AI crawlers·OpenAI
ChatGPT-User
OpenAI’s fetcher for ChatGPT users. When someone asks ChatGPT or a custom GPT a question, it may visit a web page to answer, and GPT Actions use it to reach outside apps. OpenAI says it does not crawl the web automatically.
- Operator
- OpenAI
- robots.txt token
ChatGPT-User- Follows robots.txt
- Not always
- IP ranges
- Published
- In Spreelytics
- AI answers tab
- Source
- OpenAI’s documentation
What user agent does ChatGPT-User use?
OpenAI publishes this user agent string for ChatGPT-User.
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ChatGPT-User/1.0; +https://openai.com/botHow do I block ChatGPT-User?
OpenAI says that because a person starts these visits, robots.txt rules may not apply to ChatGPT-User. It is also not what decides whether your site appears in ChatGPT search: OAI-SearchBot is.
This is the robots.txt rule that names it:
User-agent: ChatGPT-User
Disallow: /How do I check that a ChatGPT-User visit is real?
Anyone can put a crawler’s name in a user agent, so the name alone proves nothing.
OpenAI publishes the IP addresses ChatGPT-User makes requests from, as JSON.
Spreelytics runs this check for you. Every crawl that claims to be ChatGPT-User is compared with the IP ranges OpenAI publishes, refreshed every 12 hours, and one from outside them counts as spoofed.
How do I see ChatGPT-User visits on my site?
Your server’s access logs record the user agent of each request, so you can search them for “ChatGPT-User”.
Or add the Spreelytics server middleware, @spreelytics/ai-crawl. It recognises ChatGPT-User by its user agent and counts each visit on the Bots page under AI answers, as ChatGPT, apart from your visitor numbers.
Sources: developers.openai.com/api/docs/bots
See your own numbers today.
Free up to 100k events a month · no credit card