modelbenchmark.io

GLM 5 Turbo

Zhipu · glm-5-turbo

Compare

Faster GLM-5 lane for coding agents that need lower latency

Specification

most-agreed values

Context
203K
Max output
131K
Released
2026-03-16
Knowledge cutoff
2025-01-01
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.20
Output
$4.00
Cache read
$0.24
Cache write
free

Available from 20 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
zai-coding-planfreefreefreefree200K131K
zhipuai-coding-planfreefreefreefree200K131K
302ai$0.72$3.20200K131K
zenmux · z-ai$0.88$3.48200K128K
crossmodel · z-ai$0.90$3.70$0.18$0.90200K128K
cortecs$1.186$3.955$0.296$1.544203K203K
edenai · zai$1.20$4.00$0.24203K131K
impossibl · zai$1.20$4.00$0.24200K131K
kilo · z-ai$1.20$4.00$0.24203K131K
llmgateway$1.20$4.00$0.24200K131K
llmgateway-providers · tencent$1.20$4.00$0.24200K128K
merge-gateway · zai$1.20$4.00$0.24free200K131K
nano-gpt · z-ai$1.20$4.00$0.24203K131K
novita$1.20$4.00$0.24203K131K
ofox · z-ai$1.20$4.00$0.24200K131K
openrouter$1.20$4.00$0.24203K131K
openrouter · z-ai$1.20$4.00$0.24203K131K
tensorx · z-ai$1.20$4.00$0.30$1.50203K131K
vercel · zai$1.20$4.00$0.24203K131K
zai$1.20$4.00$0.24free200K131K

Other listings of this model

same model, different key

More from Zhipu

most-hosted first