MiniMax: minimax-m2 API
MiniMax-M2 is a high-efficiency Mixture-of-Experts (MoE) model architected specifically for coding and agentic workflows. While boasting 230B total parameters, it only activates 10B per token, ensuring low latency and high throughput. Its standout feature is "Interleaved Thinking," where the model uses internal reasoning tags (<think>) to plan and self-correct during complex tasks. This makes it exceptionally robust for multi-step tool use, terminal-based coding, and long-horizon planning. It ranks as a top-tier open-weight model, rivaling proprietary giants in agentic benchmarks like VIBE and SWE-bench.
- Context window: 196,608 tokens
- Max output: 128,000 tokens
- Input: text
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- Released: 2025-10-27
- Knowledge cutoff: 2025-05-31
Frequently Asked Questions
What is the context window of minimax-m2?
minimax-m2 supports a context window of up to 196,608 tokens.
Does minimax-m2 support function calling?
Yes. minimax-m2 supports tool / function calling.
Does minimax-m2 support reasoning?
Yes. minimax-m2 is a reasoning-capable model.
What is the knowledge cutoff of minimax-m2?
The knowledge cutoff of minimax-m2 is 2025-05-31.