Perceptron Mk1 (short for “Mark 1”) is our flagship closed-source vision-language model, with image, video, and reasoning support.Documentation Index
Fetch the complete documentation index at: https://docs.perceptron.inc/llms.txt
Use this file to discover all available pages before exploring further.
Specs
- Model ID:
mk1 - Inputs: Text, Images, Videos
- Outputs: Text
- Context: 32K tokens
- Reasoning: Yes
- Pricing: $0.15/M input, $1.50/M output
- Max images per prompt: TBD
- Max video per prompt: TBD
- Supported MIME types:
image/png,image/jpeg,image/webp,video/mp4,video/webm - Source: Closed