Groq

Access Groq’s ultra-fast inference through NotPixel. Groq uses custom LPU (Language Processing Unit) hardware for extremely low-latency responses.

Setup

1. Get API Key

1. Go to Groq Console 
2. Create an account or sign in
3. Navigate to API Keys
4. Create a new API key

2. Configure Environment

GROQ_API_KEY=gsk_...

Usage

import Ads from 'notpixel';
 
const ads = new Ads({
  publisherId: 'pub_xxx',
  model: 'groq/llama-3.1-70b-versatile',
  input: 'Explain how caching works in web applications',
});
 
const response = await ads.offer();
console.log(response.text);

Available Models

Model Selection

// High quality, still very fast
model: 'groq/llama-3.1-70b-versatile'
 
// Maximum speed
model: 'groq/llama-3.1-8b-instant'
 
// Balanced performance
model: 'groq/mixtral-8x7b-32768'

Why Groq?

• Ultra-low latency: Responses in milliseconds
• High throughput: Handle more requests per second
• Competitive pricing: Pay per token, not per second
• Open models: Access to Llama, Mixtral, and more

Environment Variable