POST /v1/video/generations. Wan image models use POST /v1/images/generations and POST /v1/images/edits.
Supported Wan models
Current prices for these models are on aisa.one/models.
wan3.0-video is a single model for text-to-video, first-frame and first-and-last-frame image-to-video, reference-to-video, video editing and video extension, with output up to 30 seconds. The Wan 2.7 video models are split by input: t2v text-to-video, i2v image-to-video, r2v reference-to-video.
Official DashScope API compatibility
Paths, request bodies, responses and error codes are the official ones; see the Wan video generation API. This covers the Wan video models:
wan3.0-video, wan2.7-t2v, wan2.7-i2v and wan2.7-r2v.
oss:// temporary files and local files (file://) do not work.
Resolution
The default resolution follows the API you call and is what you are billed for:1080P on the DashScope API, as on the official API, and 720P on the AIsa video API. Set resolution to choose it. Wan 3.0 and Wan 2.7 requests that include size are rejected before anything is charged, because these models do not use size to choose the output resolution.