← All models View on HuggingFace →
OpenAI: gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b
Tool useJSONReasoningStreaming
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...
Pricing
Input
$0.075 / 1M
Output
$0.3 / 1M
Specs
Context
131,072 tokens
Input
text
Output
text
Released: 2025-10
Supported parameters
include_reasoningmax_tokensreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_p
Open weights · HuggingFace
59,013 downloads/mo
228 likes
apache-2.0 text-generation