OpenAI 的 GPT-OSS-Safeguard-20B 安全模型現已在 Vercel AI Gateway 中推出
Original: OpenAI's GPT-OSS-Safeguard-20B now available in Vercel AI Gateway
Vercel announced in its Changelog that it is officially adding support for OpenAI's new safety guardrail model, **GPT-OSS-Safeguard-20B**…
Vercel 宣布其 AI Gateway 已正式支援 OpenAI 推出的 GPT-OSS-Safeguard-20B 模型。這款擁有 200 億參數的安全防護模型，旨在幫助開發者在 Gateway 端直接進行輸入與輸出的安全過濾。透過此整合，開發者能更輕鬆地為 AI 應用部署強大的安全護欄（Guardrails），有效防止惡意提示詞攻擊並過濾不當內容。
Vercel announced in its Changelog that it is officially adding support for OpenAI's new safety guardrail model, **GPT-OSS-Safeguard-20B**, within the Vercel AI Gateway.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Vercel Changelog →Summaries are AI-generated; the original article is authoritative.