Video
MiniMax H3
MiniMax H3 is a frontier video model. This endpoint generates video from a text prompt alone, rendering at 2K in durations from 5 to 15 seconds across seven aspect ratios.
- Text to video
- Image to video
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for MiniMax H3. Review your own result before publishing.
Use MiniMax H3 through the API.
Start with this model ID for the endpoint featured on this page:
minimax/h3/text-to-video
Available modes
- text-to-video ·
minimax/h3/text-to-video - image-to-video (image-to-video) ·
minimax/h3/image-to-video - image-to-video (reference-to-video) ·
minimax/h3/reference-to-video
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.