An OpenAI-compatible API accepts the same request format as OpenAI's API, so apps written for OpenAI can talk to other models by changing a few settings.
In plain words
Many providers and tools accept the same request format as OpenAI's API. If a service is OpenAI-compatible, you keep using the OpenAI library and just point it at a different base URL with a different key and model name. Google's Gemini API and the local tool Ollama both offer this. Compatibility is often partial, so some features may be missing.
A quick example
Imagine a Python app that uses the official OpenAI library. To try a Gemini model, the developer changes three things: the API key, the base URL to Google's OpenAI-compatible endpoint, and the model name. The rest of the code stays the same.
Where you'll meet it
- Switching providers without rewriting code.
- Running local models behind a familiar interface.
Related
Sources
- DocsOpenAI compatibility, Google AI for Developers (Gemini API) · read 2 Nov 2026
- DocsOpenAI compatibility, Ollama documentation · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 2 Nov 2026. Spotted an error? Report it.