seedance-2.0 · ByteDance · video · 3 modes: text-to-video, image-to-video, reference-to-video.
This page reflects the current catalog. Inputs, allowed values, limits and prices can change as the model evolves; the field names and their meaning do not. For the exact schema at any time, your agent calls
get_model with the mode.Text To Video
Modetext-to-video. Text to video.
Input
Pricing
~7.32 credits per second at 720p (Seedance 2.0; rate varies by resolution; output + input-video seconds both billed). Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded. For the exact price of a request, useestimate_generation.
Example
The arguments ofgenerate_media:
Image To Video
Modeimage-to-video. Animate a first frame, or go from a first to a last frame.
Input
Pricing
~7.32 credits per second at 720p (Seedance 2.0; rate varies by resolution; output + input-video seconds both billed). Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded. For the exact price of a request, useestimate_generation.
Example
The arguments ofgenerate_media:
Reference To Video
Modereference-to-video. A video guided by references: up to 9 images, 3 videos and 3 audios.
Input
References: up to 15: 9 images, 3 videos of 1.8 to 15.2 s (15 s in total), 3 audio files (15 s in total). Assets, URLs and elements are accepted.
Pricing
~7.32 credits per second at 720p (Seedance 2.0; rate varies by resolution; output + input-video seconds both billed). Settled on actual usage: the reserve is adjusted to what the model produced, and the difference refunded. For the exact price of a request, useestimate_generation.
Example
The arguments ofgenerate_media:
