Sobre

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).

Modelos Relacionados

GPT-5.4 mini (xhigh)2026-03-17 GPT-5.4 nano (xhigh)2026-03-17 GPT-5.4 nano (medium)2026-03-17 GPT-5.4 mini (medium)2026-03-17 GPT-5.4 nano (Non-Reasoning)2026-03-17 GPT-5.4 mini (Non-Reasoning)2026-03-17 GPT-5.4 (xhigh)2026-03-05 GPT-5.4 (Non-reasoning)2026-03-05

OpenAI: gpt-oss-safeguard-20b

Sobre

Modelos Relacionados

Preços

Calculadora de Custo

vs. Modelos Similares

Desempenho

Open Source

Comparação Rápida

Modelos Similares