Models

MiniMax-M2

MiniMax-M2 is a multimodal large language model developed by MiniMax, designed for strong performance in reasoning, coding, and general language understanding tasks. It likely supports long-context interactions and is optimized for both performance and cost-efficiency.

CodingReasoningMultimodal
Input / 1M tokens
$0.30
Output / 1M tokens
$1.20
Output tokens/s
77.76
First-token seconds
1.29s
Supported plans
7

Benchmark history

Evaluations

15

TAU2

Measured Jul 10, 2026Source

Score

0.87

Terminalbench Hard

Measured Jul 10, 2026Source

Score

0.26

Lcr

Measured Jul 10, 2026Source

Score

0.61

Ifbench

Measured Jul 10, 2026Source

Score

0.72

Aime 25

Measured Jul 10, 2026Source

Score

0.78

Scicode

Measured Jul 10, 2026Source

Score

0.36

Livecodebench

Measured Jul 10, 2026Source

Score

0.83

Hle

Measured Jul 10, 2026Source

Score

0.13

Gpqa

Measured Jul 10, 2026Source

Score

0.78

Mmlu Pro

Measured Jul 10, 2026Source

Score

0.82

Artificial Analysis Math Index

Measured Jul 10, 2026Source

Score

78.3

Artificial Analysis Intelligence Index

Measured Jul 10, 2026Source

Score

28.3

Tau Banking

Measured Jul 10, 2026Source

Score

0.09

Terminalbench V2 1

Measured Jul 10, 2026Source

Score

0.55

Artificial Analysis Coding Index

Measured Jul 10, 2026Source

Score

52.6

Plan availability

Products and plans that support this model

2
Apertis Coding Plan

Apertis Coding Plan

Apertis Coding Plan is a subscription-based AI coding service providing unified access to 30+ AI models (GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, and more) through a single API key. Designed for developers using coding agents like Claude Code, Cursor, Cline, and OpenCode, it offers predictable monthly pricing, free prompt caching, auto-failover, and quota-based billing across OpenAI, Anthropic, Google, and other providers.

User ratings

Loading ratings...

Discussion

Thinking... Make sure you are connected to GitHub server