OpenAI
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...
| Specifications | |
|---|---|
| Provider | OpenAI |
| Input pricing | $0.07/M tokens |
| Output pricing | $0.30/M tokens |
| Context length | 131K tokens |
| Max output | 66K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | GPT |
| Content moderated | No |
| HuggingFace | openai/gpt-oss-safeguard-20b |
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p