Video models - Chenvoya API documentation

The three models share one API key and one set of request parameters; put the model ID in the model field of the body.

Available models

Model	Model ID	Resolution	Duration (s)
Seedance 2.0	`dreamina-seedance-2-0-260128`	480p · 720p · 1080p	4–15, default 5
Seedance 2.0 Fast	`dreamina-seedance-2-0-fast-260128`	480p · 720p	4–15, default 5
Seedance 2.0 Mini	`dreamina-seedance-2-0-mini-260615`	480p · 720p	4–15, default 5

Seedance 2.0 Fast and Seedance 2.0 Mini accept only 480p or 720p as resolution.

Inputs

A request has at most 16 content items: a text prompt, plus up to 9 images, 3 reference videos and 3 reference audio clips, with at most 15 materials in all.
A first-frame request takes one image and a first-and-last-frame request two, with at most one first_frame and one last_frame.
Each reference video or audio clip lasts 2–15 seconds; the videos together and the audio clips together each stay within 15 seconds. Reference audio needs a reference image or video.
Images and audio can be HTTPS links, asset:// references or base64 data URIs; videos can be HTTPS links or asset:// references. See Generate a video.

Outputs

Parameter	Values	Default
`duration`	Whole seconds from 4 to 15	`5`
`resolution`	`480p` · `720p` · `1080p`	`720p`
`ratio`	`adaptive` · `21:9` · `16:9` · `4:3` · `1:1` · `3:4` · `9:16`	`adaptive`
`generate_audio`	`true` · `false`	`false`
`watermark`	`true` · `false`	`false`
`seed`	An integer from -1 to 4294967295; -1 means random	`-1`
`return_last_frame`	`true` · `false`	`false`

Charges

Usage is recorded in meters such as video_tokens: funds for the upper bound are reserved at creation and the task is settled on actual usage, as How billing works explains. List prices are on the Pricing page; your team's prices are in the console.

Next steps

Generate a videoRequests for text to video, first frames, first and last frames, reference images and reference media.How billing worksFunds for the upper bound are reserved at creation and settled on actual usage; failed and cancelled tasks are free.Create a video taskSubmit a prompt with optional images, videos or audio to create an asynchronous generation task; the task ID and the reserved amount come back at once.