MiniMax: MiniMax M2Active

minimax/minimax-m2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency. The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors. Benchmarked by Artificial Analysis, MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.

By:MiniMaxInput Type:Output Type:Publish time:2025-10-27

Providers

Route requests across multiple providers. Copy a provider slug to set your preference.

ProviderCache Hit RateContext

MiniMax

minimax

-$0.3/ M tokens$1.2/ M tokensRead:0.03/ M tokensWrite:0.375/ M tokens204.8K1.3s53.9tps

Uptime

24hours

Direct request success rate on AI Gateway and per-provider.

Throughput

24hours

P50 throughput on live AI Gateway traffic, in tokens per second (TPS).

Latency

24hours

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.

Activity

Token volume and request traffic to this model over time.

Token Consumption

Related Models

More models from MiniMax

MiniMax: MiniMax H3

2.74Ktokens

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and video-to-video motion transfer. The model is suited for commercial creative workflows across advertising, e-commerce, gaming, and interface design, with native audiovisual output for reference-driven generation.

MiniMax: MiniMax M3

24.43Btokens

MiniMax M3 is the first open-weights flagship that brings coding, agentic reasoning, million-token context, and native multimodality together in one model. It handles autonomous task decomposition, tool use, and multi-step reasoning with ease — and writes code that's meant to ship, not code that just runs. Built on MiniMax's proprietary Sparse Attention architecture, M3 natively supports million-token context windows for long-horizon agents, large codebases, and long-video understanding. Its multimodality isn't bolted on — it's trained in from day one, with text and vision deeply aligned at the semantic level.

MiniMax: MiniMax M2.7 highspeed

1.46Btokens

M2.7 highspeed: Same performance, faster, more agile