Perceptron Mk1
perceptron/perceptron-mk1Perceptron 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...
$0.15Input, per million tokens
$1.50Output, per million tokens
33KContext window
8KLongest answer
33K tokens of context — about 24,576 words, on a scale that ends at 2M.
What it can do
- Reasoning
- Vision
- Takes text
- Takes image
- Takes video
- Gives text
Released 12 May 2026 · checked 3 Oct 2026.