gpt-oss-safeguard-20b reasoning
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.
Capabilities
Context Window 131k tokens
Max Output 65k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.07
Output $0.30
Cache Read $0.04
Cache Write -
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_p