# ChatGPT-User vs GoogleOther

ChatGPT-User and GoogleOther compared on 12 documented fields, from 18 claims, last verified 2026-09-15.

| Field | ChatGPT-User | GoogleOther | Comparison |
| --- | --- | --- | --- |
| cites_sources | not_documented | not documented | different |
| honours_crawl_delay | not_documented | no | different |
| observed_fetches_robots_txt | not documented | no | different |
| observed_requested_mcp_endpoint | not documented | yes | different |
| publishes_ip_list | yes | yes | same |
| purpose_documented | user_fetch | mixed | different |
| reads_llms_txt | not_documented | not documented | different |
| respects_robots_txt | partial | yes | different |
| robots_txt_token | not documented | GoogleOther | different |
| separate_search_and_training_tokens | not_documented | not_documented | same |
| user_agent_string_full | Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ChatGPT-User/1.0; +https://openai.com/bot | not documented | different |
| verifiable_by_rdns | not_documented | yes | different |

## Differences

| Field | ChatGPT-User statement | GoogleOther statement |
| --- | --- | --- |
| cites_sources | OpenAI does not publish whether ChatGPT responses cite pages fetched by ChatGPT-User. | not documented |
| honours_crawl_delay | OpenAI does not publish whether ChatGPT-User honours the robots.txt Crawl-delay directive. | Google does not support the robots.txt Crawl-delay directive for GoogleOther. |
| observed_fetches_robots_txt | not documented | GoogleOther made 93 requests to Rattlesnakes By Mail between 2026-09-13T20:00Z and 2026-09-15T09:00Z and fetched /robots.txt on none of those requests. GoogleOther's first request to Rattlesnakes By Mail was the home page at 2026-09-14T12:03:30Z. |
| observed_requested_mcp_endpoint | not documented | GoogleOther requested the /mcp endpoint of Rattlesnakes By Mail twice between 2026-09-13T20:00Z and 2026-09-15T09:00Z, at 2026-09-14T15:07:30Z and at 2026-09-14T18:27:49Z. Rattlesnakes By Mail returned status 405 to both GoogleOther requests for /mcp. |
| purpose_documented | ChatGPT-User visits web pages for user actions in ChatGPT and in Custom GPTs. | GoogleOther is a generic crawler that Google product teams use to fetch publicly accessible content from sites. |
| reads_llms_txt | OpenAI does not publish whether ChatGPT-User reads llms.txt files. | not documented |
| respects_robots_txt | ChatGPT-User fetches pages in response to user actions in ChatGPT, and OpenAI states that robots.txt rules may not apply to ChatGPT-User fetches. | GoogleOther obeys robots.txt rules when crawling automatically. |
| robots_txt_token | not documented | The robots.txt token for GoogleOther is GoogleOther. |
| user_agent_string_full | ChatGPT-User sends the user agent string Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ChatGPT-User/1.0; +https://openai.com/bot. | not documented |
| verifiable_by_rdns | OpenAI does not publish a reverse-DNS verification method for ChatGPT-User. | GoogleOther requests are verifiable by reverse DNS lookup resolving to googlebot.com, google.com, or googleusercontent.com. |

## Sources

- https://developers.google.com/crawling/docs/crawlers-fetchers/verifying-googlebot
- https://developers.google.com/search/blog/2019/07/a-note-on-unsupported-rules-in-robotstxt
- https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers
- https://developers.google.com/static/crawling/ipranges/common-crawlers.json
- https://developers.openai.com/api/docs/bots
- https://openai.com/chatgpt-user.json
- https://rattlesnakesbymail.com/observed/googleother