modelgrep
M

MiniMax: MiniMax M2

minimax/minimax-m2

57th smartest of 178ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
36.1
57th of 178
Design Elo
1193
UI Component
Speed
161
26th fastest
Latency
338ms
first token
Input price
$0.255
116th cheapest
Context
205K
197K max out

How it compares

Smarter than68%
of all ranked models
Faster than91%
of all ranked models
Cheaper than61%
of all ranked models

Overview

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Benchmarks

independent · via OpenRouter
Artificial Analysis65th percentile
Intelligence Index
36.1
Coding Index
29.2
Agentic Index
47.5
GPQA Diamond
78%
Humanity's Last Exam
13%
SciCode
36%
Tau²-Bench (agentic)
87%
Design Arena · Elo5,275 tournaments
UI Component
1193
Game Dev
1187
Website
1187
codecategories
1187
Data Viz
1185
3D
1178
svg
1157

Providers & pricing (4)

ProviderIn $/MOut $/MUptime
AtlasCloudfp8$0.255$1.00
Minimaxfp8$0.255$1.02
Google$0.300$1.20
Novitafp8$0.300$1.20

Specifications

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

MiniMax M2 FAQ

How much does MiniMax M2 cost?

MiniMax M2 costs $0.255 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 116th cheapest of 298 paid models.

How smart is MiniMax M2?

MiniMax M2 scores 36.1 on the Artificial Analysis Intelligence Index, ranking 57th of 178 benchmarked models, with a GPQA Diamond score of 78%.

How fast is MiniMax M2?

MiniMax M2 generates around 161 tokens per second with 338ms time-to-first-token (p50), the 26th fastest tracked model.

What is MiniMax M2's context window?

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

Compare head-to-head