🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
B

Wan 3.0

AlibabaModel IDwan3.0-video
B

Wan 3.0

AlibabaModel IDwan3.0-video

Wan3.0-Video is an all-in-one multimodal video generation model from Alibaba Cloud. It supports text, image, video, audio, file, and web-link inputs for text-to-video, first/last-frame image-to-video, reference-based generation, video editing, and video extension. It supports native audio-video generation, 480P/720P/1080P output, and videos up to 30 seconds.

ModeText / Image / Audio / Video → Video
Input price$0.05 / second
Output priceUnknown
Context lengthUnknown

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Alibaba
Input modality
Text / Image / Audio / Video
Output modality
Video
Max output
Unknown

Pricing

ProviderBilling typePrice summary
Q
Qwen-Balanced
Per second
Input price$0.05per second
Completion price—
Cache read price—
Cache write price—
Q
Qwen-Custom
Per second
Input price$0.05per second
Completion price—
Cache read price—
Cache write price—

Integration

Code Example

curl http://127.0.0.1:4179/v1/services/aigc/video-generation/video-synthesis \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
wan-video

Supported Parameters

ParameterTypeDefaultDescription
string1080PVideo output resolution. Supported values: 480P, 720P, and 1080P. Default: 1080P.
stringadaptiveVideo aspect ratio. Supported values: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16. Default: adaptive.
integer5Video duration in seconds. Supported range: 2 to 30 seconds. Set to -1 to enable smart duration.
booleantrueWhether to generate audio with the video. Audio is enabled by default and does not affect pricing.
booleantrueWhether to enable intelligent prompt rewriting to improve generation quality.
booleanfalseWhether to add an "AI Generated" watermark to the output video.
integer-1Random seed used for video generation. Set to -1 to automatically generate a random seed.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.