models/minimax/minimax-m2
M
minimax·active

MiniMax: MiniMax M2

minimax's mid-tier model. Context window: 205K tokens.

Overall score
4.46
/5.00 · ranked #67
Input
$0.255
per 1M tokens
Output
$1.02
per 1M tokens
Context
205K
tokens
Blended
$0.829
3:1 out:in ratio

Price drops, new benchmarks, model updates. Stay current on MiniMax: MiniMax M2.

One email per change. Unsubscribe anytime.

modelpicker.aipowered by live benchmark data

Scores by test

Methodology →
Structured Output
4.0
Strategic Analysis
5.0
Constrained Rewriting
4.0
Creative Problem Solving
4.0
Tool Calling
5.0
Faithfulness
5.0
Classification
4.0
Long Context
4.0
Safety Calibration
4.0
Persona Consistency
5.0
Agentic Planning
4.0
Multilingual
5.0
Tabular Data
5.0

What you need to know

MiniMax M2 distinguishes itself through high reliability in complex execution, specifically scoring 5/5 in strategic analysis, tool calling, and faithfulness. These metrics indicate a model that follows instructions precisely and minimizes hallucinations, making it a strong candidate for autonomous agent workflows where accuracy and tool integration are critical.

The model offers a massive 205K context window and maintains a high performance floor across all tested categories, with no score falling below 4/5. This consistency extends to specialized tasks like tabular data processing and multilingual support, both of which achieved perfect internal scores.

At a blended cost of $0.829/MTok, the model is priced competitively for its performance tier. It provides high-end reasoning and agentic capabilities without the premium pricing typically associated with top-tier proprietary models.

Use this model if you are building agents that require rigorous tool calling, strategic planning, or processing of large datasets in multiple languages. Skip this model if your primary requirement is highly nuanced creative rewriting or complex structured output, where it performs slightly below its own peak benchmarks.

Strengths — Top 3

Strategic Analysis5.0/5.0
Tool Calling5.0/5.0
Faithfulness5.0/5.0

Relative weaknesses — Bottom 3

Structured Output4.0/5.0
Constrained Rewriting4.0/5.0
Creative Problem Solving4.0/5.0

Similar models

NNex AGI: Nex-N2-Mini$0.0814.54GGoogle: Gemini 3.8 Flash$3.004.69OOpenAI: GPT-5.6 Luna Pro$4.754.69QQwen: Qwen3.8 Max$5.004.69