← Back to all generators

minimax/h3

Generate videos with MiniMax H3, a multimodal video model from MiniMax that supports text-to-video, first- and last-frame image-to-video, and reference-based video generation.

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

promptrequiredstring

Text prompt for generation

durationinteger

Output duration in seconds.

Default: 5
456789101112131415
first_frame_imagestring

First frame image for video generation. The output video will have the same aspect ratio as this image.

last_frame_imagestring

Last frame image for video generation. The final frame of the output video will match this image.

ratiostring

Output aspect ratio. Required for text-to-video; adaptive for image-to-video.

Default: "16:9"
adaptive21:916:94:31:13:49:16
reference_audio_urlsarray

Public URLs for up to 3 reference audio clips.

Default:
reference_image_urlsarray

Public URLs for up to 9 reference images.

Default:
reference_video_urlsarray

Public URLs for up to 3 reference videos, 15 seconds total. Reference video seconds are billed at the same rate as output seconds.

Default:
resolutionstring

Output resolution.

Default: "2K"
768P2K
Version: 150d557601a8Updated: 11/7/2026108.4K runs