GlobalFeaturedinferenceglobal
Groq
High-speed AI inference with LPU architecture for ultra-fast model responses.
Common Models
Llama 3.3 70B VersatileOpenAI GPT OSS 120BOpenAI GPT OSS 20BMetaLlama 4 Scout 17BWhisper Large V3 Turbo
Tags
fast-inferencelpulow-latencyhardware
Quick Info
Region
Global
Status
activeLast Verified
2026-03-24