Video Generation Models

Explore currently public text-to-video and image-to-video models, task endpoints, and specification limits on Infistar.

Currently public models

8 models
  • wan3.0-videoFrom ¥0.2634 / second (480p)
  • wan2.7-t2vFrom ¥0.6 / second (720p)
  • wan2.7-i2vFrom ¥0.6 / second (720p)
  • doubao-seedance-2-5-260628From ¥39.9 / 1M output tokens (480p)
  • doubao-seedance-2-0-260128From ¥16 / 1M output tokens (4k)
  • doubao-seedance-2.0-miniFrom ¥8.8667 / 1M output tokens (480p)
  • doubao-seedance-2-0-fast-260128From ¥14.6667 / 1M output tokens
  • MiniMax-H3From ¥0.1631 / second (768p)