modelbenchmark.io

GLM 5.2 Short Flex

Zhipu · glm-5-2-short-flex

Compare

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

Specification

most-agreed values

Context
200K
Max output
32K
Released
2026-06-17
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.9425
Output
$2.925
Cache read
$0.0943

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
neuralwatt$0.9425$2.925$0.0943200K32K

More from Zhipu

most-hosted first