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,...
Details
| Field | Value |
|---|---|
| id | perceptron/perceptron-mk1.5 |
| modality | text+image+video+audio->text |
| context_length | 36864 |
| max_output_tokens | 8192 |
| release_date | 2026-09-25 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | yes |
| input_modalities | text, image, video, audio |
| output_modalities | text |