Perceptron: Perceptron Mk1

Name: Perceptron: Perceptron Mk1
Author: OpenRouter

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces

Context

33K

Max output

Input price

$0.15/1M tokens

Output price

$1.5/1M tokens

Capabilities

Show unsupported (5)

Reasoning & Interaction

Reasoning

Output Control

Structured Output

JSON Mode

Details

Model IDperceptron/perceptron-mk1

ProviderOpenRouter

Creatorperceptron

Family—

License—

Status—

Type—

Input modalitiestext, image, video

Output modalitiestext

Open weight—

Parameters—

Architecture—

Context window33K tokens

Max input—

Max output8K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2026-05-12

Sourceofficial

Pricing

Input

$0.15

Output

$1.5

Cache write

—

Cache read

—

Batch in

—

Batch out

—

API

GET/v1/models/openrouter/perceptron/perceptron-mk1