080p (send as tier).

{
  "model": "wan-3.0-fal",
  "mode": "image_to_video",
  "aspect_ratio": "adaptive",
  "duration_seconds": 5,
  "generate_audio": true,
  "first_frame": "asset_…",
  "tier": "1080p"
}

Field	Allowed	Default
`aspect_ratio`	`adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"adaptive"`
`duration_seconds`	2.0 – 30.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`
`first_frame`	asset id (up to 1)
`last_frame`	asset id (up to 1)

Reference → Video

Guide the result with up to 10 images, 5 videos, and 5 audio clips. Reference videos and audio can each total up to 15 seconds. Select it with "mode": "reference_to_video", or leave mode out and the inputs decide. Required: duration_seconds
Optional: reference_images, reference_videos, reference_audios, aspect_ratio, generate_audio Resolution tiers: 480p, 720p, 1080p (send as tier).

{
  "model": "wan-3.0-fal",
  "mode": "reference_to_video",
  "aspect_ratio": "adaptive",
  "duration_seconds": 5,
  "generate_audio": true,
  "tier": "1080p"
}

Field	Allowed	Default
`aspect_ratio`	`adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"adaptive"`
`duration_seconds`	2.0 – 30.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`
`reference_images`	asset ids (up to 10)
`reference_videos`	asset ids (up to 5)
`reference_audios`	asset ids (up to 5)

Reference inputs take asset ids from POST /v1/uploads or an earlier output’s asset_id. Prices and allowed values come from the live catalog; GET /v1/models/wan-3.0-fal is always current.

Start here

Using the API

Choosing a model

Image models

Video models

Audio models

Agents and MCP

Text → Video

Image → Video

Reference → Video

​Text → Video

​Image → Video

​Reference → Video

Text → Video

Image → Video

Reference → Video