ChatGPT-User

Questions about ChatGPT-User

What is ChatGPT-User?

ChatGPT-User fetches a page when an action in ChatGPT or a Custom GPT requires it. OpenAI says it is not used for crawling the web automatically.

Does ChatGPT-User follow robots.txt?

OpenAI says that because these actions are initiated by a user, robots.txt rules may not apply. A Disallow rule for ChatGPT-User is a published preference, not a reliable block.

Does ChatGPT-User decide whether my site appears in ChatGPT search?

No. OpenAI says search inclusion is governed by OAI-SearchBot.

OpenAI documents ChatGPT-User as the crawler used “when users ask ChatGPT or a CustomGPT a question” and it “may visit a web page” to help answer it, including when a Custom GPT takes an action against an external site through GPT Actions.

Why this is different from GPTBot

ChatGPT-User requests are triggered by a specific person’s question, not a bulk crawl. It is tracked separately in CrawlPact’s registry from the training-purpose GPTBot and the search-purpose OAI-SearchBot — a website can restrict one without restricting the others.

A robots.txt limitation worth knowing

OpenAI’s own documentation states: “Because these actions are initiated by a user, robots.txt rules may not apply.” A Disallow rule aimed at ChatGPT-User is therefore not a reliable way to prevent a specific page from being fetched on a person’s behalf — this is OpenAI’s documented position (wording checked against its bots page on 2026-09-19), not a CrawlPact-observed workaround. See /limitations for what a robots.txt rule can and cannot guarantee more generally.

Site-owner controls

A robots.txt rule for ChatGPT-User may not be honoured, per OpenAI’s own documentation above — unlike the search- and training-purpose tokens, where OpenAI’s page makes no such statement. It does not affect GPTBot (training) or OAI-SearchBot (search), each governed by its own token.

Note on this page’s source

OpenAI’s crawler documentation moved from platform.openai.com/docs/bots to developers.openai.com/api/docs/bots since this record was first added — the citation above reflects the current location as of the last-verified date.

How to verify ChatGPT-User requests

OpenAI documents this user agent:

                  Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ChatGPT-User/1.0; +https://openai.com/bot
                

OpenAI publishes ChatGPT-User's IP ranges at https://openai.com/chatgpt-user.json. Operator documentation.

A user-agent string alone can be copied by anyone; confirming a request really came from OpenAI needs your server or CDN logs. CrawlPact audits declared policy and does not see your traffic.

Example robots.txt configuration

To disallow ChatGPT-User specifically, without affecting any other crawler:

User-agent: ChatGPT-User
Disallow: /

If no dedicated User-agent: ChatGPT-User group exists in a domain'srobots.txt, this crawler falls back to whatever the wildcard User-agent: * group says (RFC 9309) — see robots.txt syntax basics for how group selection works. A robots.txt rule is a published instruction; it does not technically prevent access.

Official source

https://developers.openai.com/api/docs/bots

Verified against the source above as of 24 July 2026 — see how CrawlPact verifies crawler information.