GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Direct via Z-AI (Zhipu).
Specification
most-agreed values
Context
128K
Max output
24K
Released
2025-12-08
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.60
Output
$0.90
Cache read
$0.30
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt · z-ai | $0.60 | $0.90 | $0.30 | — | 128K | 24K | — |
More from Zhipu
most-hosted first