modelbenchmark.io

MiniMax-M2.5-highspeed

MiniMax · minimax-m2-5-highspeed

Compare

High-speed MiniMax model for low-latency coding and agent workflows

Specification

minimax listing

Context
205K
Max output
131K
Released
2026-02-13
Knowledge cutoff
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · minimax list price

Input
$0.60
Output
$2.40
Cache read
$0.06
Cache write
$0.375

Available from 12 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
minimaxvendor$0.60$2.40$0.06$0.375205K131K
minimax-cn-coding-planfreefreefreefree205K131K
minimax-coding-planfreefreefreefree205K131K
llmgateway$0.60$2.40$0.03$0.375205K131K
llmgateway-providers · minimax$0.60$2.40$0.03205K131K
merge-gateway · minimax$0.60$2.40$0.06$0.375205K8K
minimax-cn$0.60$2.40$0.06$0.375205K131K
novita$0.60$2.40$0.03205K131K
novita-ai · minimax$0.60$2.40$0.03205K131K
orcarouter · minimax$0.60$2.40$0.03$0.375205K131K
vercel · minimax$0.60$2.40$0.03$0.375205K131K
qiniu-ai · minimax205K128K

More from MiniMax

most-hosted first