modelbenchmark.io

GLM 5.1 Thinking TEE

Zhipu · glm-5-1-thinking

Compare

Strong GLM coding model for agentic engineering, terminals, and repository generation

Specification

most-agreed values

Context
203K
Max output
66K
Released
2026-04-07
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.70
Output
$2.50
Cache read
$0.18

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · tee$0.70$2.50$0.18—203K66K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02nano-gpt · teeCache read$0.30
2026-10-13nano-gpt · teeCache read$0.18
2026-09-02nano-gpt · teeInput$1.50
2026-10-13nano-gpt · teeInput$0.70
2026-09-02nano-gpt · teeOutput$5.25
2026-10-13nano-gpt · teeOutput$2.50

More from Zhipu

most-hosted first