modelbenchmark.io

GLM-5.2

Zhipu · glm-5-2-fp8

Compare

Open flagship GLM for long-horizon coding agents and million-token context work

Specification

most-agreed values

Context
203K
Max output
203K
Released
2026-06-13
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.20
Output
$4.20
Cache read
$0.26
Cache write
free

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
gmicloud · zai-org$0.979$3.08$0.182—1M131K—
ambient · zai-org$1.20$4.20$0.26free203K203K—

Other listings of this model

this page is one of them

The corpus files GLM-5.2 under several keys. This page is the glm-5-2-fp8 listing. The full record — every host, every price and every benchmark score — is on the main GLM-5.2 page.

More from Zhipu

most-hosted first