ModelBeat
Models/MiniMax-M2.1
All models
M
minimax/minimax-m2.1

MiniMax-M2.1 is MiniMax’s open-weights AI model, released Dec 23, 2025. It costs $0.30/M input and $1.20/M output tokens, and handles a 205K-token context window.

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.

Context
205K
Input
$0.30 / 1M
Output
$1.20 / 1M
Released
Dec 23, 2025
Modalities
texttext

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where MiniMax-M2.1 lands among all models tracked on Model Beat.

42.0
Intelligence Index
Epoch AI
42nd percentile of tracked models
43.0
Coding Index
Epoch AI
43rd percentile of tracked models
41.0
Agentic Index
Epoch AI
41st percentile of tracked models

Reasoning

3 evals
GPQA Diamond83.0%

Graduate-level scientific reasoning

Humanity's Last Exam22.2%

Frontier of human expert knowledge

MMLU-Pro87.5%

Broad expert knowledge

Coding

3 evals
LiveCodeBench81.0%

Contamination-free coding

SciCode40.7%

Scientific research coding

WebDev Arena1392

Human-rated web development

Math

1 evals
AIME 2024/202582.7%

Olympiad-qualifier math

Agentic & Tools

2 evals
Terminal-Bench36.6%

Command-line agentic tasks

τ²-bench85.4%

Tool-agent-user reliability

Compare MiniMax-M2.1 with

Frequently asked questions

What is MiniMax-M2.1?

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.

Who created MiniMax-M2.1?

MiniMax-M2.1 is an AI model developed by MiniMax, part of the MiniMax family, released Dec 23, 2025.

How much does MiniMax-M2.1 cost?

MiniMax-M2.1's list price from MiniMax is $0.30 per million input tokens and $1.20 per million output tokens.

What is MiniMax-M2.1's context window?

MiniMax-M2.1 supports a context window of up to 205K tokens.

How does MiniMax-M2.1 perform on benchmarks?

On standardized evaluations tracked by Epoch AI, MiniMax-M2.1 scores 87.5% on MMLU-Pro, 81.0% on LiveCodeBench, 85.4% on τ²-bench.

Is MiniMax-M2.1 open source?

MiniMax-M2.1 is released with open weights (Open weights (restricted use)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Jul 30, 2026.