MiniMax M2-her

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles and can learn from example dialogue to better match the style and pacing of your scenario.

MiniMax M2

MiniMax M2 is a high-efficiency 10B activated parameter model optimized for coding agents, compile-run-fix loops, and long-horizon reasoning. It balances responsiveness with strong SWE-Bench and Terminal-Bench results, excels at code generation, planning, and tool use, and preserves reasoning continuity across multi-step tasks.

MiniMax Image-01

MiniMax's first image generation model with character reference support for consistent character generation across multiple images. Produces high-quality, detailed images with strong compositional abilities.

MiniMax M3

MiniMax-M3 is a multimodal foundation model from MiniMax. It accepts text, image, and video inputs and produces text output, with a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context, roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks. Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, it is oriented toward sustained, multi-step tasks rather than single-turn execution.

MiniMax M2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.

MiniMax M2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

MiniMax M2-her

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles and can learn from example dialogue to better match the style and pacing of your scenario.

MiniMax M2

MiniMax M2 is a high-efficiency 10B activated parameter model optimized for coding agents, compile-run-fix loops, and long-horizon reasoning. It balances responsiveness with strong SWE-Bench and Terminal-Bench results, excels at code generation, planning, and tool use, and preserves reasoning continuity across multi-step tasks.

MiniMax Image-01

MiniMax's first image generation model with character reference support for consistent character generation across multiple images. Produces high-quality, detailed images with strong compositional abilities.

MiniMax M3

MiniMax-M3 is a multimodal foundation model from MiniMax. It accepts text, image, and video inputs and produces text output, with a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context, roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks. Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, it is oriented toward sustained, multi-step tasks rather than single-turn execution.

MiniMax M2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.

MiniMax M2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.