MiniMax
MiniMax: H3
minimax/hailuo-3
MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and video-to-video motion transfer. The model is suited for commercial creative workflows across advertising, e-commerce, gaming, and interface design, with native audiovisual output for reference-driven generation.
Input
$0
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
Not published
tokens
Video output · Token reference fields do not establish an output-unit price.
Model facts
Author
MiniMax
Tokenizer
Other
Modality
Text + Image + Audio + Video -> Video
Created
Jul 29, 2026
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · TextInput · ImageInput · VideoInput · AudioOutput · Video
Generation controls
Max tokensTemperatureTop p