Perceptron Mk1
by Perceptrontext+image+video->text1 endpoint
Overview
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...
Capabilities
Text generation
Image understanding
Video understanding
Extended reasoning
Top-P sampling
Modalities
Input
TextImageVideo
Output
Text
Technical Specifications
Context Window
32.8K tokens
Max Output
8.2K tokens
Tokenizer
Other
Uptime (24h)
9999.4%
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningstructured_outputstemperaturetop_ktop_p