Perceptron: Perceptron Mk1
0.0 / 10
32.8K context
Proprietary
About this model
Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...
Technical Specs
- Architecture: text+image+video->text
- Context Window: 32,768 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.15 / 1M tokens | 1.5 / 1M tokens | USD |