Install the OpenAI SDK

Here's the trick nobody tells you on day one: the OpenAI SDK isn't just for OpenAI. It's the official client for the OpenAI API, sure, published for Python (openai) and Node (openai) with the same surface. But Ollama, LM Studio, vLLM, Together, Groq, and a pile of others all speak OpenAI-compatible. Learn this one SDK and you can talk to most of them, even if you never pay OpenAI a cent.

This is post 10 of 10 in the Setup Toolbox series, and the last one. We'll install both clients and verify each with a single call.

You'll need an API key from platform.openai.com. New accounts get a small credit, then it's pay-as-you-go.

Python

Install via uv inside a project:

# add the openai sdk to your project

uv add openai

For a one-off without a project:

# run a script with the sdk available

uv run --with openai python -c "from openai import OpenAI; print(OpenAI().chat.completions.create(model='gpt-4o-mini', messages=[{'role':'user','content':'hi'}]).choices[0].message.content)"

Stuck on pip in a legacy project? pip install openai works fine.

Node

Install via npm inside a project:

# add the openai sdk to your project

npm install openai

pnpm and yarn behave the same way.

Configure the API key

The SDK reads OPENAI_API_KEY from the environment. Don't hardcode it. For dev, use .env (and .gitignore it):

# create .env with your api key

echo 'OPENAI_API_KEY=sk-...' >> .env

In production, reach for a secret manager. Same advice as any other API key.

Verify (Python)

# verify python sdk with a one-line call

from openai import OpenAI; print(OpenAI().chat.completions.create(model="gpt-4o-mini", messages=[{"role":"user","content":"hi"}]).choices[0].message.content)

Save to verify.py, then uv run python verify.py.

Verify (Node)

// verify node sdk with a one-line call

import OpenAI from "openai"; const r = await new OpenAI().chat.completions.create({ model: "gpt-4o-mini", messages: [{ role: "user", content: "hi" }] }); console.log(r.choices[0].message.content);

Save to verify.mjs, then node verify.mjs.

Pointing the SDK at a different provider

Want to run this against Ollama, LM Studio, or any OpenAI-compatible endpoint? Override base_url (Python) or baseURL (Node) and pass any string as the API key:

# point the openai sdk at a local ollama server

from openai import OpenAI; client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

See Install Ollama or Install LM Studio for the local server side.

Common gotchas

• Wrong env var name: it's OPENAI_API_KEY, exactly. Some old tutorials use OPENAI_KEY, which won't work.
• chat.completions vs responses: OpenAI now has two endpoints. chat.completions is the older, broader one most code uses. responses is newer and tool-use-first. Pick one per project, don't mix.
• Model name drift: OpenAI deprecates models on a schedule. gpt-4o-mini is currently the cheapest reasonable default, but check the docs before pinning.
• Rate limits by tier: free credits put you on tier 1, with low RPM/TPM caps. Tight loops trip them. Use exponential backoff, or batch big jobs through the Batch API (cheaper too).
• Streaming: .stream=True (Python) or .stream: true (Node) hands you an iterable of chunks instead of one response.

Once verify.py or verify.mjs prints a reply, you're set. You can call OpenAI, or any of the dozens of compatible providers, from the exact same code.

That's the toolbox done. Everything's installed and proven. Now go use it: the Local LLMs series is the hands-on track where you point all this at a model running on your own machine.