Grokcloud

A serverless API for blazing-fast, low-latency AI inference, powered by Groq's custom Language Processing Unit (LPU) hardware.

GroqCloud is the AI inference platform built for developers, providing a serverless API for unmatched speed and cost efficiency. It runs on Groq's custom-built Language Processing Unit (LPU) hardware, delivering low-latency, high-throughput token generation that fundamentally changes generative AI application performance. Since its soft launch in February 2024, the platform has rapidly scaled, attracting over 225,000 developers by offering access to popular models including Mixtral 8x7b, Llama 2x70b, and Gemma 7b.

https://groq.com/