---
id: "perceptron/perceptron-mk1.5"
also: ["perceptron/perceptron-mk1.5-20260925"]
card_usd_per_m: "0.15 in, 1.5 out, at perceptron"
cheapest_list_usd_per_m: "0.15 in, 1.5 out, at perceptron on openrouter"
cheapest_effective_usd_per_m: "0.149 in, 1.4983 out, at perceptron on openrouter"
context: 36864
max_output: 8192
input: ["text", "image", "video", "audio"]
output: ["text"]
released: "2026-09-25"
reasoning: ["high", "medium", "low", "minimal", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 0
---
# Perceptron: Perceptron Mk1.5

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...