MiniMax
Generate short videos and edit images through multimodal APIs
Standard H3 output
4–15 seconds; 768P or 2K
Other H3 variants have different limits.
Pricing
H3 video generation uses the pay-as-you-go API.
- Use text alone, guide the first and last frames, or supply reference media. Select the model and supported resolution for the job.
- Create a still from text or existing images, then set its dimensions for the intended layout.
- Keep in mind: H3 video requires pay-as-you-go API access; supported clip lengths and resolutions depend on the selected variant.
What is MiniMax?
MiniMax develops text and multimodal models with an API platform for developers. Its H3 video API creates short clips from prompts, first or last frames, or reference images, video and audio. The standard MiniMax H3 variant supports 4–15-second outputs at 768P or 2K; other variants have different limits.
For still images, H3 Image generates from text or edits using reference images with controllable output dimensions. H3 video uses pay-as-you-go API access and returns a task identifier for checking the generation result.
Direct a short video from prompts or references
- Prompt-to-video turns a text description into a clip without requiring an image input.
- First and last frames pair a prompt with start and end images to guide a transition.
- Multimodal references combine reference images, video or audio with a prompt to guide a new clip.
- Video task lookup checks the status and result of a generation by task ID within the past seven days.
Generate and edit still images
- Text-to-image and reference editing generate a still from a prompt or edit from one to 16 reference images.
- Image size controls set custom dimensions or an aspect ratio and area level for the intended layout.
User reviews
No reviews yet. Be the first to review this tool.
Log in to write a review.
Join the Aivolut newsletter
Occasional practical AI tips, app updates, and offers. Unsubscribe anytime.