What can MiniMax H3 generate video from?

A text prompt, a starting image, a pair of first and last frames, or reference material. Reference mode accepts images, video, or audio in a single request.

What resolution and duration does MiniMax H3 output?

Output is mp4 at 2K resolution, from five to 15 seconds. Supported aspect ratios include 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, and the output adapts to the aspect ratio of a supplied image.

Can I combine reference material with first and last keyframes?

No. Reference and keyframe modes are mutually exclusive, so use one per request. Split the work across separate generations when you need both kinds of control.

How do I hold a subject consistent across clips?

Pass source material through `inputReferences` and refer to each item by its order in the prompt, such as `Image 1`. MiniMax H3 conditions the generation on that reference, which keeps a character or product steady across shots.

Why do my requests time out before the video finishes?

Video generation takes longer than a text completion. Raise `pollTimeoutMs` in the provider options and extend fetch timeouts in Node.js so the request survives until the clip is ready.

Can I try MiniMax H3 before integrating it?

Yes. Use the playground on this page to generate clips and compare prompts, durations, and aspect ratios.

Does MiniMax H3 support zero data retention?

Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

MiniMax

MiniMax H3

MiniMax H3 is MiniMax's video model. It generates 2K mp4 clips from a text prompt, a starting image, a pair of first and last frames, or reference images, video, and audio.

View API reference

Price: $0.04, Per second
Lowest available configuration

Get API key Read the docs

import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'minimax/minimax-h3',
  prompt: 'A serene mountain lake at sunrise.'
});

Read docs

Overview Playground Providers API Similar About FAQ

Copy link to headingPlayground

Try out MiniMax H3 by MiniMax. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

MiniMax H3

Images(optional)

Add up to 9 images

Videos(optional)

Add up to 3 videos

Prompt(optional)

End frame(optional)

Duration8s

Resolution

Auto

Aspect ratio

Your generated video will appear here.

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Promotional pricing ends on September 13, 2026.

Provider

Input	Output	Capabilities	ZDR	No Training	Free Tier	Release Date

MiniMax

50% off

Legal:Terms•Privacy

$0.02/img+1 more

$0.04/sec+2 more

07/30/2026

Getting started

Generate videos with MiniMax H3 using the experimental_generateVideo function from AI SDK 6 or later. AI Gateway handles routing and polls until the video is ready.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the video generation quickstart.

index.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'minimax/minimax-h3',
    prompt: 'A white kitten chases a butterfly across a sunlit garden.',
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Top-level parameters

Load the supported top-level parameters: prompt, duration, aspectRatio, and resolution. 2K is the only resolution H3 renders, and the named tier is accepted in place of the {width}x{height} form.

top-level-params.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'minimax/minimax-h3',
    prompt: 'A white kitten chases a butterfly across a sunlit garden.',
    duration: 5,
    aspectRatio: '16:9',
    resolution: '2048x2048',
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Parameter	Type	Required	Description
`prompt`	`string`	No	Text description of the video to generate.
`duration`	`number`	No	Video length in seconds. 4-15 seconds.
`resolution`	`string`	No	Resolution ('2048x2048').
`aspectRatio`	`string`	No	Aspect ratio ('21:9', '16:9', '4:3', '1:1', '3:4', '9:16').
`prompt.image`	`string`	No	URL of an image to animate as the first frame. Equivalent to a single `frameImages` entry with `frameType: "first_frame"`.
`frameImages`	`Array<{ image: string; frameType: 'first_frame' \| 'last_frame' }>`	No	First and last frames of the clip. A `last_frame` without a `first_frame` is dropped with a warning, and only images are accepted.
`inputReferences`	`Array<string \| { data: string; mediaType: string }>`	No	Reference images and videos to keep a subject or follow motion. Up to 9 images and 3 videos. Pass videos as `{ data, mediaType: "video/mp4" }` — a URL without a media type is treated as an image.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Image	jpg, jpeg, png, webp, heic, heif	url	9	30 MB	≥256px · ≤5760px · aspect 2:5–5:2
Video	h264, h265, mp4	url	3	50 MB	2-15s · ≥256px · ≤5760px
Audio	wav, mp3	url	—	15 MB	2-15s

Provider options

Pass MiniMax options under providerOptions.minimax. ratio overrides the top-level aspectRatio and is the only way to request adaptive.

Learn more in the AI SDK MiniMax video docs.

provider-options.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'minimax/minimax-h3',
    prompt: 'A white kitten chases a butterfly across a sunlit garden.',
    duration: 5,
    providerOptions: {
      minimax: {
        ratio: '16:9',
        resolution: '2K',
        aigcWatermark: false,
        pollIntervalMs: 10000,
        pollTimeoutMs: 600000,
      },
    },
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Pass MiniMax-specific options under providerOptions.minimax in your generateVideo call.

Parameter	Type	Required	Description
`ratio`	`'adaptive' \| '21:9' \| '16:9' \| '4:3' \| '1:1' \| '3:4' \| '9:16'`	No	Aspect ratio of the generated video. Overrides the top-level `aspectRatio`, and unlike it can be set to `adaptive`.
`resolution`	`'2K'`	No	Output resolution. H3 currently only supports `2K`, which is also the default.
`referenceAudioUrls`	`string[]`	No	Up to 3 reference audio URLs for reference-to-video. Must be paired with at least one reference image or video, or the audio is dropped with a warning. The only input that accepts `mm_file://` handles — pass images and videos as public URLs, data URIs, or binary data.
`aigcWatermark`	`boolean`	No	Whether to embed an AIGC watermark in the output. Defaults to `false`.
`pollIntervalMs`	`number`	No	How often to check task status. Defaults to `10000`.
`pollTimeoutMs`	`number`	No	Maximum wait time. Defaults to `600000` (10 minutes).

First and last frame

Control the transition by opening on one image and closing on another. The aspect ratio follows the input images, so an explicit aspectRatio is ignored.

first-last-frame.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'minimax/minimax-h3',
    prompt: 'The kitten crosses the garden and settles under the bench.',
    duration: 5,
    frameImages: [
      { image: 'https://example.com/start.jpg', frameType: 'first_frame' },
      { image: 'https://example.com/end.jpg', frameType: 'last_frame' },
    ],
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Reference to video

Keep a subject or follow motion from reference media, and optionally drive it with reference audio. Videos need an explicit media type; audio goes in providerOptions.minimax.referenceAudioUrls and has to accompany at least one image or video.

reference-to-video.ts

import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';

async function main() {
  const result = await generateVideo({
    model: 'minimax/minimax-h3',
    prompt: 'The same kitten, now padding along a rainy city street at night.',
    duration: 5,
    inputReferences: [
      'https://example.com/kitten.jpg',
      { data: 'https://example.com/motion.mp4', mediaType: 'video/mp4' },
    ],
    providerOptions: {
      minimax: {
        ratio: 'adaptive',
        referenceAudioUrls: ['https://example.com/voice.wav'],
      },
    },
  });

  // Save the generated video
  fs.writeFileSync('output.mp4', result.videos[0].uint8Array);

  console.log('Video saved to output.mp4');
}

main().catch(console.error);

Copy link to headingMore models by MiniMax

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

minimax/minimax-m3

0.7 s

166 tps

$0.26/M

$1.02/M

Read$0.06/M

—

05/31/2026

minimax/minimax-m2.7

205K

1.0 s

60 tps

$0.30/M+1 more

$1.20/M+1 more

Read$0.06/M

Write$0.38/M

—

03/18/2026

minimax/minimax-m2.7-highspeed

205K

0.9 s

55 tps

$0.60/M

$2.40/M

Read$0.06/M

Write$0.38/M

—

03/18/2026

minimax/minimax-m2.5

0.7 s

77 tps

$0.27/M+1 more

$0.95/M+1 more

Read$0.03/M

Write$0.38/M

—

02/12/2026

minimax/minimax-m2.1

205K

0.5 s

147 tps

$0.30/M

$1.20/M

Read$0.03/M

Write$0.38/M

—

12/23/2025

minimax/minimax-m2

205K

0.9 s

78 tps

$0.30/M

$1.20/M

Read$0.03/M

Write$0.38/M

—

10/27/2025

Copy link to headingAbout MiniMax H3

MiniMax H3, released July 30, 2026, is MiniMax's video generation model. It takes a text prompt, a starting image, a pair of first and last frames, or reference material, and returns mp4 at 2K resolution.

Four generation modes cover most production needs. Text-to-video builds a clip from a description alone. First-frame image-to-video animates a still and follows that image's aspect ratio. First-to-last keyframe transitions define both endpoints and let MiniMax H3 generate the motion between them. Multimodal reference-to-video conditions a generation on reference images, video, or audio in a single request. Reference and keyframe modes are mutually exclusive, so choose one per request.

Reference mode uses ordering to hold a subject steady. Pass source material through inputReferences and refer to each item by its position in the prompt, such as Image 1. That gives you a way to carry a character or product across several clips.

Clips run from five to 15 seconds at 2K resolution in mp4. Aspect ratios include 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, or the output adapts to a supplied image. Pick the ratio at request time instead of cropping afterward.

Call MiniMax H3 with generateVideo from the AI SDK, imported as experimental_generateVideo. Set the model to minimax/minimax-h3, pass your prompt plus optional aspectRatio and duration, and add inputReferences when you condition on source material. Generation runs longer than a text completion, so raise pollTimeoutMs for longer clips.

AI Gateway routes MiniMax H3 across MiniMax, tracks usage and cost per request, and handles retries and failover. The listed video rate is N/A, and the pricing panel on this page shows the current rate and unit. AI Gateway reflects provider pricing with no markup and charges no platform fee on inference.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Reference mode and keyframe mode can't be combined in one request, so decide which control you need before you build the call. Clip length caps at 15 seconds, so longer sequences take several generations stitched together downstream. Generation runs long enough that default timeouts cut it short, so raise pollTimeoutMs and extend fetch timeouts in Node.js. When you pass a starting image, the output follows that image's aspect ratio, so crop the source to the ratio you want to deliver.
Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use MiniMax H3

Best for

Text-to-Video Generation: Clips built entirely from a written scene description
Still Image Animation: Product or character stills animated from a single starting frame
Defined Frame Transitions: Motion generated between first and last frames you supply
Consistent Multi-Clip Subjects: Reference images, video, or audio that carry a subject across shots
Multi-Ratio Delivery: Vertical, square, and widescreen 2K output from one model

Consider alternatives when

Clips Beyond 15 Seconds: Longer sequences take several generations stitched together downstream
Reference Plus Keyframes: The two modes are mutually exclusive, so split them across separate requests
Resolution Above 2K: Output caps at 2K, so plan an upscaling step for larger delivery formats
Text and Code Workloads: MiniMax M3 covers reasoning and engineering tasks instead of video

Copy link to headingConclusion

MiniMax H3 covers text-to-video, image animation, keyframe transitions, and reference conditioning in one model, with 2K mp4 output from five to 15 seconds. Call it with generateVideo from the AI SDK using minimax/minimax-h3.

Copy link to headingFrequently Asked Questions

What can MiniMax H3 generate video from?
A text prompt, a starting image, a pair of first and last frames, or reference material. Reference mode accepts images, video, or audio in a single request.
What resolution and duration does MiniMax H3 output?
Output is mp4 at 2K resolution, from five to 15 seconds. Supported aspect ratios include 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, and the output adapts to the aspect ratio of a supplied image.
Can I combine reference material with first and last keyframes?
No. Reference and keyframe modes are mutually exclusive, so use one per request. Split the work across separate generations when you need both kinds of control.
How do I hold a subject consistent across clips?
Pass source material through inputReferences and refer to each item by its order in the prompt, such as Image 1. MiniMax H3 conditions the generation on that reference, which keeps a character or product steady across shots.
How do I call MiniMax H3 from the AI SDK?
Use generateVideo, imported as experimental_generateVideo, with the model set to minimax/minimax-h3. Pass your prompt plus optional aspectRatio and duration, and add inputReferences for reference-conditioned generations.
Why do my requests time out before the video finishes?
Video generation takes longer than a text completion. Raise pollTimeoutMs in the provider options and extend fetch timeouts in Node.js so the request survives until the clip is ready.
What does MiniMax H3 cost?
The listed video rate is N/A. Check the pricing panel on this page for the current rate and unit. AI Gateway reflects provider pricing with no markup and charges no platform fee on inference.
Can I try MiniMax H3 before integrating it?
Yes. Use the playground on this page to generate clips and compare prompts, durations, and aspect ratios.
Does MiniMax H3 support zero data retention?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

Your use is subject to MiniMax's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

MiniMax H3

Copy link to headingPlayground

Copy link to headingProviders

Getting started

Top-level parameters

Input limits

Provider options

First and last frame

Reference to video

Copy link to headingMore models by MiniMax

Copy link to headingAbout MiniMax H3

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use MiniMax H3

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions

Advanced

Getting started

Top-level parameters

Input limits

Provider options

First and last frame

Reference to video

Best for

Consider alternatives when

Copy link to headingFrequently Asked Questions