268 likesNew · 7d old
Flash-speed multimodal AI model hits 1M-token context window
What is MiniMax-M3.1-Flash?
MiniMax-M3.1-Flash is a 428-billion-parameter mixture-of-experts model that accepts text, images and video and returns text. Sparse attention and DSpark speculative decoding keep inference efficient despite a context window of up to one million tokens.
Who it is for
Developers of AI agents, code assistants, or security automation can leverage its strong coding and cybersecurity scores while staying budget-friendly.
How to try it
Visit https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash and use the hosted inference API.