Streaming delivers tokens to your app as they're generated — essential for responsive, ChatGPT-like user experiences.

Python Streaming

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

In Production

Use Server-Sent Events (SSE) to stream tokens from your backend to your frontend. This is exactly how ChatGPT works under the hood.

Reference:

Streaming documentation

https://en.wikipedia.org/wiki/Special:Search?search=Streaming