modelbenchmark.io

MiniMax M2.7 Turbo

MiniMax · minimax-m2-7-turbo

Compare

Efficient MiniMax model for quick assistance, coding, and routine automation

Specification

most-agreed values

Context
205K
Max output
131K
Released
2026-03-18
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.60
Output
$2.40
Cache read
$0.06

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$0.38$1.70$0.07—197K197K—
nano-gpt · minimax$0.60$2.40$0.06—205K131K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02nano-gpt · minimaxCache read$0.30
2026-10-19nano-gpt · minimaxCache read$0.06

More from MiniMax

most-hosted first