modelbenchmark.io

GLM 5.3

umans-glm-5-3

Compare

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-08-14
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.40
Output
$4.40
Cache read
$0.26
Cache write
free

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
umans-ai-coding-planfreefreefreefree1M131K—
umans-ai$1.40$4.40$0.26—1M131K—

Other listings of this model

this page is one of them

The corpus files GLM 5.3 under several keys. This page is the umans-glm-5-3 listing. The full record — every host, every price and every benchmark score — is on the main GLM 5.3 page.