{
 "slug": "cohere-training-data-crawler",
 "name": "cohere-training-data-crawler",
 "operator": "Cohere",
 "operator_slug": "cohere",
 "category": "ai-training",
 "category_label": "AI training crawlers",
 "robots_token": "cohere-training-data-crawler",
 "user_agent_substring": "cohere-training-data-crawler",
 "user_agent_example": "Mozilla/5.0 (compatible; cohere-training-data-crawler)",
 "respects_robots_txt": "documented",
 "respects_robots_txt_label": "obeys robots.txt (documented)",
 "verification_method": "none",
 "verification_label": "no published verification method",
 "published_ip_ranges_url": null,
 "ip_ranges_endpoint": null,
 "ipv4_prefix_count": 0,
 "ipv6_prefix_count": 0,
 "what_it_is": "Cohere's separately-named bulk crawler for model training data, split out so consent for training and consent for retrieval can differ.",
 "cost_of_blocking": "Excluded from Cohere model training.",
 "operator_docs": "https://cohere.com/",
 "html_url": "https://www.pathwren.workers.dev/crawler/cohere-training-data-crawler.html",
 "json_url": "https://www.pathwren.workers.dev/crawler/cohere-training-data-crawler.json",
 "last_reviewed": "2026-09-01"
}