Video generation / ByteDance

Doubao-Seedance-2.0-fast

API name: seedance-2.0-fast-idle

MultimodalVideo Generation

Overview

Seedance 2.0 Fast is a new-generation multimodal video creation model launched by the Doubao Large Model Team. It inherits the core functions and advantages of the Seedance 2.0 model while offering faster generation speeds.

Model type: Video generation
Input: Text / Image / Video / Audio
Output: Video
Endpoints: video_generation

Video pricing (by resolution)

Resolution	No video input	With video input
720p	$0.0056/1K	$0.0033/1K

Billed per token; unit price varies by resolution and whether video input is included. Default group price (other groups converted by discount).

Capabilities

支持图片、视频、音频等多模态素材参考生成视频
具备视频编辑与延长能力
模型对物理规律的理解持续深化、更贴合真实世界
能严格遵循指令细节约束，从而保障专业级叙事的可信度

Code example

Call with seedance-2.0-fast-idle :

curl https://www.starunion.net/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-fast-idle",
    "prompt": "A silver wolf running across a snowfield under the moonlight, cinematic shot",
    "duration": 5,
    "resolution": "1080p",
    "ratio": "16:9"
  }'

# Video generation is async - poll with the id returned above
curl https://www.starunion.net/v1/video/generations/TASK_ID \
  -H "Authorization: Bearer YOUR_API_KEY"