MiniMax M3 is a frontier-level open-weight AI model released May 31, 2026 by Chinese lab MiniMax. It is the first open-weight model to combine 1M token context, native multimodal input, and frontier coding capabilities in a single architecture.

How do I use MiniMax M3 with OpenClaw?

OpenClaw v2026.6.1 adds native MiniMax M3 provider support. Configure your API key in ~/.openclaw/openclaw.json under the minimax provider. Model references follow the form minimax/MiniMax-M3.

What MiniMax models does OpenClaw support?

OpenClaw materializes MiniMax-M3, MiniMax-M2.7, and MiniMax-M2.7-highspeed as chat models when API key configuration entries are present.

What is the context window for MiniMax M3?

MiniMax M3 supports a 1 million token context window, which is the largest among open-weight models as of June 2026.

How does MiniMax M3 compare to other OpenClaw providers?

MiniMax M3 offers competitive coding performance (SWE-Bench Pro 59.0, surpassing GPT-5.5 on some benchmarks) with the advantage of being open-weight and having 1M context, making it attractive for cost-conscious OpenClaw users.

← Back to dashboard

clawsmith.com/signal/openclaw-minimax-m3-1m-context-provider-june-2026

📈 TrendsWide OpenLive

OpenClaw v2026.6.1 Adds MiniMax M3: First Open-Weight 1M-Context Multimodal Model Provider

OpenClaw v2026.6.1 adds native MiniMax M3 provider support. MiniMax M3, released May 31 by Chinese AI lab MiniMax, is the first open-weight model to combine frontier-level coding, 1M token context, and native multimodal input. OpenClaw materializes MiniMax-M3, M2.7, and M2.7-highspeed as chat models.