MiniMax H3 now available on AI Gateway

MiniMax H3 is now available on AI Gateway.

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 reference-to-video, conditioning a generation on reference images, video, or audio in a single request. Reference and keyframe modes are mutually exclusive. Output is mp4 at 2K resolution, from 5 to 15 seconds, in aspect ratios including 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, or adaptive to a supplied image.

To use MiniMax H3, set model to minimax/minimax-h3 in the AI SDK:

1
import { experimental_generateVideo as generateVideo } from 'ai';
2

3
const { videos } = await generateVideo({
4
  model: 'minimax/minimax-h3',
5
  prompt: 'A white kitten chases a butterfly across a sunlit garden.',
6
  aspectRatio: '16:9',
7
  duration: 5,
8
  providerOptions: {
9
    minimax: {
10
      pollTimeoutMs: 600000,
11
    },
12
  },
13
});

Pass a starting image with the prompt, and the model animates it following the image's aspect ratio.

1
import { experimental_generateVideo as generateVideo } from 'ai';
2

3
const { videos } = await generateVideo({
4
  model: 'minimax/minimax-h3',
5
  prompt: {
6
    image: firstFrameUrl,
7
    text: 'The camera slowly pulls back to reveal the full landscape.',
8
  },
9
  duration: 5,
10
});

Supply reference images, video, or audio as source material, and refer to each by its order in the prompt for reference to video output.

1
import { experimental_generateVideo as generateVideo } from 'ai';
2

3
const { videos } = await generateVideo({
4
  model: 'minimax/minimax-h3',
5
  prompt: 'Keep the subject from Image 1 consistent while they walk through a sunlit garden.',
6
  duration: 5,
7
  inputReferences: [imageUrl],
8
});

View all video models on AI Gateway. Try MiniMax H3 in the model playground.