How to beginner · 3 min read

How to summarize text with OpenAI API

Q: How to summarize text with OpenAI API

Use the OpenAI Python SDK to call client.chat.completions.create with a summarization prompt and a model like gpt-4o. Pass the text to summarize in the messages array and extract the summary from the response's choices[0].message.content.

Quick answer

Use the OpenAI Python SDK to call client.chat.completions.create with a summarization prompt and a model like gpt-4o. Pass the text to summarize in the messages array and extract the summary from the response's choices[0].message.content.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the official openai Python package and set your API key as an environment variable.

bash

pip install openai>=1.0

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl (xx kB)
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

This example shows how to summarize a long text using the gpt-4o model with the OpenAI Python SDK v1.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

text_to_summarize = (
    "OpenAI provides powerful language models that can perform a variety of tasks, "
    "including text summarization, translation, and question answering. "
    "Using the chat completion endpoint, you can prompt the model to generate concise summaries."
)

messages = [
    {"role": "user", "content": f"Please summarize the following text:\n\n{text_to_summarize}"}
]

response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages
)

summary = response.choices[0].message.content
print("Summary:", summary)

output

Summary: OpenAI's language models can perform various tasks such as summarization, translation, and question answering by using the chat completion endpoint to generate concise summaries.

Common variations

Use gpt-4o-mini for faster, cheaper summaries with slightly less detail.
Use async calls with asyncio for concurrent summarization tasks.
Stream partial summary results by setting stream=True in the request.

python

import os
import asyncio
from openai import OpenAI

async def async_summarize(text: str):
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    messages = [{"role": "user", "content": f"Summarize this text:\n\n{text}"}]
    stream = await client.chat.completions.acreate(
        model="gpt-4o-mini",
        messages=messages,
        stream=True
    )
    summary = ""
    async for chunk in stream:
        delta = chunk.choices[0].delta.content or ""
        print(delta, end="", flush=True)
        summary += delta
    print()
    return summary

if __name__ == "__main__":
    text = "OpenAI's models can summarize text efficiently and accurately."
    asyncio.run(async_summarize(text))

output

OpenAI's models can summarize text efficiently and accurately.

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
If the summary is too short or irrelevant, try refining the prompt or increasing max_tokens.
For rate limit errors, implement exponential backoff retries.

✅

Key Takeaways

Use the OpenAI Python SDK v1 with client.chat.completions.create for summarization.
Pass the text in a user message prompt and extract the summary from the response content.
Leverage streaming or async calls for efficient and scalable summarization workflows.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗