Spec sheet
| Field | Value | Provenance |
|---|---|---|
| Prompt character limit | 20,000 | Atlas Cloud ten prompt matched test |
| Duration range | 2 to 30 seconds, default 5 | Alibaba Cloud Model Studio guide |
| Resolution ceiling | 1080p (no 4K) | Alibaba Cloud Model Studio guide |
| Frame rate | 30 fps | Alibaba Cloud Model Studio guide |
| Audio | On by default, no price change | Alibaba Cloud Model Studio guide |
How to call text-to-video
curl -X POST "https://api.oneinfer.ai/v1/ula/generate-video" \
-H "Authorization: Bearer $ONEINFER_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "alibaba/wan-3.0-prime",
"prompt": "A quiet city street at golden hour as camera slowly pans up to the skyline",
"aspect_ratio": "16:9",
"resolution": "1080p",
"duration": 10
}'Ready to test the workflow?
Create account & add creditsWhat 20,000 characters buys
Prime handles long, over-specified, multi-shot briefs better than Seedance 2.5 and MiniMax H3 on a ten prompt matched test. The 20,000 character prompt limit is the highest in the routed video catalog; Seedance has no hard cap but is not consistently faithful past a few hundred words.
Frequently asked questions
How long can a Wan 3.0 Prime text-to-video be?
2 to 30 seconds. Default is 5 seconds. Passing -1 lets the model pick a duration from the prompt. 30 seconds is double the ceiling of MiniMax H3 and the published ceiling of Seedance 2.5.
Does Wan 3.0 Prime generate voice and music?
Yes. Audio is on by default at no extra cost. Disable with audio=false; the price does not change.
Where is the canonical Wan 3.0 Prime page on OneInfer?
The canonical model page with current pricing, providers, and capabilities is /models/alibaba/wan-3.0-prime. This page is a focused facet of that entity, not a replacement for it.
How should I treat benchmark or price claims on Prime?
Check each claim's provenance label and observed date. Vendor-reported, independently verified and derived numbers are shown as separate evidence classes on this hub.
How do I call Wan 3.0 Prime from the API?
POST to /v1/ula/generate-video with model "alibaba/wan-3.0-prime", a valid API key, and a prompt plus aspect_ratio and resolution. Reference items and document inputs are optional and are added as separate payload fields.
Put Wan 3.0 to work
Fund a controlled evaluation, send a reference frame or document, and measure quality and cost on your own workload.