MiniMax

2026•MiniMax

MaxClaw v2.5-Preview

OpenClaw × MiniMax Agent × M2.5, now fully unlocked. No deployment. No extra API fees. 7×24 across Telegram / WhatsApp / Slack / Discord. Ready-made MiniMax Expert ecosystem. Upgraded built-in tools for real work.

AI Writing Assistant

MiniMax M2.5 v2.5

Paid

AI Agents

Agentic AI

MiniMax M2.5 is a state-of-the-art model designed for coding, agentic tool use, search, and office work. It has been extensively trained with reinforcement learning in complex real-world environments, achieving top scores in various benchmarks.

Advanced coding capabilities with state-of-the-art performance

Efficient task decomposition and reasoning

High-speed execution of complex agentic tasks

Version2.5

RegionChina

2026•MiniMax

MiniMax M3 vM3

MiniMax M3 is the first open-weight frontier model to combine frontier-level coding, 1M token context via MSA (MiniMax Sparse Attention), and native multimodality (image + video input + desktop control) in a single model. It surpasses GPT-5.5 and Gemini 3.1 Pro on SWE-Bench Pro, beats Opus 4.7 on SVG-Bench, and leads on Claw-Eval for autonomous agents.

MSA (MiniMax Sparse Attention) enables true 1M token context — a new sparse attention architecture that partitions KV into blocks more precisely than DSA/MoBA; per-token compute at 1M context is 1/20 of the previous generation, with 9× prefill speedup and 15× decode speedup versus full attention, while matching full attention on nearly all capability benchmarks

Frontier coding and agentic performance — SWE-Bench Pro: 59.0%, Terminal-Bench 2.1: 66.0%, MCP Atlas: 74.2%, KernelBench Hard: 28.8%; demonstrated 24-hour autonomous CUDA kernel optimization improving Hopper FP8 hardware utilization from 7.6% to 71.3% (9.4× speedup) across 147 benchmark submissions with zero human intervention

First open-weight model with all three frontier capabilities — native multimodality (image/video input, desktop computer control) trained from Step 0 with interleaved text+image data scaled to 100T tokens; independently reproduced an ICLR 2025 Outstanding Paper over 12 hours, 18 commits, and 23 experimental figures; available via MiniMax Code, Token Plan, and API

VersionM3

RegionChina