OpenAI
OpenAI: gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b
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.
Input
$0.075
/ 1M tokens
Output
$0.3
/ 1M tokens
Context window
131.07K
tokens
Limits
Context
131,072
tokens
Max output
65,536
50% of the context window
Parameters
21,511,953,984
Model facts
Author
OpenAI
Tokenizer
GPT
Modality
Text -> Text
License
Apache-2.0
Created
Oct 29, 2025
Hugging Face
openai/gpt-oss-safeguard-20b
Reasoning
Required
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextOutput · Text
Generation controls
Include reasoningMax tokensReasoningResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop p