Macaron V1 Venti
macaron-v1-venti
GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI
Specification
most-agreed values
Context
1M
Max output
131K
Released
2026-07-21
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.825
Output
$2.475
Cache read
$0.165
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| novita-ai · mindai | $0.825 | $2.475 | $0.165 | — | 1M | 131K | — |
| novita | $1.50 | $4.50 | $0.30 | — | 1M | 131K | — |
