Skip to content
OA

oai-searchbot

GoodBotCommunity-sourced

A dedicated crawler used by OpenAI to index web content for the purpose of providing real-time, cited search results within ChatGPT. Operated by OpenAI.

GoodBot
Assessment
AI Search
Category
Bot
Kind
1
Data sources
AI-generated summary, drawn from Cloudflare, operator docs, and community data

What is oai-searchbot?

oai-searchbot is the official web crawler operated by OpenAI, designed to fetch and index public web pages to power the search capabilities of ChatGPT. Unlike general-purpose crawlers, its primary objective is to retrieve current information to ensure that AI responses are grounded in up-to-date, verifiable sources. It operates with a focus on transparency, allowing site owners to control its access via standard robots.txt directives.

Helpful — It is a verified crawler that respects robots.txt and provides attribution to content creators within AI-generated responses.

Identification

Bot name
oai-searchbot
Operator
OpenAI
Category
AI Search
Verification
Community-sourced
Main use cases
Web indexing for AI searchRetrieval-augmented generation (RAG)Providing real-time information in ChatGPT

Why it crawls your site

The bot crawls the web to build a comprehensive index of information that allows OpenAI's models to answer user queries about current events, technical documentation, and other time-sensitive topics. By processing this data, the bot enables the model to provide direct citations and links back to the original source material, fostering a symbiotic relationship between AI platforms and content publishers. Site administrators can verify the bot by performing a reverse DNS lookup on the originating IP address to ensure it resolves to the openai.com domain.

IP ranges

Requests from oai-searchbot originate from these published ranges. For strict verification, match the source IP against this list in addition to checking the user-agent and reverse-DNS.

Showing 24 of 35 ranges

Block or allow oai-searchbot

Block it

Add a Disallow rule for oai-searchbot in your robots.txt file. You can also block at the server level using your web server configuration or CDN firewall rules to filter requests matching the user-agent string.

# Block oai-searchbot from crawling your entire site
User-agent: oai-searchbot
Disallow: /

# Allow oai-searchbot full access
User-agent: oai-searchbot
Allow: /
Allow & verify

Ensure your robots.txt allows oai-searchbot. Verify requests by checking the user-agent string.

Traffic & trends

Cloudflare Radar traffic

No Cloudflare traffic data available.

Google Trends interest

Loading trend data…

Data sources

This profile is compiled from the following sources.

GithubWhitelist
Last updated July 21, 2026