Back to all models
openai
openaiOpenAI: 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](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide).
openai/gpt-oss-safeguard-20b
Context Size
131.072K
Input Price
461.25 Ks/M
Output Price
1,845 Ks/M
Architecture
Text
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_p
Details
TokenizerGPT
Max Completion65,536 tokens
Provider Context131.072K tokens
ModeratedNo