OpenAI API Quickstart with FastAPI

A FastAPI port of openai/openai-quickstart-python. Check out the examples folder to try them out.

Example	What it shows
examples/pet-name	A form that generates superhero pet names, using the Responses API
examples/chat	A multi-turn chat that streams tokens as they arrive, using Chat Completions

Setup

1. If you don’t have Python installed, install it from Python.org.

2. Clone this repository.

3. Navigate into the project directory:

   $ cd openai-quickstart-fastapi

4. Create a new virtual environment:

   • macOS / Linux:

     $ python -m venv venv
     $ . venv/bin/activate

   • Windows:

     > python -m venv venv
     > .\venv\Scripts\activate

5. Install the requirements:

   $ pip install -r requirements.txt

6. Make a copy of the example environment variables file:

   $ cp .env.example .env

7. Add your API key to the newly created .env file.

8. Run an example:

   $ cd examples/pet-name
   $ fastapi dev app.py

You should now be able to access the app from your browser at http://localhost:8000!

Using uv

Steps 4 and 5 with uv instead:

$ uv venv
$ uv pip install -r requirements.txt

Choosing a model

Both examples read OPENAI_MODEL, so you can try another model without editing the code:

$ OPENAI_MODEL=gpt-5-mini fastapi dev app.py

The SDK also reads OPENAI_BASE_URL, which lets the chat example run against any OpenAI-compatible endpoint. Note that the pet name example uses the Responses API, which fewer providers implement.

Docker

Builds the pet name example:

$ docker build -t openai-quickstart-fastapi .
$ docker run -e OPENAI_API_KEY=<your-api-key> -p 8000:8000 openai-quickstart-fastapi

Reference

• openai/openai-quickstart-python