ModelPickr

Models / Mindlab / Macaron V1 Venti

Mindlab

Macaron V1 Venti

GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI

$0.83 in · $2.48 out

per 1M tokens · provider rate closest to the median. No first-party Mindlab price was listed. The reference price is Novita AI's rate, the provider closest to the median.

Context
1,048,576
Max output
131,072
Cache read
$0.17
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
MIT
Released
Jul 21, 2026
Updated in source
Jul 21, 2026
Knowledge
—
Providers
1

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Novita AIreference$0.83$2.48$0.17——