TRStart creating
Menu

MiniMax H3

MiniMax H3 is a frontier video model. This endpoint generates 2K video from multimodal references up to 9 images for subject and style, 3 video clips for motion, and 3 audio clips each cited in the prompt by order, keeping subjects consistent while following the referenced motion and audio.

Input

Fields marked * are required. Review the price before generating.

Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.

The duration of the video in seconds.

The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result.

The aspect ratio of the generated video.

URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files.

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Additional settings

Random seed. A random seed is selected when omitted.

Tips and requirements

How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'fast' returns in about a second. 'balanced' picks per request. 'quality' spends up to ~30s on a richer prompt.

Tips and requirements

Optional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Cannot be combined with reference audio. Longer clips are trimmed to the generated video's length, keeping the beginning; shorter clips are padded with silence. The clip is resampled to 32 kHz stereo and replaces the output soundtrack without changing playback speed. Accepts an HTTP(S) URL or a base64 data URI.

Uploading a file needs an account. Create accountMP3, WAV · up to 50 MB

Price$1.03 / run

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use MiniMax H3

Getting started

Plan the subject’s action, camera movement and sound. Separate image and reference operations work from supplied visuals.

Review your result

Watch for changing identities, disappearing objects and sound that misses the action.

Inputs and settings

Raywake requires prompt and exposes duration from 5–15 seconds, aspect_ratio and resolution. Use the current operation’s fields when requesting a quote.

Image-to-video offers image_url and end_image_url; reference-to-video offers reference_image_urls. Keep these inputs in their corresponding operation.

We use analytics cookies. Privacy policy