{
 "slug": "gptbot",
 "name": "GPTBot",
 "operator": "OpenAI",
 "operator_slug": "openai",
 "category": "ai-training",
 "category_label": "AI training crawlers",
 "robots_token": "GPTBot",
 "user_agent_substring": "GPTBot",
 "user_agent_example": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.2; +https://openai.com/gptbot",
 "respects_robots_txt": "documented",
 "respects_robots_txt_label": "obeys robots.txt (documented)",
 "verification_method": "published-ranges",
 "verification_label": "published IP ranges",
 "published_ip_ranges_url": "https://openai.com/gptbot.json",
 "ip_ranges_endpoint": "https://www.pathwren.workers.dev/ip-ranges/openai-gptbot.json",
 "ipv4_prefix_count": 21,
 "ipv6_prefix_count": 0,
 "what_it_is": "OpenAI's bulk crawler. Pages it fetches may be used to train future OpenAI foundation models. It is not the bot that puts you in ChatGPT's search results, and blocking it does not remove you from them.",
 "cost_of_blocking": "Your content is excluded from training data for future OpenAI models. No effect on ChatGPT search visibility, on citations, or on links a user pastes into ChatGPT.",
 "operator_docs": "https://platform.openai.com/docs/bots",
 "html_url": "https://www.pathwren.workers.dev/crawler/gptbot.html",
 "json_url": "https://www.pathwren.workers.dev/crawler/gptbot.json",
 "last_reviewed": "2026-09-03",
 "links": [
  {
   "rel": "self",
   "href": "https://www.pathwren.workers.dev/crawler/gptbot.json",
   "type": "application/json"
  },
  {
   "rel": "changes",
   "href": "https://www.pathwren.workers.dev/changes.json?since=111",
   "type": "application/json",
   "title": "What changed since your cursor — poll this instead of re-downloading this document",
   "cursor_param": "since",
   "head_cursor": 111,
   "min_poll_seconds": 21600,
   "how": "Read `cursor` from the response and send it back as `since`. It advances only when something really changed, so an unchanged answer is proof rather than luck — about 2.5 KB, or a 304 with no body if you send back the ETag."
  },
  {
   "rel": "related",
   "href": "https://www.pathwren.workers.dev/data/agents.json",
   "type": "application/json",
   "title": "Every crawler record in one file"
  },
  {
   "rel": "related",
   "href": "https://www.pathwren.workers.dev/crawler/gptbot.md",
   "type": "text/markdown"
  },
  {
   "rel": "related",
   "href": "https://www.pathwren.workers.dev/ip-ranges/openai-gptbot.json",
   "type": "application/json"
  },
  {
   "rel": "service-desc",
   "href": "https://www.pathwren.workers.dev/openapi.json",
   "type": "application/json",
   "title": "Every read endpoint, described formally"
  }
 ]
}