OAI-SearchBot
OpenAI uses OAI-SearchBot to index sites for ChatGPT's search answers.
- Operated by
- OpenAI
- robots.txt token
OAI-SearchBot- User-Agent sent
- Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36; compatible; OAI-SearchBot/1.4; +https://openai.com/searchbot
- Honours robots.txt
- Yes — OpenAI documents that it honours robots.txt.
This one is on the answer path.
OpenAI uses it to index your site, so while it's blocked your pages can't appear in ChatGPT's search answers.
Two lines in robots.txt.
Block OAI-SearchBot
User-agent: OAI-SearchBot
Disallow: /Goes in the robots.txt at the root of your domain.
Allow OAI-SearchBot
User-agent: OAI-SearchBot
Allow: /Only needed if a broader rule already blocks it — a group of its own overrides the wildcard.
Group selection matches the token, not the full User-Agent string, and it is case-insensitive. A rule under User-agent: * applies only when the crawler has no group of its own.
OpenAI runs more than one, and they do different jobs.
Blocking one does not block the others. This is where most advice goes wrong: the rule that stops model training is not the rule that decides whether you appear in an answer.
Everything on this page was read from OpenAI’s own published source on . Read the source. Vendors change these pages without announcing it — if you find something here that no longer matches, tell us and we’ll correct it.
We run a crawler too. Here is what it does and how to block it.
Knowing what OAI-SearchBot does doesn’t tell you whether your site lets it in.
The free checker reads your robots.txt and asks your site for its homepage as each major AI crawler, then tells you which ones it turned away. No signup, about 20 seconds.