minimax/hailuo-h3
Hailuo H3 builds video from a mix of reference images, clips and audio, addressed by position in the prompt.
Model Inputs
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.
Random seed. A random seed is selected when omitted.
Whether to expand the prompt with a vision language model before generation.
The aspect ratio of the generated video.
Subject / style reference images (.jpg/.png/.webp), up to 9. Address them in the prompt as Image 1, Image 2, …
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Motion reference clips (.mp4/.mov/.webm), 2-15 seconds each, up to 3. Address them in the prompt as Video 1, Video 2, …
Drag & drop a file here, or click to select
Supported formats: MP4, WEBM, MOV (max 100MB)
Drag & drop a file here, or click to select
Supported formats: MP4, WEBM, MOV (max 100MB)
Drag & drop a file here, or click to select
Supported formats: MP4, WEBM, MOV (max 100MB)
Reference audio clips (.mp3/.wav/.flac/.m4a/.ogg), 2-15 seconds each, up to 3. Address them in the prompt as Audio 1, Audio 2, …
Drag & drop a file here, or click to select
Supported formats: MP3, WAV, M4A, FLAC, OGG (max 10MB)
Drag & drop a file here, or click to select
Supported formats: MP3, WAV, M4A, FLAC, OGG (max 10MB)
Drag & drop a file here, or click to select
Supported formats: MP3, WAV, M4A, FLAC, OGG (max 10MB)
Result
Pricing
minimax/
hailuo-h3
You are billed for what this model actually produces — by the second — so a shorter request costs less and you never pay for idle time.
For example, a request of 60 seconds costs about $7.80.
You are charged for what the request actually produces, so the final amount scales with the seconds you use.
| Provider | Price ($) | Saving (%) |
|---|---|---|
| Synexa | $0.05 | - |
| fal | $0.65 | 92.3% |
Comparison prices are for an equivalent request.
Readme
Hailuo H3 is a multimodal reference-to-video model. Supply up to 9 reference images, 3 reference video clips and 3 reference audio clips, then address them in the prompt by modality and order - Image 1, Video 2, Audio 1 and so on.
All references together must not exceed 12 files, and audio cannot be the only reference supplied. 480P and 768P are generated natively; 2K and 4K are upscaled from a 768P base. The first 5 reference images are free upstream, each additional one costs extra.