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 and safety labeling.
Try NowContent classification and moderation
LLM output filtering
Trust and safety labeling
131,072 tokens
65,536 tokens
$0.075
$0.30
$0.037
$15
$0.19