MiniMax-M3 — это амбициозная мультимодальная ИИ-модель, способная работать с текстом, фото и видео на уровне топовых решений рынка. Благодаря инновационной архитектуре MSA, нейросеть поддерживает гигантское контекстное окно до 1 млн токенов, показывая отличные результаты в кодинге и автономной работе.
MiniMax M3 is officially released today. M3 reaches frontier-level performance on specialized tasks such as coding and agentic work. It uses MSA (MiniMax Sparse Attention), a new attention architecture proposed by our team, and supports ultra-long context windows of up to 1M tokens. To much anticipation, it is also a natively multimodal model that supports image and video input and can operate a desktop computer. These three capabilities are now table stakes for closed-source frontier models. M3 is currently the first and only open-weight model to bring all three together.