ModelPickr

Models / Perceptron / Perceptron Mk1

Perceptron

Perceptron Mk1

Multimodal reasoning model for visual analysis, planning, and tool use

$0.15 in · $1.50 out

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

Context
32,768
Max output
8,192
Cache read
$0.075
Cache write
—
Reasoning
Yes
Tool calls
No
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
May 12, 2026
Updated in source
May 12, 2026
Knowledge
—
Providers
1

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
NanoGPTreference$0.15$1.50$0.075——