Loading...
Loading...
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...
No benchmark data available.
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.