Perceptron Mk1
Perceptron Mk1 is a vision-language model developed by Perceptron that specializes in analyzing video and image content alongside text. It is designed for tasks requiring visual understanding and reasoning, offering a context window of 32,768 tokens.
Perceptron Mk1 specs and pricing
- Provider: Perceptron
- Released: May 12, 2026
- Context window: 33K tokens
- Max output: 8K tokens
- Input: text, images, video
- Output: text
- Price: $0.15 input / $1.50 output per 1M tokens
- Reasoning: yes
What Perceptron Mk1 is good at
- Analyzing video content for specific events
- Interpreting complex visual data from images
- Reasoning tasks involving multimodal inputs
To-dos to try with Perceptron Mk1
- Upload a video of a manufacturing process and identify any safety protocol violations.
- Provide a series of images from a technical manual and ask for a summary of the assembly steps.
- Analyze a video clip and describe the sequence of actions taken by the subjects.
FAQ
- What types of media can Perceptron Mk1 process? The model accepts text, images, and video as input.
- What is the primary focus of this model? Perceptron Mk1 is built for vision-language tasks, specifically focusing on video and embodied reasoning.
- How much does Perceptron Mk1 cost? Perceptron Mk1 costs $0.15 per million input tokens and $1.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.63 credits ($1 = 100 credits).
- What is the context window of Perceptron Mk1? Perceptron Mk1 can read up to 33K tokens at once and write up to 8K tokens in one reply.
- Can I use Perceptron Mk1 without coding? Yes. In todo.is you pick Perceptron Mk1 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.