🎉 Get Free $5 on Signup!
Models
Enterprise
Subscribe
Resource
Activity
Documentation
Console

/alibaba/wan3.0-video-prime

B

Alibaba: Wan 3.0 Prime

Wan3.0-Video-Prime is the speed-optimized version of Wan3.0-Video from Alibaba Cloud. It supports multimodal inputs including text, image, video, audio, files, and links for text-to-video, image-to-video, reference-based generation, video editing, and extension. It supports native audio-video generation, 480P/720P/1080P output, and videos up to 30 seconds.

Modetext、image、audio、video → video
Input price$0.0636 per M tokens
Output price—
Context length
Listed at2026-08-20T00:00:00Z

Alibaba

Latency—
Throughput—
Upload rate—
Context length—
Max output—
Input price$0.0636per second
Output price—per second
Cache read—per second
Cache write—per second

Performance

Avg TPS—
Avg latency—
Avg success rate—
TPS—
TTFT—
Latency—
Success rate—

Success rate

Speed

Code Example

curl ${API_BASE_URL}/v1/services/aigc/video-generation/video-synthesis \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video-prime",
    "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.
integer5Video duration in seconds. Supports videos up to 30 seconds.
stringadaptiveVideo aspect ratio. Uses adaptive mode by default when supported.
booleantrueWhether to generate native audio together with the video.
booleantrueWhether to enable intelligent prompt enhancement for video generation.
booleanfalseWhether to add an AI-generated watermark to the output video.
integer-1Random seed used for video generation. Set to -1 to use a random seed.

Rate Limits

GroupRPMTPMRPD

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.

Pricing

ProviderBilling typePrice summary
Q
Qwen
Per second
Input price$0.0636per second
Completion price$—per second
Cache read price$—per second
Cache write price$—per second