About this model
MiniMax H3 Max Turbo is the text-to-video entry in the newest tier of MiniMax's H3 video family, dated September 2026. It sits above the original MiniMax H3 and its MiniMax H3 Enhanced refresh, and pairs with the image-driven MiniMax H3 Max Turbo (image-to-video) released the same day.
The H3 line is described by MiniMax as a general-purpose, omni-modal generative system: the Hugging Face model card states that it accepts a mixed context of text, images, video and audio, and produces video with native stereo audio at up to 2K resolution and durations up to about 15 seconds, with base weights published under MiniMax's community license. MiniMax's API documentation exposes the H3 and H3 Max checkpoints through a single video generation endpoint covering text-to-video, first/last-frame image-to-video, and reference-to-video.
Relative to the standard MiniMax H3 Max from late August 2026, Turbo is a separate Turbo-labelled variant of the Max tier listed alongside standard H3 Max, rather than a different input or output envelope. Sibling variants MiniMax H3 Max (image-to-video) and MiniMax H3 Max R2V handle image and reference-conditioned generation, while earlier MiniMax H3 (image-to-video) and MiniMax H3 R2V variants cover the first generation. MiniMax has not published detailed public benchmark figures specific to the Turbo tier, so this entry stays to documented specifications.
This About section is AI-generated from public sources (Claude Opus 5), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.
Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 4h ago