Infer Docs

Infer is a unified OpenAI-compatible endpoint for top AI models (GPT, Claude, Gemini, and more). Start with the integration path that matches how you use Infer.

Quickstart

Create an API key, point your client at Infer, and make the first request.

CLI

Set up terminal agents such as Codex, Claude Code, and OpenCode with environment variables and config files.

VS Code extension

Use VS Code-based AI extensions with Infer as the model gateway.

API

Call the OpenAI-compatible API directly from Python, Node.js, curl, or any HTTP client.

Before you start

Create an Infer API key in the API Keys dashboard.
Make sure the team has available balance on the Billing page.
Pick the integration card above that matches your workflow and follow the guide.

Runtime API base URL

This value is resolved from PublicRuntimeConfigProvider for the current environment, so copy-paste works without baking a deployment URL into static MDX.

Base URL

https://api-agenthub-pre.riema.xyz/v1