OpenAI: gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20bgpt-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...
Input modalitiesT
Output modalitiesT
Source-linkedClosed weights
Context window131.072K
Maximum output65.536K
Provider offers0
Knowledge cutoffUndisclosed
CapabilitiesWhat this model supports
- Creator
- OpenAI
- Family
- Not documented
- Modalities
- Text
- License
- Not documented
- Release date
- Not documented
- Model ID
openai/gpt-oss-safeguard-20b
No known providers available.
EvidencePublished benchmark results
Insufficient benchmark coverage. ModelBench does not infer a score from price, context size, or model name.
