OpenAI has unveiled the OpenAI Privacy Filter, an open-source model designed to detect and redact personally identifiable information (PII) in text. The model, featuring 1.5 billion total parameters and 50 million active parameters, supports a context window of up to 128,000 tokens. It utilizes a bidirectional token classification architecture to identify eight categories of PII, including names, addresses, and email addresses, achieving a 96% F1 score on the PII-Masking-300k benchmark. The OpenAI Privacy Filter is now accessible on Hugging Face and GitHub under the Apache 2.0 license, allowing developers to deploy and fine-tune the model locally. This release aims to enhance privacy protection in text processing applications by providing a robust tool for anonymizing sensitive information.