Multimodal Video API
useCases.descriptions.multimodal-video
3 models
New
seedance
Seedance 2.5
Generate 4–30 second videos with synchronized audio, first/last frames and up to 30 image, 10 video and 10 audio references.
seedance
With video references, billed duration includes input and output seconds. Automatic duration is settled using actual consumption.
New
seedance
Seedance 2.0
Seedance 2.0 is ByteDance's multimodal AI video model on KIE, combining text prompts with optional image, video, and audio references for controllable cinematic video generation.
seedance
No-video-reference pricing: $0.095/s @480p, $0.205/s @720p, $0.51/s @1080p. Video-reference requests: $0.0575/s @480p, $0.125/s @720p, $0.31/s @1080p, billed on input + output seconds.
New
wan
Wan 3.0
Generate 2–30 second videos from text, frames, image/video/audio references, documents or public webpages.
wan
With video references, billed duration includes input and output seconds. Automatic duration is settled using actual consumption.