MiniMax H3 now available on AI Gateway
MiniMax H3 video model now live on Vercel's AI Gateway — text-to-video, keyframe transitions, multimodal reference conditioning all in one API.
Why it matters
A capable video generation model (2K, 5-15s, multimodal conditioning) is now accessible through a major API platform, expanding practitioner options for embedding video AI into applications without building custom infrastructure.
The key facts
10 to knowMiniMax H3 generates 2K video from text, images, keyframes, or reference material (video/audio)
Supports first-to-last keyframe transitions and multimodal reference-to-video conditioning
Output: mp4, 5–15 seconds, aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, or adaptive
Available via Vercel AI Gateway with SDK integration (model=minimax/minimax-h3)
Accessible in model playground for testing
MiniMax H3 generates 2K video from text, images, keyframes, or reference material
Supports text-to-video, image-to-video, keyframe-to-keyframe transitions, and multimodal reference conditioning
Output: MP4, 2K resolution, 5–15 seconds, multiple aspect ratios (21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive)
Available via Vercel AI Gateway with SDK integration (model: minimax/minimax-h3)
Published: July 30, 2026
Go to the source
Vercel Blogvercel.com
Publisher excerpt: is now available on AI Gateway.MiniMax H3 H3 generates 2K video from a text prompt, a starting image, a pair of first and last frames, or reference material. Alongside text-to-video and first-frame image-to-video, the model supports first-to-last keyframe transitions and multimodal…