Stream OpenAI Responses API text in Python

Steps

1. Pass stream=True to receive typed events. Handle text deltas separately from lifecycle events.
2. Treat interrupted or failed streams as unfinished work even if some text has already appeared.

Example

Python · Python API examples require OPENAI_API_KEY and OPENAI_MODEL in your server environment. API calls may incur OpenAI charges.

import os
from openai import OpenAI

stream = OpenAI().responses.create(
    model=os.environ["OPENAI_MODEL"], input="Explain HTTP streaming.", stream=True,
)
completed = False
for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)
    elif event.type == "response.completed":
        completed = True
    elif event.type in {"error", "response.failed", "response.incomplete"}:
        raise RuntimeError("Response stream did not complete")
if not completed:
    raise RuntimeError("Stream ended without completion")

Check the result

Expect incremental text and a completion event. In a web app, preserve an explicit failed or interrupted state instead of silently saving partial text as a complete answer.

Official source

Streaming API responses

Check current provider documentation and model support before deployment. This guide is separate from the approved evidence records listed in the catalog.