MiniMax M2

Overview

MiniMax M2 is an open-source large language model by MiniMax, built for agents and coding tasks. It delivers state-of-the-art tool use, reasoning, and search performance while maintaining exceptional cost-efficiency and speed, priced at just 8% of Claude 3.5 Sonnet’s cost and running at nearly double its inference speed (≈100 TPS). Designed for end-to-end agentic workflows, it excels at long-chain tool calling across Shell, Browser, Python, and other MCP tools. While slightly behind top overseas models in programming, it ranks among the best domestic models and top five globally on the Artificial Analysis benchmark. M2 powers the MiniMax Agent platform, available in Lightning Mode for fast tasks and Pro Mode for complex multi-step reasoning, and its weights, API, and deployment guides are freely available on Hugging Face, vLLM, and SGLang.

MiniMax M2 was released on October 27, 2025. API access is available through MiniMax, Novita.

Benchmarks

MiniMax M2 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Fri Jan 02 2026

Pricing

Pricing, performance, and capabilities for MiniMax M2 across different providers:

Provider	Input ($/M)	Output ($/M)	Max Input	Max Output	Latency (s)	Throughput	Quantization	Input	Output
MiniMax	$0.30	$1.20	1.0M	1.0M	4.0	70.0 c/s	—	Text Image Audio Video	Text Image Audio Video
Novitabf16	$0.30	$1.20	204.8K	131.1K	—	—	bf16	Text Image Audio Video	Text Image Audio Video

Price Comparison for MiniMax M2

Price per 1M input tokens (USD), lower is better

llm-stats.com - Fri Jan 02 2026

Throughput Comparison for MiniMax M2

Tokens per second, higher is better

llm-stats.com - Fri Jan 02 2026

Latency Comparison for MiniMax M2

Time to first token (s), lower is better

llm-stats.com - Fri Jan 02 2026

API Access