modelbenchmark.io

Z.ai: GLM 5.3 Prime

Zhipu · glm-5-3-prime

Compare

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-09-23
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.80
Output
$8.80
Cache read
$0.56

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo · z-ai$2.80$8.80$0.56—1M131K—
openrouter$2.80$8.80$0.56—1M131K—
openrouter · z-ai$2.80$8.80$0.56—1M131K—

More from Zhipu

most-hosted first