MiniMax-M3 is a multimodal foundation model from MiniMax. It accepts text, image, and video input with text output, has a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context. That costs roughly 1/20 of the previous generation at 1M tokens, with much faster prefill and decode and the same quality across most tasks. Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration through an interactive user-simulator framework, it is aimed at sustained, multi-step tasks rather than single-turn execution.
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. Open weights are planned.