Probed: missed a spoken codeword inside the clip although it accepts standalone audio — its video path drops the track. Any comment it makes on sound is invented.
SHAUD: YELLOW SQUARE AUDIO: NONE
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,...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000015 | $0.150 |
| completion | 0.0000015 | $1.50 |
2 answersin this database. A round opens every model's answer to the same prompt.