glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.
Specification
most-agreed values
Context
1M
Max output
131K
Released
2026-06-13
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.254
Output
$5.016
Cache read
$0.3135
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| greenpt | $1.254 | $5.016 | $0.3135 | — | 1M | 131K | — |
More from Zhipu
most-hosted first