Skip to main content

OpenAI Python SDK

Install the SDK:

python -m pip install openai

Set OPENAI_API_KEY and OPENAI_BASE_URL as shown in LLM SDKs. Then run this Python code:

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="claude-sonnet",
    messages=[{"role": "user", "content": "In one sentence, explain what an AI model is."}],
)
print(response.choices[0].message.content)

The code prints the response of the model. To use a different model, change the model value.

Use the Responses API​

response = client.responses.create(model="gpt-6-luna", input="Say hello.")
print(response.output_text)

Select a provider​

To select the provider that serves the model, add a header when you create the client:

client = OpenAI(default_headers={"X-AmSC-MAG-Provider": "openai"})

or:

client = OpenAI(default_headers={"X-AmSC-MAG-Provider": "microsoft"})

See Model Selection & Options.