Groq logo

Groq

Operational

Fastest inference on custom LPU hardware

Lightning-fast inference powered by custom Language Processing Units.

— uptime —
API Documentation View Pricing Website

Company

Headquarters
Mountain View, CA
Founded
2016

Capabilities

Models Hosted
Curated Deck
Inference Speed
500+ tokens/sec
Specialties
Ultra-low latency
Unique Features
Custom LPU hardware
API Style
OpenAI-compatible
Compute Location
Global

Models

Coming soon

We are standardizing model listings across providers.

Why Use Groq

Blazing Fast

500+ tokens/second inference speed.

Free Tier

Generous free tier for testing.

Details

About Groq

Groq developed custom Language Processing Units optimized for AI inference.

Newsletter

Get the signal, skip the noise.

Weekly digest of new models and provider updates across 41+ compute providers. Curated for AI builders who ship.

New model releases
Capability updates
Provider status
bots.so
The AI Inference Model Index

Models

Providers

Resources

Legal

© bots.so — The AI Inference Model Index

bots.so aggregates publicly available model deployment information from official provider sources. We are not affiliated with any model provider. Model availability changes rapidly; always verify on official sites.