modelgrep
M

MiniMax: MiniMax M2.1

minimax/minimax-m2.1

42nd smartest of 180ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
39.4
42nd of 180
Design Elo
1280
UI Component
Speed
129
36th fastest
Latency
1.1s
first token
Input price
$0.290
126th cheapest
Context
205K
197K max out

How it compares

Smarter than77%
of all ranked models
Faster than88%
of all ranked models
Cheaper than58%
of all ranked models

Overview

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

Benchmarks

independent · via OpenRouter
Artificial Analysis73th percentile
Intelligence Index
39.4
Coding Index
32.8
Agentic Index
47.4
GPQA Diamond
83%
Humanity's Last Exam
22%
SciCode
41%
Tau²-Bench (agentic)
85%
Design Arena · Elo9,380 tournaments
UI Component
1280
Data Viz
1250
Website
1246
3D
1246
codecategories
1242
Game Dev
1203
svg
1189

Providers & pricing (4)

ProviderIn $/MOut $/MUptime
AtlasCloudfp8$0.290$0.950
Novitafp8$0.300$1.20
Minimaxfp8$0.300$1.2097.7%
Minimaxfp8$0.300$2.40

Specifications

Context window205K
Max output197K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.030/M
ModeratedNo

MiniMax M2.1 FAQ

How much does MiniMax M2.1 cost?

MiniMax M2.1 costs $0.290 per million input tokens and $0.950 per million output tokens via OpenRouter, making it 126th cheapest of 298 paid models.

How smart is MiniMax M2.1?

MiniMax M2.1 scores 39.4 on the Artificial Analysis Intelligence Index, ranking 42nd of 180 benchmarked models, with a GPQA Diamond score of 83%.

How fast is MiniMax M2.1?

MiniMax M2.1 generates around 129 tokens per second with 1.1s time-to-first-token (p50), the 36th fastest tracked model.

What is MiniMax M2.1's context window?

MiniMax M2.1 supports a 205K-token context window and can output up to 197K tokens. It accepts text input.

Compare head-to-head