What is OAI-SearchBot?
OAI-SearchBot is OpenAI's crawler for surfacing websites in ChatGPT's search features, and sites that opt out of it are not shown in ChatGPT search answers. Of the four user agents OpenAI documents, it is the one that decides whether your pages can appear as sources in ChatGPT search. OpenAI recommends allowing it, separately from GPTBot, which collects training data.
What is OAI-SearchBot's user agent string?
OAI-SearchBot identifies itself with the product token OAI-SearchBot, and that token is what a robots.txt group must name. Unlike GPTBot's, its full string starts with a browser-style block, and OpenAI notes the version numbers can change, so match on the token. When it fetches your robots.txt, OpenAI says the string may carry an extra robots.txt marker.
To confirm a request is genuine, check its IP against openai.com/searchbot.json, the list OpenAI publishes for this agent.
This is the full string OpenAI's documentation gives (OpenAI's crawler docs, read Oct 15, 2026):
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/searchbotWhat does OAI-SearchBot decide?
OAI-SearchBot decides whether ChatGPT search can show your site. OpenAI says it is used to surface websites in ChatGPT's search features, and that sites opted out of it will not be shown in ChatGPT search answers, though they can still appear as navigational links.
OpenAI recommends allowing OAI-SearchBot in robots.txt and allowing requests from its published IP ranges. Its rule is independent of GPTBot's: allowing OAI-SearchBot does not opt you into training.
How is OAI-SearchBot different from GPTBot?
OAI-SearchBot is for search and GPTBot is for training. The two rules are set separately, and OpenAI gives the split as its own example: allow OAI-SearchBot to appear in search results, disallow GPTBot to keep content out of training. If both are allowed, OpenAI says it may use one crawl for both purposes.
| Agent | Purpose | Published IP list |
|---|---|---|
| OAI-SearchBot | Surfaces websites in ChatGPT search | openai.com/searchbot.json |
| GPTBot | Crawls content that may train OpenAI's foundation models | openai.com/gptbot.json |
| ChatGPT-User | Visits a page when a user's question or a GPT Action calls for it | openai.com/chatgpt-user.json |
| OAI-AdsBot | Checks landing pages submitted as ChatGPT ads | openai.com/adsbot.json |
How do you check that you allow OAI-SearchBot?
Check three places, because any one of them can shut OAI-SearchBot out while the others look fine:
- robots.txt: no group naming OAI-SearchBot disallows your pages, and no catch-all User-agent: * rule blocks them without an OAI-SearchBot group to override it.
- Your CDN or firewall: no bot-blocking setting rejects OAI-SearchBot's requests or its published IP ranges before robots.txt is even read.
- The page itself: the text you want cited is in the HTML, not only added after JavaScript runs.
- Then give it time: OpenAI says robots.txt changes can take about 24 hours to show in search results.
# Allow ChatGPT search, keep content out of training
User-agent: OAI-SearchBot
Allow: /
User-agent: GPTBot
Disallow: /What does this mean for being cited in ChatGPT?
In the public Tesla example (Oct 4, 2026), ChatGPT cited tesla.com 12 times in 93 citations across 25 buyer questions, about 13%, the highest share of the four engines. The other three together cited tesla.com 5 times in 915.
A site that opts out of OAI-SearchBot cannot be among those sources, by OpenAI's own description. The free AI crawler checker reads your live robots.txt for OAI-SearchBot and the other AI agents in seconds; whether ChatGPT then names you is measured by asking it the questions. See how ChatGPT chooses the brands it names.
Common questions about OAI-SearchBot
Does allowing OAI-SearchBot let OpenAI train on my content?
No. OpenAI says each robots.txt setting is independent: training is GPTBot's rule. If you allow both, OpenAI says it may use one crawl for both purposes, so disallow GPTBot if you do not want training use.
How long does a robots.txt change take for ChatGPT search?
OpenAI says it can take about 24 hours from a robots.txt update for its systems to adjust for search results.
If I block OAI-SearchBot, can my site still appear in ChatGPT?
OpenAI says opted-out sites are not shown in ChatGPT search answers, but can still appear as navigational links. ChatGPT-User may also open a page a user asks about, and OpenAI says robots.txt rules may not apply to those user-started visits.
Does OAI-SearchBot run JavaScript?
OpenAI's crawler page does not say. Put the text you want cited in the HTML the server sends, so no crawler depends on running scripts to read it.
Related terms
- GPTBot
GPTBot is OpenAI's web crawler for collecting content that may be used to train OpenAI's generative AI foundation models.
- ClaudeBot
ClaudeBot is Anthropic's web crawler that collects web content that could contribute to training Anthropic's Claude models.
- PerplexityBot
PerplexityBot is Perplexity's crawler that indexes web pages so they can be surfaced and linked in Perplexity's search results.
Worked example: Tesla, public AI answers, Oct 4, 2026: Proofsource's first scan of Tesla, 25 buyer questions and 5 brand questions, one answer per question on each of four engines. A small sample from one brand, shown as an example, not a benchmark.
See where AI leaves you out, and what to fix.
See which buyer questions name your brand, who gets named instead, and what to fix. 200 answers. 25 Prompts/Question. Top AI engines. 2 days. Free. No card.
Google AI OverviewsGoogle AI Mode
