Skip to main content

OpenAI Compatible

Overview​

AIProxy agents can be invoked through OpenAI-compatible endpoints. Because they speak the same request and response shapes as OpenAI's own APIs (both Chat Completions and Responses), you can reach them with the tools you already use, from a plain curl request to the official OpenAI SDKs to editors that accept a custom model provider.

Whichever route you choose, the fundamentals are the same:

  • One base URL: point your client at https://api.serenitystar.ai.
  • Your API key: sent as X-API-KEY or as a bearer token, so the OpenAI SDKs authenticate out of the box.

Read the pages below to learn how to use Serenity* Star as your OpenAI-compatible provider:

AIProxy

The raw HTTP reference — endpoints, the model identifier, and tools, with cURL examples.

Python SDK

Call the same endpoints with the official OpenAI Python SDK — just change the base URL and API key.

VS Code Chat

Add an AIProxy agent as a custom model in VS Code Chat and use it while you code.

Looking for self-hosted models instead of agents?

The endpoints described here run a configured AIProxy agent. If you want to call a self-hosted model directly, with no agent in front of it, see OpenAI Compatible Inference under AI Services.