modelbenchmark.io

GLM 5.3 Uncensored

Zhipu · glm-5-3-uncensored

Compare

An experimental uncensored version of the full GLM 5.3 reasoning model for chat, creative writing, coding, and tool use. It may show unusual behavior or inconsistent response quality.

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-09-26
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.25
Output
$2.25
Cache read
$0.30

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · z-ai$1.25$2.25$0.30—1M131K—

More from Zhipu

most-hosted first