Bot directory · AI search

AI search · OpenAI

OAI-SearchBot

OAI-SearchBot is the crawler OpenAI uses to find pages for ChatGPT’s search answers and links. A site that blocks it isn’t shown in ChatGPT search answers. It is separate from GPTBot, OpenAI’s training crawler, so you can appear in ChatGPT search without your pages being used for training.

Checked against OpenAI’s documentation on 19 October 2026

Operator
OpenAI
Purpose
AI answers. Crawlers that build the indexes AI assistants answer from and cite. Blocking one keeps you out of its answers.
robots.txt token
OAI-SearchBot
We test with
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
OpenAI’s example string for page requests, above.
Documentation
developers.openai.com/api/docs/bots

What OAI-SearchBot does

OAI-SearchBot is used to surface websites in search results in ChatGPT’s search features. Sites that are opted out of OAI-SearchBot will not be shown in ChatGPT search answers, though can still appear as navigational links.

developers.openai.com
BotWhat it doesModel training
GPTBotCollects pages that may be used to train OpenAI’s modelsYes
OAI-SearchBotIndexes pages for ChatGPT search answers and linksNo training sentence from OpenAI; it is the search control
ChatGPT-UserOpens a page when a ChatGPT user or a custom GPT asks for itNo

OpenAI’s page has no training sentence for OAI-SearchBot; it presents GPTBot as the training control and says a site that allows both may be crawled once for both purposes.

The OAI-SearchBot user agent

RequestUser agent string
PagesMozilla/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
robots.txtMozilla/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; robots.txt; +https://openai.com/searchbot

Both are OpenAI’s examples; the versions change. The string starts like Chrome on a Mac, so a rule that matches browsers by their opening words also matches OAI-SearchBot. Match on OAI-SearchBot.

How OAI-SearchBot reads robots.txt

Each setting is independent of the others – for example, a webmaster can allow OAI-SearchBot in order to appear in search results while disallowing GPTBot to indicate that crawled content should not be used for training OpenAI’s generative AI foundation models. If your site has allowed both bots, we may use the results from just one crawl for both use cases to avoid duplicative crawling. For search results, please note it can take ~24 hours from a site’s robots.txt update for our systems to adjust.

developers.openai.com

OAI-SearchBot IP addresses and how to verify them

OpenAI publishes the addresses each of its bots crawls from as JSON, in the same format Google uses. It documents no reverse DNS names (the addresses we looked up had none), so the list is the way to verify OAI-SearchBot. Every list is IPv4 only.

ListCoversIPv4IPv6Dated
openai.com/searchbot.jsonOAI-SearchBot3902 January 2026
openai.com/gptbot.jsonGPTBot18022 September 2026
openai.com/chatgpt-user.jsonChatGPT-User23407 October 2026

Fetch the lists automatically rather than copying them: OpenAI adds and removes ranges, and an allowlist built from an old copy turns real requests away.

Check an IP now

Paste an address from your logs. We match it against OpenAI’s current lists, along with the lists of the other operators that publish them.

Block OAI-SearchBot at your firewall or CDN

robots.txt asks; a firewall enforces. Blocking OAI-SearchBot keeps your site out of ChatGPT search answers, so most sites allow it. Match the name case-insensitively and anywhere in the string, never a full string or a version.

Cloudflare

In Security → WAF → Custom rules, create a rule with this expression and the action Block. Cloudflare’s contains is case-sensitive, hence lower().

(lower(http.user_agent) contains "oai-searchbot")

Cloudflare also has one-click controls: AI bot policies, which block AI crawlers by what they do (search, agent or training), and AI Crawl Control, which lets you allow or block crawlers one by one and shows which of them fetch your pages.

nginx

# in the http block
map $http_user_agent $blocked_bot {
    default 0;
    ~*oai-searchbot 1;
}

# in the server block
if ($blocked_bot) { return 403; }

Block OAI-SearchBot

Add a group naming it to /robots.txt. Compliant crawlers stop before requesting any page. A firewall rule on the user agent is the only way to enforce it against crawlers that ignore robots.txt. Blocking OAI-SearchBot removes your pages from ChatGPT search answers. To keep them out of training only, block GPTBot instead.

User-agent: OAI-SearchBot
Disallow: /

Allow OAI-SearchBot when everything else is blocked

A group naming the bot wins over User-agent: *, so an explicit allow lets it in while your catch-all rules stay in place.

User-agent: OAI-SearchBot
Allow: /

User-agent: *
Disallow: /

Does OAI-SearchBot reach your site?

The checker applies your robots.txt the way OAI-SearchBot does, then requests your page with the user agent above, alongside 29 other bots, and opens the report on OAI-SearchBot.

Questions about OAI-SearchBot

What is OAI-SearchBot?

OAI-SearchBot is the crawler OpenAI uses to surface websites in ChatGPT’s search features. Sites that block it aren’t shown in ChatGPT search answers, though they can still appear as navigational links.

Is OAI-SearchBot used to train OpenAI’s models?

OpenAI presents GPTBot as the training control and says each setting is independent: you can allow OAI-SearchBot to appear in search while disallowing GPTBot to keep content out of training.

Should I block OAI-SearchBot?

Only if you don’t want to appear in ChatGPT search. Blocking it removes your pages from ChatGPT’s search answers. To opt out of training while staying in search, block GPTBot and allow OAI-SearchBot.

What IP addresses does OAI-SearchBot use?

OpenAI publishes them at openai.com/searchbot.json: 39 IPv4 ranges and no IPv6 in October 2026. Verify an address against the list, since OpenAI documents no reverse DNS names.

How long until ChatGPT search reflects a robots.txt change?

OpenAI says it can take about 24 hours from a robots.txt update for its systems to adjust.

Also run by OpenAI: GPTBot, ChatGPT-User.

Other ai search: PerplexityBot, Claude-SearchBot, DuckAssistBot, Amazonbot, YouBot.

Build a complete file with the robots.txt generator.