perceptron/perceptron-mk1
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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Perceptron | $0.150 | $1.50 | 33K | — |
Perceptron Mk1 costs $0.150 per million input tokens and $1.50 per million output tokens via OpenRouter, making it 76th cheapest of 298 paid models.
Perceptron Mk1 generates around 15 tokens per second with 897ms time-to-first-token (p50), the 289th fastest tracked model.
Perceptron Mk1 supports a 33K-token context window and can output up to 8K tokens. It accepts text, image, video input.