import os
from openai import OpenAI

# https://model-XXXXXXX.api.baseten.co/environments/production/sync/v1
model_url = ""

client = OpenAI(
    base_url=model_url,
    api_key=os.environ.get("BASETEN_API_KEY"),
)

stream = client.chat.completions.create(
    model="baseten",
    messages=[
        {"role": "user", "content": "Which weighs more, a pound of bricks or a pound of feathers?"},
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

["streaming", "output", "text"]