Architecture layer

Models

LLM providers and local inference options

Part of an AI agent architecture— design the blueprint first, then pick tools for this layer.

tools

State-of-the-art frontier models built for safe, steerable, and capable agentic use

Fastest inference API for open-source models — purpose-built for speed

Run open-source LLMs locally with a simple API and no cloud dependency

The GPT model family with vision, audio, and the broadest tool-calling ecosystem