Wan 3.0
Alibaba's Wan 3.0 API. Text-to-video and image-to-video up to 1080p, 2-30 seconds, with audio and first/last-frame control.
Pricing, live playground and model overview: Wan 3.0 API on YepAPI
/v1/media/queueOverview
Alibaba's Wan 3.0 — video generation up to 1080p and 30 seconds, with audio and first/last-frame control. Async operation — submit a job, poll for completion.
| Property | Value |
|---|---|
| Model ID | alibaba/wan-3.0 |
| Alias | wan-3 |
| Provider | Alibaba |
| Inputs | text-to-video, image-to-video |
| Resolutions | 480p, 720p, 1080p |
| Aspect Ratios | 16:9, 4:3, 1:1, 3:4, 9:16, adaptive |
| Duration | 2–30 seconds |
| Audio Generation | Supported (on by default) |
| Billing | Per job — priced when queued, charged only on success |
| Pricing | from $0.10/second |
Usage
All media models use the async job queue. Submit a job, then poll for the result.
Step 1: Submit Job
Text-to-Video
options.params passes this model's own parameters (see Model parameters).
const res = await fetch('https://api.yepapi.com/v1/media/queue', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'alibaba/wan-3.0',
prompt: 'A cinematic drone shot over a rugged coastline at golden hour',
options: {
aspectRatio: 'adaptive',
resolution: '1080p',
duration: '5',
generateAudio: true,
params: {
seed: 42,
},
},
}),
});
const { data } = await res.json();
// data.jobId — use this to poll for resultscurl -X POST https://api.yepapi.com/v1/media/queue \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "alibaba/wan-3.0", "prompt": "A cinematic drone shot over a rugged coastline", "options": {"aspectRatio": "adaptive", "resolution": "1080p", "duration": "5", "generateAudio": true, "params": {"seed": 42}}}'Image-to-Video
Pass a reference image via imageData. By default it is the first frame; set options.imageRole to last_frame to make it the final frame instead.
const res = await fetch('https://api.yepapi.com/v1/media/queue', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'alibaba/wan-3.0',
prompt: 'Animate this scene — clouds drifting, light changing',
options: {
resolution: '1080p',
duration: '5',
generateAudio: true,
imageRole: 'first_frame',
},
imageData: {
mimeType: 'image/jpeg',
base64: '...', // Base64-encoded image
},
}),
});curl -X POST https://api.yepapi.com/v1/media/queue \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "alibaba/wan-3.0", "prompt": "Animate this scene — clouds drifting, light changing", "options": {"resolution": "1080p", "duration": "5", "generateAudio": true, "imageRole": "first_frame"}, "imageData": {"mimeType": "image/jpeg", "base64": "..."}}'Step 2: Poll for Result
const status = await fetch(`https://api.yepapi.com/v1/media/status/${data.jobId}`, {
headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status — "pending" | "processing" | "completed" | "failed"
// job.result.video — { mimeType, base64 } when completedcurl https://api.yepapi.com/v1/media/status/JOB_ID \
-H "x-api-key: YOUR_API_KEY"Request Body
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
model | string | Yes | alibaba/wan-3.0 or alias wan-3 | — |
prompt | string | Yes | Text description of the video to generate | — |
options.aspectRatio | string | No | One of: 16:9, 4:3, 1:1, 3:4, 9:16, adaptive | adaptive |
options.resolution | string | No | 480p, 720p, 1080p | 1080p |
options.duration | string or number | No | 2 to 30 (seconds) | 5 |
options.generateAudio | boolean | No | Generate an audio track for the video | true |
options.imageRole | string | No | How to use the input image: first_frame or last_frame | first_frame |
options.params | object | No | Model-specific parameters under their own names: enable_thinking, seed. Unknown names return 400 | — |
imageData.mimeType | string | No | MIME type of input image (image/png, image/jpeg, image/webp) | — |
imageData.base64 | string | No | Base64-encoded input image for image-to-video generation | — |
Options are validated when you submit: an unsupported duration, resolution or value returns 400 naming the allowed values.
Model parameters
Pass these inside options.params.
| Parameter | Type | Allowed | Description | Default |
|---|---|---|---|---|
enable_thinking | boolean | — | Let the model reason over the prompt before generating | false |
seed | integer | 0–2147483647 | Random seed for reproducible results | — |
Features
- Text-to-video and image-to-video
- 480p, 720p or 1080p, 2–30 seconds
- Audio included at no extra cost
- First or last frame from
imageData
Pricing
| Resolution | Cost/sec |
|---|---|
| 480p | $0.10 |
| 720p | $0.20 |
| 1080p | $0.40 |
Example: 5-second 720p video = 5 × $0.20 = $1.00. Audio is included at no extra cost. Each job is priced when it's queued and charged only if it succeeds — failed or moderated jobs are free.
Video jobs can take several minutes to complete. When capacity is busy, jobs wait in the queue (status stays pending or processing) — no action needed. Results retained for 1 hour.
Powered by Alibaba's Wan 3.0 via our AI provider.