modelbenchmark.io

GLM 5 Original Thinking

Zhipu · glm-5-original

Compare

GLM-5 original with extended thinking capabilities for complex reasoning.

Specification

most-agreed values

Context
200K
Max output
128K
Released
2026-02-11
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.00
Output
$3.20
Cache read
$0.20

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · thinking$1.00$3.20$0.20200K128K
nano-gpt · z-ai$1.00$3.20$0.20200K128K

More from Zhipu

most-hosted first