Skip to content
SFAI
SFAI / MODEL PROFILE

MiniMax H3 Reference to Video

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.

Developer
minimax
Input modalities
image
Output modalities
video
Context tokens
Not reported
Latest price observation
2026-09-28
Lowest paired standard token quote
Not available

Dated price and provider records

Provider and channelInputOutput or native rateUnit and statusSource and observation
fal.aifalNot token-priced$0.05secondspriced · USDfal2026-09-28

These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.