GM documentation

Swap one base URL, keep every SDK you already use.

Make your first request Browse integrations

One gateway, familiar interfaces

GM supports OpenAI-compatible Chat Completions and Responses, Anthropic Messages, and Gemini generateContent. Requests are routed through a gateway running inside an Intel TDX trusted execution environment.

Start in five minutes

Create an API key, discover an available model, and make your first request. Open the quickstart →

Use your existing tools

Connect Claude Code, Codex CLI, Cursor, SDKs, chat interfaces, and more. Browse integrations →

Understand the privacy model

Learn what the gateway protects, what upstream model providers can see, and how confidential models differ. Read the privacy guide →

Explore the API

Read endpoint guides or inspect the reference generated from GM’s OpenAPI specification. Open the API overview →