Perceptron Mk1.5

Name: Perceptron Mk1.5
Author: Perceptron

Released

2026-09-25

Last refreshed

2026-09-28

Status

Researched 14d ago

ProprietaryCommercial use: conditionalMultimodalAgentsVisionJSON / Tool useVisionMultimodalAgent

Perceptron releases · 2 in the last 12 monthsChangelog →

Specifications

Family: Perceptron Mk
Released: 2026-09-25
Context: 36K
Max output: 8K
Architecture: Decoder Only
Specialization: vision
Openness: Proprietary
License: ProprietaryCommercial use: conditional
Weights: Not released
Code: Unknown
Training: Pretrained

Created by

Perceptron

Physical AI and video reasoning models

United States

Founded 2024

Website

Pricing

Output / 1M

$1.50

Input / 1M

$0.150

Cheapest of 1 route · OpenRouter

Providers(1)

OpenRouter

View 1 provider route

Links

Website

About

Perceptron Mk1.5 is Perceptron's embodied vision-language model released September 25, 2026 (first-party blog). Successor to Mk1 in the Perceptron Mk family: native audio in, video object tracking, web search, sub-agent/tool calls, and stronger visual reasoning; blog cites ~2-5x faster end-to-end vs Mk1. Accepts text, images, video, and audio; emits text plus spatial/temporal annotations (points, boxes, polygons, clips, object tracks). First-party docs: Model ID perceptron-mk1.5; context window 36,864 tokens; max output 8,192; pricing $0.15/M input, $1.50/M output, $0.0375/M cached input. Available via Perceptron Platform + SDK and OpenRouter (perceptron/perceptron-mk1.5). Closed-source hosted API under a proprietary license.