OpenAI Privacy Filter

OpenAI Privacy Filter is a bidirectional token-classification model for personally identifiable information (PII) detection and masking in text. It is intended for high-throughput data sanitization workflows where teams need a model that they can run on-premises that is fast, context-aware, and tunable.

OpenAI Privacy Filter is pretrained autoregressively to arrive at a checkpoint with similar architecture to gpt-oss, albeit of a smaller size. We then converted that checkpoint into a bidirectional token classifier over a privacy label taxonomy, and post-trained with a supervised classification loss. (For architecture details about gpt-oss, please see the gpt-oss model card.) Instead of generating text token-by-token, this model labels an input sequence in a single forward pass, then decodes coherent spans with a constrained Viterbi procedure. For each input token, the model predicts a probability distribution over the label taxonomy which consists of 8 output categories described below.

Highlights:

• Permissive Apache 2.0 license: ideal for experimentation, customization, and commercial deployment.
• Small size: Runs in a web browser or on a laptop – 1.5B parameters total and 50M active parameters.
• Fine-tunable: Adapt the model to specific data distributions through easy and data efficient finetuning.
• Long-context: 128,000-token context window enables processing long text with high throughput and no chunking.
• Runtime control: configure precision/recall tradeoffs and detected span lengths through preset operating points.

Metadata

• Developed by: OpenAI

• Funded by: OpenAI

• Shared by: OpenAI

• Model type: Bidirectional token classification model for privacy span detection

• Language(s): Primarily English; selected multilingual robustness evaluation reported

• License: Apache 2.0

• Source repository: https://github.com/openai/privacy-filter

• Model weights: https://huggingface.co/openai/privacy-filter

• Model card: OpenAI Privacy Filter Model Card