Groq operates an inference cloud built on its own LPU chips. Developers call open models such as Llama, Qwen and GPT-OSS through an API that is compatible with the OpenAI format, and the platform targets high token throughput and low latency. The company also offers dedicated infrastructure for enterprises. The pricing page did not render readable prices during this check, so no price was recorded.
Price note: Groq's billing page lists a Free plan at $0 and a Developer plan billed per token, plus Enterprise.
Categories: LLM & Chatbots
Tags: inference, api, open-models, lpu
Follow these steps to get started.
