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.
OpenAI: gpt-oss-safeguard-20b – Recent Activity and Usage Stats
Recent activity on gpt-oss-safeguard-20b
Total usage per day on OpenRouter
Prompt
306M
Reasoning
41.9M
Completion
13.8M
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.