Video Generation 3.0

Generate Wan 3.0 videos from text, frames, or reference media through the TokenByte API

POSThttps://api.tokenbyte.ai/v1/videos

Submit asynchronous Wan 3.0 video generation tasks. Create an API key in the console and select the wan-video key group before making a request.

Before you start

Image, video, and audio inputs must use publicly accessible URLs. resolution values are case-sensitive.

Model	Supported resolutions
`w3.0-video`	`480p`, `720p`, `1080p`
`w3.0-video-pro`	`1080p`, `2k`, `4k`

duration accepts 2–30 seconds and defaults to 5.

Text to video

curl --request POST 'https://api.tokenbyte.ai/v1/videos' \
  --header 'Authorization: Bearer sk-replace-with-your-key' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "w3.0-video-pro",
    "prompt": "A corgi runs through a futuristic neon city, cinematic camera movement, smooth and stable motion",
    "duration": 5,
    "resolution": "1080p",
    "ratio": "16:9",
    "audio": true,
    "prompt_extend": true,
    "seed": 123456
  }'

First-frame image to video

curl --request POST 'https://api.tokenbyte.ai/v1/videos' \
  --header 'Authorization: Bearer sk-replace-with-your-key' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "w3.0-video-pro",
    "prompt": "The person turns naturally toward the camera with smooth, cinematic movement",
    "first_frame": "https://example.com/first-frame.jpg",
    "duration": 5,
    "resolution": "1080p",
    "ratio": "16:9",
    "audio": true,
    "prompt_extend": true
  }'

First and last frames

curl --request POST 'https://api.tokenbyte.ai/v1/videos' \
  --header 'Authorization: Bearer sk-replace-with-your-key' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "w3.0-video-pro",
    "prompt": "Transition smoothly from daytime to night as the camera slowly moves forward",
    "first_frame": "https://example.com/first-frame.jpg",
    "last_frame": "https://example.com/last-frame.jpg",
    "duration": 5,
    "resolution": "1080p",
    "ratio": "16:9",
    "audio": false,
    "prompt_extend": true
  }'

Reference media to video

curl --request POST 'https://api.tokenbyte.ai/v1/videos' \
  --header 'Authorization: Bearer sk-replace-with-your-key' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "w3.0-video-pro",
    "prompt": "Keep the referenced character consistent and reproduce the action and camera rhythm",
    "reference_images": ["https://example.com/person.jpg"],
    "reference_videos": ["https://example.com/action.mp4"],
    "reference_audios": ["https://example.com/background.mp3"],
    "duration": 10,
    "resolution": "1080p",
    "ratio": "adaptive",
    "audio": true,
    "prompt_extend": true
  }'

Compatible `images` field

The first item in images becomes first_frame; the second becomes last_frame.

curl --request POST 'https://api.tokenbyte.ai/v1/videos' \
  --header 'Authorization: Bearer sk-replace-with-your-key' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "w3.0-video-pro",
    "prompt": "Create a natural, smooth transition between the two scenes",
    "images": [
      "https://example.com/first-frame.jpg",
      "https://example.com/last-frame.jpg"
    ],
    "duration": 5,
    "size": "1080p",
    "ratio": "16:9"
  }'

Check a task and download the video

Save the id returned by the create request. Download the content after the task reaches completed.

curl --request GET 'https://api.tokenbyte.ai/v1/videos/TASK_ID' \
  --header 'Authorization: Bearer sk-replace-with-your-key'

curl --location --request GET \
  'https://api.tokenbyte.ai/v1/videos/TASK_ID/content' \
  --header 'Authorization: Bearer sk-replace-with-your-key' \
  --output result.mp4

Successful submission response:

{
  "id": "public-task-id",
  "object": "video",
  "model": "w3.0-video-pro",
  "status": "queued"
}

Parameters

Parameter	Type	Required	Description
`model`	string	Yes	`w3.0-video` or `w3.0-video-pro`.
`prompt`	string	Yes	Video generation prompt.
`first_frame`	string	No	Public URL for the first-frame image.
`last_frame`	string	No	Public URL for the last-frame image.
`reference_images`	string[]	No	Public reference-image URLs.
`reference_videos`	string[]	No	Public reference-video URLs.
`reference_audios`	string[]	No	Public reference-audio URLs.
`resolution`	string	No	Output resolution; supported values depend on the model and are case-sensitive.
`duration`	number	No	2–30 seconds; default 5.
`ratio`	string	No	`adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, or `9:16`; default `adaptive`.
`audio`	boolean	No	Generate or preserve audio; an explicit `false` is forwarded upstream.
`seed`	integer	No	Random seed from 0 to 2147483647.
`prompt_extend`	boolean	No	Enable prompt expansion; an explicit `false` is forwarded upstream.