MiniMax M2 is a high-efficiency large language model built for coding and agentic workflows. With 10 billion activated parameters (230 billion in total), it delivers exceptional performance in multi-file edits, coding-run-fix loops, and test-validated repairs. The model supports a context window of 204,800 tokens and ranks among the top five globally in intelligence, achieving similar scores to Claude Sonnet 4.5 while being highly cost-effective.