Now in research preview: gpt-oss-safeguard Two open-weight reasoning models built for safety classification. openai.com/index/introducing…

gpt-oss-safeguard lets developers use their own custom policies to classify content. The model interprets those policies to classify messages, responses, and conversations. These models are fine-tuned versions of our gpt-oss open models, available under Apache 2.0 license. Now on Hugging Face. huggingface.co/collections/o…

Our gpt-oss-safeguard models outperform gpt-5-thinking and the gpt-oss open models on multi-policy accuracy.

We partnered with ROOST to shape this open-weight release, identify developers’ critical needs, test the model, and produce developer documentation. Our cookbook explains how to write policy prompts that maximize gpt-oss-safeguard's reasoning power, choose the right policy length for deep analysis, and integrate oss-safeguard's reasoning outputs into production Trust & Safety systems. cookbook.openai.com/articles…