Perceptron Mk1.5
perceptron-mk1-5
Perceptron Mk1.5 is a multimodal reasoning model for visual analysis and physical agents. It accepts text, images, video, and audio, supports tool calling and structured output, and can return spatial annotations such as points, boxes, polygons, and tracks.
Specification
most-agreed values
Context
37K
Max output
8K
Released
2026-09-25
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, video, audio
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.15
Output
$1.50
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kilo · perceptron | $0.15 | $1.50 | — | — | 37K | 8K | — |
| nano-gpt · perceptron | $0.15 | $1.50 | — | — | 37K | 8K | — |
| openrouter | $0.15 | $1.50 | — | — | 37K | 8K | — |
| openrouter · perceptron | $0.15 | $1.50 | — | — | 37K | 8K | — |
