AI & Inferencellminferencespeedrealtime

Groq Inference API

The Groq API delivers extremely fast LLM inference on custom hardware, ideal for real-time chat and voice applications.

Get started

Start building with Groq

Create an account, get your API key and start integrating Groq Inference API.

Features: Ultra-low latency inferenceOpen-model supportStreaming responsesOpenAI-compatible API
Use case: Real-time chat, voice agents and latency-critical apps
Website: https://groq.com

OpenAI Whisper API

AI & Speech

Stripe Payments API

Finance

Supabase Database API

Backend