modelbenchmark.io

GLM 5.3 Flash FP4

Zhipu · glm-5-3-flash-fp4

Compare

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-08-26
Knowledge cutoff
Retires
Open weights
yes
Input
text, image, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.50
Cache read
free

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
coralbricks$0.15$0.50free1M131K

More from Zhipu

most-hosted first