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,...
- Context window: 37K tokens
- Max output: 8K tokens
- Reads: text, image, video, audio
- Writes: text