How Fast New Pages Get Cited in AI Search and How to Speed It Up
How long new content takes to show up as a citation in AI answers, engine by engine: what Google, Bing, OpenAI and Perplexity document, plus a test to time it.
On this page
How long does it take for new content to show up as a citation in AI answers? We found no such number from any of the four operators covered here. What they do publish are the clocks around it. Google says crawling can take anywhere from a few days to a few weeks. OpenAI says its search systems take about 24 hours to adjust after a robots.txt update, and Perplexity says up to 24 hours. Microsoft says Bing typically rechecks a sitemap at least once a day. The step that decides the outcome, an engine choosing your page as a source for a specific question, has no published timing anywhere we looked. So the useful work is to shorten the parts each operator documents and to time the rest on your own pages. We read every document cited below on November 6, 2026.
The mistake we see most often is treating "indexed" as the finish line. Indexing only makes a page eligible. Citation is a separate choice each engine makes question by question, and the wait for it has to be measured.
What each engine documents about new pages
How fast AI search engines index new content for citations differs by engine, and so does the route in. The table summarizes what each operator's own documentation says.
| Engine | Where the page has to be | Crawler to allow | Published timing | Documented ways to speed discovery | Citation reporting |
|---|---|---|---|---|---|
| Google AI Overviews and AI Mode | Indexed by Google and eligible to show with a snippet | Googlebot | Crawling takes a few days to a few weeks | URL Inspection for a few URLs, a sitemap for many | Generative AI performance report in Search Console (impressions by page and date) |
| Microsoft Copilot and AI summaries in Bing | Discovered and indexed by Bing | Bing's crawler | Sitemaps typically rechecked at least once a day | A sitemap with accurate lastmod, plus IndexNow | AI Performance report in Bing Webmaster Tools (public preview) |
| ChatGPT search | Reachable by OAI-SearchBot | OAI-SearchBot | About 24 hours for a robots.txt change to take effect | We found no submission route | We found no publisher report |
| Perplexity | Reachable by PerplexityBot | PerplexityBot | Up to 24 hours for robots.txt changes to be reflected | We found no submission route | We found no publisher report |
Two different clocks sit in that table. The 24-hour figures from OpenAI and Perplexity describe how long a robots.txt change takes to reach their systems, and neither page gives a time for discovering a brand-new URL. Google's range is about crawling, and Google adds that a recrawl request does not guarantee inclusion in results at all.
Getting a new page into AI Overviews and AI Mode
How quickly new website content gets indexed and appears in Google AI Overviews citations follows ordinary Google indexing. According to Google Search Central, a page has to be indexed and eligible to be shown in Google Search with a snippet to appear as a supporting link, and there are no additional technical requirements. Google says no new machine-readable files, AI text files, markup or special structured data are needed, and that indexing and serving aren't guaranteed. The same page says both features may use query fan-out, issuing multiple related searches across subtopics and data sources to develop a response, while its models identify more supporting web pages. That makes a narrow sub-question a realistic first target for a new page.
The documented route is the one Google gives for any page. Its recrawl guidance on Google Search Central says to use the URL Inspection tool for a few URLs, within a quota, and a sitemap for many, and it puts crawling at "anywhere from a few days to a few weeks." Requesting a recrawl of the same URL more than once won't get it crawled any faster.
Two Google tokens get confused here. Google Search Central states that Google-Extended does not affect a site's inclusion in Google Search and is not used as a ranking signal; it governs Gemini model training and grounding in Gemini Apps and Vertex AI. Blocking it leaves AI Overviews eligibility alone; for Search, Googlebot is the crawler whose robots.txt rules count.
Measurement got better in 2026. Google's AI features page still counts these appearances inside overall Search traffic, under the Web search type in the Search Console Performance report. Separately, Search Console Help says the Generative AI performance report reached all websites worldwide as of August 31, 2026. It counts impressions, how many times links to your site were shown in AI Overviews or AI Mode, by page, country, device and date, which can date a new URL's first appearance. Sites with too few AI impressions may not see it, and it has no query dimension, so a prompt test still shows which question surfaced the page.
Copilot and AI answers in Bing
How long new content takes to appear in AI search citations on Perplexity, Bing AI and Google's AI features depends on discovery first, and Microsoft documents its side of discovery most fully. A July 31, 2025 post from Bing says freshness signals affect how quickly updates appear in both search results and AI-generated answers. Bing attempts to fetch a sitemap as soon as it is submitted or referenced in robots.txt, then typically rechecks it at least once a day. The post calls lastmod a key signal for recrawling and says it should reflect when the page content last changed. It also says no tool can guarantee when content will appear in AI results.
IndexNow is the push side. The IndexNow FAQ says one submission is shared with every participating engine, lists Amazon, Bing, Naver, Seznam.cz, Yandex and Yep as participants, and caps a single request at 10,000 URLs. Submission doesn't guarantee immediate indexing, since each engine still decides whether to crawl based on crawl quota, scheduling and quality signals. Google is not among the participants listed there.
Microsoft also offers a citation dashboard, something we could not find from OpenAI or Perplexity. Its Bing announcement of the AI Performance report, in public preview since February 10, 2026, says it covers Microsoft Copilot, AI-generated summaries in Bing and select partner integrations. It shows total citations, average cited pages, a sample of grounding queries, page-level citation activity and visibility trends over time. The same post recommends IndexNow so AI systems reference the most current version of a page. Page-level citation activity, like the Pages view of Google's Generative AI performance report, comes close to a "first cited on" date.
ChatGPT search and Perplexity
OpenAI's crawler documentation is where ChatGPT search crawling and indexing are described for publishers. OpenAI says OAI-SearchBot is the crawler that surfaces websites in ChatGPT's search features; sites that opt out are excluded from ChatGPT search answers, though they can still appear as navigational links. For search results, it can take "~24 hours from a site's robots.txt update" for OpenAI's systems to adjust. GPTBot covers model training and is set independently, so a site can allow OAI-SearchBot and disallow GPTBot. ChatGPT-User handles user-initiated actions, isn't used to crawl the web automatically, and isn't used to determine whether content appears in Search.
Perplexity's crawler documentation answers the access question and leaves indexing speed and citation timing open. Perplexity says PerplexityBot is designed to surface and link websites in Perplexity's search results and isn't used to crawl content for AI foundation models. Changes can take up to 24 hours to show in its systems. Perplexity-User works on demand: when someone asks a question, it may visit a page to help answer and link to that page in the response, and because a user requested the fetch, it generally ignores robots.txt.
We found no published timeline in either company's crawler documentation for how soon a new URL enters search results, and no URL submission route. With crawler access as the only documented lever, we link new pages from pages those crawlers already visit and confirm in the logs that the link got followed. If the main content needs JavaScript to render, our notes on whether AI crawlers render JavaScript cover how to test it.
Timing your own first crawl to first citation
The time for a new page to be cited by ChatGPT, Perplexity, Copilot or Google is something you measure page by page, because we found no operator that publishes it. The test we run has five parts.
- Log the publish time and every submission made: sitemap update, IndexNow ping, URL Inspection request.
- Filter server logs for the new URL by the documented crawler names (Googlebot, OAI-SearchBot, PerplexityBot) plus Bing's crawler, and note the first hit from each. Verify claimed bots against published IP lists where they exist; Perplexity publishes one for each of its two agents.
- Write five to ten prompts the page should answer, phrased the way a buyer asks, and run them in each engine once a day from a fresh session. Record the first day the URL shows up as a cited source.
- For Copilot and Bing, cross-check against page-level citation activity in Bing Webmaster Tools, and for Google, against the Pages view of the Generative AI performance report in Search Console.
- Split the wait into crawl lag (publish to first crawler hit) and selection lag (first hit to first citation).
The table below is a hypothetical log for one page. The days are invented to show how to read a result and are not measured data.
| Engine | First crawler hit | First citation in the daily test | What the gap points to |
|---|---|---|---|
| Copilot and AI answers in Bing | Day 0, after an IndexNow ping | Day 3 | Discovery and selection both worked |
| Google AI Overviews and AI Mode | Day 2 | Day 15 | Selection took longest; compare the page with the sources Google cites today |
| ChatGPT search | Day 9 | None by day 28 | Long crawl lag first, so check robots.txt and the links into the page |
| Perplexity | Day 1 | None by day 28 | Crawled quickly and still unchosen, so the page itself needs work |
The reading matters more than the numbers. A long crawl lag is a discovery problem that crawler access, sitemaps, IndexNow and internal links can address. A short crawl lag followed by silence is a page problem, and no ping touches it. In our experience that second case is where most of the effort goes: answering the sub-questions the engines search for, keeping your facts consistent everywhere they appear (our entity consistency audit walks through it), and shaping the page along the lines of our guide to getting cited by ChatGPT, Perplexity and AI Overviews.
What shortens the wait
- Allow Googlebot, OAI-SearchBot and PerplexityBot in robots.txt. Training opt-outs for GPTBot and Google-Extended can stay in place.
- Keep one sitemap with honest lastmod values, reference it in robots.txt, and submit it in Search Console and Bing Webmaster Tools.
- Send an IndexNow ping on publish and on every substantive update.
- Use URL Inspection once for the few pages that matter most, and skip repeat requests.
Once those are in place, the remaining wait is selection, and the way to watch it shrink is to track citations across a fixed prompt set month over month, which is what AI share of voice measures. For a quick read on how a page shows up in AI answers today, our AI visibility checker is a starting point, and our AI search optimization page describes how we work with teams on this.
Sources
- Google Search Central: AI features and your website
- Google Search Central: Ask Google to recrawl your URLs
- Google Search Central: List of Google's common crawlers
- Bing: Keeping Content Discoverable with Sitemaps in AI Powered Search, July 31, 2025
- Bing: Introducing AI Performance in Bing Webmaster Tools Public Preview, February 10, 2026
- IndexNow: Frequently asked questions
- OpenAI: Overview of OpenAI Crawlers
- Perplexity: Perplexity Crawlers
- Search Console Help: Generative AI performance report (Search)
