About gpt-oss-safeguard-20b
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust & safety labeling.
Learn more about this model in OpenAI's gpt-oss-safeguard [user guide](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).
Specifications
- Provider
- OpenAI
- Context Length
- 131,072 tokens
- Input Types
- text
- Output Types
- text
- Category
- GPT
- Added
- 10/29/2025