Fast variant of GLM 4.6 for general chat, coding, and analysis with improved latency and strong reasoning.
Specification
most-agreed values
Context
205K
Max output
131K
Released
2025-10-02
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.00
Output
$3.00
Cache read
$0.50
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt · thinking | $1.00 | $3.00 | $0.50 | — | 205K | 131K | — |
| nano-gpt · z-ai | $1.00 | $3.00 | $0.50 | — | 205K | 131K | — |
More from Zhipu
most-hosted first