Groq

Fast, cheap inference for open-source models

Wafer-scale AI chips built for blazing-fast inference

Google's free playground for building with Gemini models

One API for Claude, Llama, Titan, and more on AWS

AI-powered Git history explanations inside VS Code

Web scraping API that outputs clean markdown for LLMs

Fast, low-latency inference API for image and video models

One API for AI models from every major provider

Pay-per-token cloud inference for open-source models