How to build scalable web apps with OpenAI's Privacy Filter

Model Card for OpenAI Privacy Filter

The OpenAI Privacy Filter is a 1.5‑billion‑parameter, bidirectional token‑classification model that detects and redacts personally identifiable information and secrets in unstructured text. It is built from an autoregressive checkpoint, converted into a banded‑attention classifier, and uses a constrained Viterbi decoder to produce coherent spans across eight privacy categories in a single forward pass. The model supports configurable precision‑recall tradeoffs, a 128,000‑token context window, and is designed for efficient local deployment and domain‑specific fine‑tuning as a data‑minimization component within layered privacy workflows.

Introducing OpenAI Privacy Filter

OpenAI Privacy Filter is an open-weight model for detecting and redacting personally identifiable information (PII) in text with state-of-the-art accuracy

Broad access through consistent standards

OpenAI collaborates with distribution partners to maintain consistent safeguards and responsible access to its technology. The company clarifies expectations through its Usage Policies, ensuring that partners adhere to established standards. This approach aims to provide broad, reliable access while upholding safety and responsibility.

Creating Privacy Preserving AI with Substra

New and improved content moderation tooling

We are introducing a new and improved content moderation tool. The Moderation endpoint improves upon our previous content filter, and is available for free today to OpenAI API developers.

Scaling security with responsible disclosure

OpenAI introduces its Outbound Coordinated Disclosure Policy to guide how it responsibly reports vulnerabilities in third-party software—emphasizing integrity, collaboration, and proactive security at scale.