What is Wan 3.0 Video API?
Wan 3.0 — Alibaba Cloud's all-in-one reference-based video generation model. It supports text-to-video, image-to-video (first/last frame), and reference-based generation from images, videos, audio, documents, and web links, producing videos up to 30 seconds long.
Technical Specifications
- Supported inputs: Image, Text (plus video, audio, document, and web-link references)
- Output: Video
- Max duration: 30 seconds
Performance Benchmarks
[embed]
Wan 3.0 Video API Pricing
- 480p: $0.065 per second
- 720p: $0.13 per second
- 1080p: $0.26 per second
Where to Use Wan 3.0 Video
All-in-one video generation
Generate from text, animate an image, or guide output with reference images, video, audio, documents, or web links — all from one model.
Long-form clips
Produce videos up to 30 seconds long in a single generation.
Reference-driven production
Use existing assets (images, video, audio, documents, links) as generation references instead of prompting from scratch.
Code Sample
[embed]
Wan 3.0 Video is documented as suited to advertising and marketing videos, including product demos and branded promotional content.
It is also documented for film-related work such as films, short dramas, and other cinematic or previsualization use cases.
It is documented for social content creation, including short-form social media clips and creator-focused videos.
It is documented for training and explainer content, including educational videos and corporate or internal communication videos.
import requests response = requests.post( "https://api.aimlapi.com/v2/video/generations", headers={ "Authorization": "Bearer <YOUR_AIMLAPI_KEY>", "Content-Type": "application/json", }, json={'model': 'alibaba/wan-3-0-video', 'prompt': 'Describe what you want the model to generate.', 'image_url': 'https://example.com/input.jpg', 'duration': 5}, ) print(response.json())
const response = await fetch('https://api.aimlapi.com/v2/video/generations', {
method: 'POST',
headers: {
'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "alibaba/wan-3-0-video",
"prompt": "Describe what you want the model to generate.",
"image_url": "https://example.com/input.jpg",
"duration": 5
}),
});
console.log(await response.json());
curl --request POST \ --url 'https://api.aimlapi.com/v2/video/generations' \ --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \ --header 'Content-Type: application/json' \ --data '{"model": "alibaba/wan-3-0-video", "prompt": "Describe what you want the model to generate.", "image_url": "https://example.com/input.jpg", "duration": 5}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
480p $0.065/sec, 720p $0.13/sec, 1080p $0.26/sec.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Wan 3.0 Video This page | All-in-one video generation |
Wan 3.0 Video takes image, text as input and returns video.
Wan 3.0 Video became available on August 6, 2026.
Wan 3.0 Video is priced at $0.065–$0.26 / sec (by resolution).
Wan 3.0 Video is billed per generation — a fixed charge per output rather than by prompt length.
Yes, Wan 3.0 Video accepts image input as well as a text prompt.
Wan 3.0 Video was built by Alibaba Cloud.
Use alibaba/wan3.0-video as the model id on AI/ML API.
Yes. Wan 3.0 Video is served through AI/ML API, so the same key and endpoint format used for other models applies.
-min.webp){kind=small}
