OpenAI has its own index, including cached web content. It's used for offline web search:

> Offline web search is a better fit for stable web research than for workflows that require real-time freshness, guaranteed URL availability, or audit-grade evidence.

> OpenAI’s systems may update some indexed content quickly, but there is no refresh SLA for a specific URL. A particular page may be refreshed on a different schedule depending on the site, crawl access, caching, popularity, and other technical factors.