Video
Text-to-video
Image-to-video

Standard & Paid Price

The locked value is the exact Paid Price after your first top-up; the discount is derived from the two absolute prices
Unlock with a top-up
MeterStandard PricePaid PriceSave
Model price$0.100 / second$0.085 / second-15%

Description

Alibaba Wan3.0 (Video) — an all-in-one video model that unifies text-to-video, image-to-video and reference-to-video behind a single endpoint. Generates H.264 MP4 at 480P, 720P or 1080P, up to 30 seconds, from a prompt and an optional first-frame image URL. Billed per second of generated video against the vendor's own ladder: 720P is the base rate, 480P is charged at half of it and 1080P at double. A request that does not name a resolution is produced at 1080P by the model and is charged at that tier. Reference video and reference audio inputs exist in the vendor's model but are not carried on this endpoint.

Capabilities

Tasks
text-to-video, image-to-video

Decision evidence

Wan 3.0 Video is Alibaba's all-in-one video model, on Alibaba Cloud Model Studio since 2026-08-06, that covers text-to-video, first-frame and first-and-last-frame video, multimodal reference, video editing and extension in one model, generating up to 30 seconds at 30 fps with native dialogue, music and sound effects at 480P, 720P or 1080P. Alibaba has published no Wan 3.0 weights. In the reviewed side-by-side test it beat MiniMax H3 on fast action, physics and camera motion but still struggled with dialogue-driven scenes.

2026-09-25 · Markdown evidence · JSON data

API endpoints

  • POST /v1/videos (openai-video)