modelbenchmark.io

MiniMax-M2

MiniMax · minimax-m2

Compare

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Specification

minimax listing

Context
205K
Max output
131K
Released
2025-10-27
Knowledge cutoff
2024-10
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · minimax list price

Input
$0.30
Output
$1.20
Cache read
$0.03
Cache write
$0.375

Quality

1 benchmark · 1 source

Composite
68th
percentile of 334 scored models
Rank
109 / 334
±0.10 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
coding50th1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified61.0default · mini-SWE-agentSWE-bench

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 23 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
minimaxvendor$0.30$1.20205K131K
minimax-cn-coding-planfreefree205K131K
minimax-coding-planfreefree205K131K
nano-gpt · minimax$0.17$1.53$0.085200K131K
llmgateway$0.20$1.00$0.03197K131K
llmgateway-providers · minimax$0.20$1.00$0.03197K131K
openrouter$0.255$1.02205K205K
openrouter · minimax$0.255$1.02205K131K
edenai · minimax$0.30$1.20205K131K
fireworks_ai$0.30$1.204K4K
huggingface · minimaxai$0.30$1.20205K131K
kilo · minimax$0.30$1.20205K131K
merge-gateway · minimax$0.30$1.20$0.03$0.375205K8K
minimax · minimax$0.30$1.20$0.03$0.375200K8K
minimax-cn$0.30$1.20205K131K
novita$0.30$1.20$0.03205K131K
novita-ai · minimax$0.30$1.20$0.03205K131K
ofox · minimax$0.30$1.20$0.03$0.375205K131K
vercel · minimax$0.30$1.20$0.03$0.375205K205K
zenmux · minimax$0.30$1.20$0.03$0.38204K64K
302ai$0.33$1.321M128K
cortecs$0.349$1.405400K196K
qiniu-ai · minimax200K128K

More from MiniMax

most-hosted first