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,...
The figures
- Made by
- Perceptron
- Model ID
- perceptron/perceptron-mk1.5
- Input
- $0.15 per million tokens
- Output
- $1.5 per million tokens
- Context window
- 37K tokens
- Longest answer
- 8K tokens
- Takes in
- text, image, video, audio
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- No
- Released
- 25 Sept 2026
Read on 3 Oct 2026.