Previewing Private Safety Processing, which strengthens safeguards across interactions while remaining compatible with ZDR.
Update on September 22, 2026: We are rolling out Private Safety Processing to API customers, with access expanding in phases. Private Safety Processing enables us to continue offering ZDR as frontier models become more capable. This is just the beginning, as we continue working with our customers on collaborative approaches to privacy and safety. Learn more about Private Safety Processing in our developer guide(opens in a new window).
Zero Data Retention gives eligible API customers a clear promise: OpenAI does not retain their prompts or model responses after a request is processed. Customer content is not available to OpenAI personnel for review1, and enterprise customer data is not used to train our models unless customers explicitly opt-in.
As models take on longer, more complex tasks, some serious risks may only become visible across multiple interactions. Existing ZDR-compatible safety systems evaluate each interaction individually. Today, we’re previewing Private Safety Processing, which is designed to identify patterns across related interactions without giving OpenAI personnel access to the underlying content.
For ZDR deployments, customer content remains on infrastructure the customer controls. We are also developing an option in which content is stored on OpenAI infrastructure, encrypted with keys controlled by the customer. In both cases, automated systems can identify potential misuse and return limited safety signals without exposing the underlying prompts or responses to OpenAI personnel.
The most serious AI safety risks are not always visible in a single interaction.
Source link
