ByteDance: Seedance 2.0

bytedance/seedance-2.0

Released Apr 15, 2026from $7 /M tokens

Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency, visual style, and camera movement from reference material. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024

ByteDance: Seedance 2.0

bytedance/seedance-2.0

Released Apr 15, 2026from $7 /M tokens

Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency, visual style, and camera movement from reference material. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024

Sample code and API for Seedance 2.0

OpenRouter normalizes requests and responses across providers for you.

OpenRouter supports video generation models that can create videos from text prompts. Submit a generation request with your prompt and model, then poll the returned URL to check the status. Once complete, the response includes URLs to download the generated video. Learn more about video generation.

Using third-party SDKs