
Groq
Very low latency inference on custom silicon

Very low latency inference on custom silicon

Real-time web search API for RAG and agents

Run open language models locally with one command

Open-source vector database with hybrid search

Desktop app for running local LLMs

Fast serving and tuning for open models

One API across hundreds of language models
The hub for open models, datasets and demos

Run and fine-tune open models behind an API

Track, evaluate and monitor machine learning work

Find and fix vulnerabilities in code and dependencies

Detect malicious packages in your supply chain

Fast static analysis with rules that read like code

Voice and speech APIs with emotional nuance

Realtime voice and character AI for games

Cloud AI software engineer for delegated tasks

Keep a brand mascot on-model in every pose

Error tracking and performance monitoring for apps
Embedded analytics SaaS teams can ship in a day

Structured content platform with a customisable studio

TypeScript headless CMS that installs into Next.js

Turn any REST API into an admin dashboard