MiniMax launches M3.1 Flash with faster inference and lower token prices

MiniMax says M3.1 Flash improves coding, computer use, and security work, exceeds 200 output tokens/s in typical use with sparsity optimization, and scores 82% on CyberGym. The API costs $0.15 per million input tokens, $0.60 per million output tokens, and $0.015 per million cached input tokens. MiniMax said weights would follow the API launch.

Visit original source