Reasoning JSON

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

perceptron/perceptron-mk1 2026-05-12 32.768K context $0.15/M input $1.5/M output
3 providers

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,...

perceptron/perceptron-mk1.5 36.864K context $0.15/M input $1.5/M output