MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency. Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance. To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://ask-coreai.com).
With CoreAI, you can start chatting with MiniMax: MiniMax M2.1 instantly — no separate subscription needed. CoreAI bundles access to MiniMax: MiniMax M2.1 along with 300+ other AI models from Minimax and other providers like OpenAI, Anthropic, Google, Meta, and more.
Chat with MiniMax: MiniMax M2.1 and 300+ other AI models — all in one app.