Skip to main content
Perceptron Mk1.5 is available. See the Mk1.5 model guide for tool calling and updated annotation handling.
Perceptron Mk1 is a vision-language model that understands images and video. Ask it questions, detect objects, read text, get captions, or clip events — all through a simple API.

Try Perceptron Mk1 in 30 seconds

Create an API key

Get your key from the Perceptron platform

Join Discord

Get help and see what others are building

Get started with Image

Step through this example interactively

Get started with Video

Step through this example interactively
For Python, start with the Perceptron SDK. It provides helpers for questions, detection, OCR, and structured annotations. Direct HTTP and the OpenAI-compatible client are also available:
Using Python? Install our SDK with pip install perceptron. For the alternative OpenAI-compatible example, install openai instead.
Supported image formats: JPEG, PNG, WebP — pass a URL or local file path. Supported video formats: MP4, WebM — pass a URL or local file path. Outputs are deterministic by default (temperature defaults to 0.0). See API Reference for all parameters.

Explore our developer guides

Image Q&A

Ask questions about images and get grounded answers

Video Q&A

Ask questions about video and get answers grounded in time

Object Detection

Locate targets with precise bounding boxes

Video Clipping

Find events in video and return start/end timestamps

Multilook

Ask up to 16 questions about one image or video in a single call

OCR

Extract text from images and documents

Image Captioning

Generate descriptions of images

In-Context Learning (Image)

Adapt Perceptron Mk1 to image tasks with a handful of examples

In-Context Learning (Video)

Adapt Perceptron Mk1 to video tasks with a handful of examples

Models overview

Perceptron Mk1

Best-in-class closed-source VLM with reasoning — accepts image and video inputs. (“Mk1” is short for “Mark 1”.)
  • Model ID: perceptron-mk1
  • Context: 32K tokens
  • Reasoning: Yes
  • Pricing: $0.15/M input, $1.50/M output, $0.0375/M cached input (Multilook)
  • Closed source

Benchmarks

Perceptron Mk1 benchmark results: Efficiency frontier ER benchmark Video benchmark Image benchmark