How to beginner · 3 min read

OpenAI Enterprise zero data retention

Quick answer

OpenAI Enterprise offers a zero data retention option that prevents your data from being stored or used for model training. To enable this, set the data_usage parameter to none in your API requests or configure it in your Enterprise dashboard settings.

PREREQUISITES

Python 3.8+
OpenAI Enterprise API key
pip install openai>=1.0

Setup

Install the official openai Python package and set your OpenAI Enterprise API key as an environment variable. This key must be provisioned with zero data retention enabled or configured accordingly in your Enterprise dashboard.

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

Use the data_usage parameter set to none in your API call to ensure zero data retention. This disables logging and training on your data.

python

import os
from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, ensure zero data retention."}],
    data_usage="none"
)

print(response.choices[0].message.content)

output

Hello! Your request was processed with zero data retention enabled.

Common variations

You can also configure zero data retention globally in the OpenAI Enterprise dashboard to apply to all API requests without specifying data_usage each time. For asynchronous calls, use the same parameter in async methods. Different models like gpt-4o-mini support this parameter similarly.

python

import os
import asyncio
from openai import OpenAI

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

async def main():
    response = await client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": "Test zero data retention async."}],
        data_usage="none"
    )
    print(response.choices[0].message.content)

asyncio.run(main())

output

Your async request was processed with zero data retention.

Troubleshooting

If you receive errors about data_usage being unrecognized, verify your API key is from an OpenAI Enterprise plan with zero data retention enabled.
If data retention is still occurring, check your Enterprise dashboard settings to confirm zero data retention is active globally or per request.
Contact OpenAI Enterprise support if your configuration does not apply as expected.

✅

Key Takeaways

Set data_usage="none" in API calls to enable zero data retention per request.
Configure zero data retention globally in the OpenAI Enterprise dashboard for convenience.
Ensure your API key is provisioned for Enterprise zero data retention to avoid errors.
Use the same parameter with async calls and across supported models like gpt-4o and gpt-4o-mini.

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

Verify ↗