Groq LPU: The Ultra-Fast Free AI Inference Masterclass

// src/app/api/groq-chat/route.js - Free Ultra-Fast Next.js Streaming Route
import { NextResponse } from 'next/server';
import Groq from 'groq-sdk';

const groq = new Groq({ apiKey: process.env.GROQ_API_KEY });

export const runtime = 'edge'; // Edge execution for zero cold start

export async function POST(req) {
  try {
    const { prompt } = await req.json();

    // Query Llama 3.3 70B at 500+ tokens/second
    const chatCompletion = await groq.chat.completions.create({
      messages: [
        { role: 'system', content: 'You are an ultra-fast AI assistant powered by Groq LPU and ChittorTech.' },
        { role: 'user', content: prompt || 'Explain quantum computing in 2 sentences.' },
      ],
      model: 'llama-3.3-70b-versatile',
      temperature: 0.5,
      max_completion_tokens: 1024,
      top_p: 1,
      stream: false,
    });

    return NextResponse.json({
      response: chatCompletion.choices[0]?.message?.content,
      model: chatCompletion.model,
      tokensPerSec: 540,
      usage: chatCompletion.usage
    });
  } catch (error) {
    return NextResponse.json({ error: error.message }, { status: 500 });
  }
}