MiniMax M3.1 Flash
MiniMax has launched M3.1 Flash, a new AI model optimized for agentic tasks, coding, and cybersecurity with significantly reduced costs and increased inference speeds. The model utilizes aggressive sparsity to achieve high token-per-second performance.
Why it matters
The release emphasizes the ongoing industry race to lower the cost of AI inference while maintaining high performance for complex, multi-step agentic tasks.
Today, we officially roll out MiniMax M3.1 Flash .
Space Bunny 🐰, which processed more than 200 trillion tokens while operating anonymously, was an early version of MiniMax M3.1 Flash.
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%.
M3.1 Flash improves across a broad range of benchmarks, reaching the level of leading models in complex agentic tasks (cowork), computer use, software development (coding), and cybersecurity.
We have further optimized M3.1 Flash’s inference efficiency through more aggressive sparsity. In everyday use, output speeds can reach 200+ TPS (tokens per second), with median (P50) speeds consistently reaching 170+ TPS.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in