Wan 3.0 Pro API
Wan 3.0 Pro video generation from text, first and last frames, or multimodal references. 2–30 seconds with native audio at 480p, 720p, 1080p, 2K or 4K.
- Text to video
- Image to video
Starting at
$0.086
per second of output
Wan 3.0 Pro playground
Input
Text description. Required unless at least one media input is supplied. In reference mode you can address assets positionally with "图N / 视频N / 音频N" labels; indices run per media type.
Image URLs without explicit roles. In the frame family the first item is the start frame and an optional second is the end frame; in the reference family every item is a reference image (up to 10).
Reference videos, up to 5 clips of 1-15s each (total <= 15s). Input video duration plus the requested output duration must stay within 30 seconds.
Reference audio, up to 5 clips of 1-15s each (total <= 15s).
Reference document driving the generation (docx/xlsx/pptx/pdf/txt/md and similar, <=100MB, <=50 pages). Cannot be combined with linkUrl. A prompt is optional when this is supplied.
Public, login-free web page to turn into a video. Cannot be combined with fileUrl.
Runs are charged to your balance.
Output

Output will appear here.
Fill in the fields, review the cost and run the model. Your result will appear here; you do not need a separate API key to try it in your browser.
Wan 3.0 Pro API pricing
| Option | Price per second |
|---|---|
| 480p | $0.086 |
| 720p | $0.172 |
| 1080p | $0.286 |
| 2K | $0.343 |
| 4K | $0.429 |
Quick start
Full API reference →1curl -X POST https://api.api-stock.com/api/v1/generation/create \2 -H "Authorization: Bearer $API_STOCK_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "wan3.0-video-pro",6 "input": {7 "size": "adaptive",8 "duration": 5,9 "audio": true,10 "resolution": "480p",11 "promptExtend": true12 }13 }'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | No | — | Text description. Required unless at least one media input is supplied. In reference mode you can address assets positionally with "图N / 视频N / 音频N" labels; indices run per media type. |
imageUrls | string[] | No | — | Image URLs without explicit roles. In the frame family the first item is the start frame and an optional second is the end frame; in the reference family every item is a reference image (up to 10). |
imageWithRoles | object[] | No | — | Images with explicit roles. Use this when you need first/last frame or reference images stated outright rather than inferred from order. |
videoUrls | string[] | No | — | Reference videos, up to 5 clips of 1-15s each (total <= 15s). Input video duration plus the requested output duration must stay within 30 seconds. |
audioUrls | string[] | No | — | Reference audio, up to 5 clips of 1-15s each (total <= 15s). |
fileUrl | string | No | — | Reference document driving the generation (docx/xlsx/pptx/pdf/txt/md and similar, <=100MB, <=50 pages). Cannot be combined with linkUrl. A prompt is optional when this is supplied. |
linkUrl | string | No | — | Public, login-free web page to turn into a video. Cannot be combined with fileUrl. |
generationType | string | No | — | How bare imageUrls are classified: frame (first/last frame) or reference. Omit to let it be inferred — reference when the request already carries reference-family inputs, frame otherwise.One of: frame, reference |
size | string | No | adaptive | Aspect ratio. `adaptive` lets the model pick one from the inputs.One of: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 |
duration | number | No | 5 | Duration in seconds (2-30). Billing is per second at the resolution's rate. With reference videos, total input video duration plus this value must be at most 30 seconds. |
audio | boolean | No | true | Include an audio track in the output. |
resolution | string | No | 480p | Output resolution. Billing is per second, including reference video seconds.One of: 480p, 720p, 1080p, 2K, 4K |
promptExtend | boolean | No | true | Let the model expand the prompt. Set false to keep the literal prompt. |
Frequently asked questions
How much does Wan 3.0 Pro cost?
Wan 3.0 Pro starts at $0.086 per second of output through the API Stock API. You pay per use from a single prepaid balance — there is no subscription — and the final price scales with parameters such as resolution or duration.
When was Wan 3.0 Pro released?
Wan 3.0 Pro was released on October 11, 2026. It is available through the API Stock API with the same key and prepaid balance as every other model.
How do I get an API key for Wan 3.0 Pro?
Sign up for API Stock, top up your balance using an available payment method and create an API key in the dashboard — it takes a couple of minutes and needs no contract. The same key works with every model in the catalog, so there is no separate key to obtain for Wan 3.0 Pro.
How do I call the Wan 3.0 Pro API?
Send a POST request to https://api.api-stock.com/api/v1/generation/create with your API key and the model id "wan3.0-video-pro". The call returns a task id you poll, or a webhook callback when the result is ready. A ready-to-run example is in the quick start above.
What input parameters does Wan 3.0 Pro accept?
Wan 3.0 Pro accepts 13 input parameters. Their types, defaults and allowed values are listed in the parameters table above.
What happens if a Wan 3.0 Pro request fails?
API Stock automatically retries the request on a reserve provider. If every provider fails, the charge is refunded to your balance.
Can I use Wan 3.0 Pro with the same API key as other models?
Yes. Every model on API Stock — video, image, music and chat — shares one API key and one prepaid balance, so you can switch to Wan 3.0 Pro without new credentials.
Other Video models
- FLUX 3 VideoBlack Forest Labs$0.06/ second
- Kling 3.0 Motion ControlKling$0.065/ second
- Seedance 1.5 ProByteDance$0.065/ generation
- Wan 3.0 Video PrimeAlibaba$0.066/ second
- Wan 2.7 VideoAlibaba$0.086/ second
- Seedance 2.0ByteDance$0.091/ second
- Kling 3.0Kling$0.096/ second
- Veo 3.1 LiteGoogle$0.1/ generation
- Seedance 2.5ByteDance$0.137/ second
Read next
Guides
- Text to videoWhich text-to-video model fits the shot you have in mind, prompts that actually work, and the full API run from create to finished file.9 min read
- Image to videoTurning a still into a shot — which model to animate it with, first and last frame control, motion transfer, and the prompts that keep the subject intact.8 min read
- Going to productionKey handling, webhooks over polling, idempotency, terminal states, retry policy by error code, balance monitoring, rate limits and media storage.10 min read

