{
  "dataset": "ai-crawler-directory-data",
  "dataset_url": "https://bozos.si/ai-crawlers.json",
  "updated": "2026-10-20",
  "license": "CC0-1.0",
  "collection": "crawlers",
  "id": "gptbot",
  "permalink": "https://bozos.si/ai-crawlers.json#gptbot",
  "record": {
    "id": "gptbot",
    "permalink": "https://bozos.si/ai-crawlers.json#gptbot",
    "cite": "GPTBot (OpenAI): Crawls content that may be used to train OpenAI's generative AI foundation models. robots.txt: obeys. Used for AI training: yes. Source: BOZOS, AI Crawler Directory, verified 2026-10-20, high confidence. https://bozos.si/ai-crawlers.json#gptbot",
    "review_due": "2027-01-18",
    "token": "GPTBot",
    "operator": "OpenAI",
    "category": "training",
    "purpose": "Crawls content that may be used to train OpenAI's generative AI foundation models.",
    "robots_txt": "obeys",
    "robots_note": "Disallowing GPTBot signals the site's content should not be used for training.",
    "used_for_ai_training": true,
    "documentation": "https://developers.openai.com/api/docs/bots",
    "ip_ranges": "https://openai.com/gptbot.json",
    "user_agent_example": "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; GPTBot/1.4; +https://openai.com/gptbot",
    "docs_vs_reports": "none-recorded",
    "verified": "2026-10-20",
    "confidence": "high",
    "evidence": [
      {
        "supports": "purpose",
        "quote": "It is used to crawl content that may be used in training our generative AI foundation models.",
        "source": "https://developers.openai.com/api/docs/bots"
      },
      {
        "supports": "robots_txt",
        "quote": "Disallowing GPTBot indicates a site's content should not be used in training generative AI foundation models.",
        "source": "https://developers.openai.com/api/docs/bots"
      }
    ]
  }
}