Models

As a next-generation Flash model, M3.1 Flash delivers a generational leap in agentic tasks, coding, Computer Use and cybersecurity, while making online inference nearly three times faster and reducing usage costs by 70%.

MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.

Korean short-form meme-tone assistant built on minimax-m3:cloud.

MiniMax-M2.7 REAP 139B-A10B Uncensored MoE (139B total, 10B active, i1-IQ2_M + GGUF <think> patch). 130.9 tok/s Decode, 4121 tok/s Prefill, 85.7% Precision, 0.0% Hallucination (6/6), 100% Zero-Refusal. License: MiniMax Open / Apache-2.0.