MiniMax H3 Lite

MiniMax H3 Lite is the lower-cost version of minimax/h3, the multimodal video model from MiniMax. It does the same things as H3 at a lower price and a lower maximum resolution, which makes it a good fit for trying out ideas, drafting shots, and generating lots of videos.

What it does

• Text-to-video: describe a scene and get a video back.
• Image-to-video: give it a first frame, a last frame, or both, to control how the video starts and ends.
• Reference generation: give it reference images, videos, or audio to guide the character, motion, camera, style, voice, or editing rhythm.

Videos can be 4 to 15 seconds long, at 480P or 768P.

How it compares to H3

If you need 2K output, use minimax/h3.

Inputs

• prompt: the text describing the video.
• first_frame_image: optional first frame. When you provide one, the video uses the image’s aspect ratio.
• last_frame_image: optional last frame.
• reference_image_urls: optional public URLs for up to 9 reference images.
• reference_video_urls: optional public URLs for up to 3 reference videos.
• reference_audio_urls: optional public URLs for up to 3 reference audio clips. Reference audio needs to be combined with a reference image or video.
• duration: video length in seconds, from 4 to 15.
• resolution: 480P or 768P (the default).
• ratio: aspect ratio for text-to-video and reference generation. Image-to-video ignores this and uses the input image’s aspect ratio.

Pricing

MiniMax H3 Lite is billed per second of video it generates: $0.025 per second at 480P and $0.04 per second at 768P. A 10-second 768P video costs $0.40.