Privacy Filter
OpenAI's Privacy Filter is a bidirectional token-classification model designed for personally identifiable information (PII) detection and masking in text, exceling at high-throughput data sanitization workflows. It boasts a notable technical trait in its long-context capability, with a 131,072-token context window enabling processing of long text with high throughput and no chunking.
Input
Output
Context
131K
Max Output
-
Parameters
1.4B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output TokensNot available
Parameters1.4B
Release DateApr 17, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Privacy Filter
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.