perceptronVision

Perceptron: Perceptron Mk1

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...

Context
33k tokens
Input / 1M tokens
$0.15
Output / 1M tokens
$1.50
Benchmark

Pricing

Input tokens$0.15 per 1M tokens
Output tokens$1.50 per 1M tokens

Technical details

Model IDperceptron/perceptron-mk1
Context window33k tokens
Input modalitiestext, image, video
Output modalitiestext
TokenizerOther
Max output tokens8,192

Use with MegaBrain

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://getmegabrain.com/api/gateway/v1',
  apiKey: process.env.MEGABRAIN_API_KEY,
})

const response = await client.chat.completions.create({
  model: 'perceptron/perceptron-mk1',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use Perceptron: Perceptron Mk1?

Get an API key and start making requests in minutes.

Get an API key