Skip to main content
MiniMax H3 supports text-to-video, image-to-video, and reference-to-video generation in one asynchronous API. It accepts first and last frames, reference images, reference video, and reference audio, with 4-15 second output at 768P or 2K. Choose either first-and-last-frame guidance or multimodal references; these input workflows cannot be combined.

Model ID

Pass this exact public ID in the top-level model field.

Supported modes

  • text_to_video
  • image_to_video
  • reference_to_video

Inputs

  • Text
  • Image
  • Video
  • Audio

Outputs

  • Video

Capabilities

  • Text-to-video
  • Image-to-video
  • Reference-to-video

Additional capabilities

  • Text-to-video
  • First-and-last-frame control
  • Reference images
  • Reference video
  • Reference audio
  • 2K output
  • Callback task updates

Technical details

Availability and final customer prices can change. Check the Dashboard model catalog before production use.
See the API reference overview for authentication, request conventions, and response schemas.