Back to Models

Minimax m2

MiniMax M2 is a 230B (10B active) MoE model. It is highly efficient, designed for coding and agentic workflows with low latency.

Thinking Mode
Parameters
230000000000 B
Context
204,800 tokens
Released
Invalid Date

Leaderboards

Performance vs. Industry Average

Intelligence

Minimax m2 is of lower intelligence compared to average (4.1), with an intelligence score of 4.0.

Price

Minimax m2 is cheaper compared to average ($4.91 per 1M Tokens) with a price of $0.71 per 1M Tokens.

Latency

Minimax m2 has a higher average latency compared to average (120.77s), with an average latency of 136.96s.

P99 Latency

Minimax m2 has a higher P99 latency compared to average (354.03s), taking 472.81s to receive the first token at P99 (TTFT).

Context Window

Minimax m2 has a smaller context window than average (347k tokens), with a context window of 205k tokens.

Minimax m2 - AutoBench