Uses text, images, videos, and audio as creative guidance.
Back to models
Multimodal references Flexible video generation
Seedance
Seedance 2.0
Rich multimodal video creationInputAudioImageTextVideoOutputVideo
API formatOpenAI
A production video generation model for text, image, video, and audio-guided creation.
seedance-2.0Input price$7.2115per million tokens
Output price$7.2115per million tokens
Context window--Maximum context per request
Max output--
BillingPer token
HealthNo dataNo performance samples in the last hour
Model details
Capabilities, benchmarks, and typical use
Seedance 2.0 supports text-to-video and multimodal video creation with image, video, and audio references. Output quality and billing depend on the requested resolution and whether video input is included, so the fixed original price fields remain null until an operator defines a product-specific display price.
Supports text-to-video and reference-driven video workflows.