OpenAI · Model identity
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...
1pricing route
What published route metadata supports
CachingHugging FaceReasoningStructured outputTool use
Input modalities
Text
Supported API parameters
include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2025-10-29
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | openai/gpt-oss-safeguard-20b | $0.075 | $0.0375 | $0.3 | 131K | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
Tracking from today forward
No verified price changes have been recorded since tracking began on Aug 26, 2026. Today’s catalog is the baseline; LLMPrice does not invent or backfill older prices.
See all verified price changes →