Skip to main content
Perceptron offers vision-language models that you call through one chat completions API, and services with their own endpoints for specific jobs.
  • The Models tab has the quickstart, capabilities, and guides for each model. Pick a model from the dropdown at the top of the sidebar.
  • The Services tab covers Detect and Egocentric video annotation.
  • The API reference tab has a selector for the Perceptron Mk1.5, Perceptron Mk1 and service references.

Perceptron Mk1.5 quickstart

Get started with image, video, and audio understanding, tracking, and tool calling.

Choose a model

Choose a model and discover its API capabilities.

Egocentric video annotation

Submit first-person videos, follow each job, and download completed annotations.

Detect

Get grounded object detections for a single image.

API reference

Reference for Perceptron Mk1.5 (Latest), Perceptron Mk1, Detect and Egocentric.

Python SDK

Set up a Python environment and send a complete Mk1.5 image request.
Every API request needs a Perceptron API key.

Create an API key

Get your key from the Perceptron platform

Join Discord

Get help and see what others are building