MiniMax M3

• 🆕 MiniMax's latest M-series frontier model for coding and agents.
• 📏 Provider reports up to one-million-token context via new sparse attention.
• 👁️ Natively multimodal: accepts text, image, and video input.
• 🔧 Built for tool use, function calling, and agentic workflows.
• 🧠 Targets agentic reasoning and structured task execution.
• 🌐 Capabilities include web search and code-optimized generation.
• 🏢 From MiniMax, founded 2022, building multimodal foundation models.
• 📚 M2.7 and M2.5 remain available for existing workflows.

MiniMax

MiniMax is an AI company building generative models across multiple modalities, with a focus that spans both language understanding and audio creation. Their rapid release cadence in early 2026—delivering several new models within just a few months—reflects…

MiniMax M3 is the newest entry in MiniMax's "M" series of text/reasoning models, positioned by the company as a frontier model for coding, agentic workflows, and complex reasoning. According to MiniMax, M3 reaches frontier capability on coding and agentic tasks, introduces a new MiniMax Sparse Attention (MSA) mechanism supporting up to a one-million-token context, and is natively multimodal. Its API supports text, image, and video input through OpenAI- and Anthropic-compatible interfaces.

The headline architectural change versus its predecessors is MSA. Where the prior MiniMax M2.7 was a mixture-of-experts model with 230 billion total parameters, 10 billion active per token, 256 experts, and a roughly 200K-token context, M3's sparse-attention design is the provider's reported route to handling far longer documents, codebases, and multi-step agent sessions more efficiently. MiniMax presents M3 as the successor while keeping M2.7 and earlier models available for existing pipelines.

For context on the lineage, MiniMax reported that MiniMax M2.5 scored 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp (with context management), and completed SWE-Bench Verified evaluation 37% faster than M2.1. MiniMax has not published comparable official M3 benchmark figures here, so specific scores are omitted pending the model card.

Note that MiniMax's documentation cites the one-million-token figure for M3, whereas this catalog entry lists a 198,000-token window; treat the provider's specification as authoritative and verify the exact limit at launch.