GPT-OSS Safeguard 20B

JSON →
openai llm
text

A 20-billion-parameter safety classifier from OpenAI designed to detect harmful content and enforce usage policies in open-source deployments.

context window 131K tokens
max output 66K tokens
input price $0.075 / 1M tokens
output price $0.3 / 1M tokens
json-modestreamingopen-weightsfunction-callingtool-usereasoning
releasedMar 2025
knowledge cutoffJun 2024