AI Citation Tracker: Sites ChatGPT & Perplexity Cite
Pricing
$50.00 / 1,000 ai answer analyzeds
AI Citation Tracker: Sites ChatGPT & Perplexity Cite
See which websites and pages ChatGPT and Perplexity cite when buyers ask about your market. Get every cited URL, domain citation share, your citation rate vs competitors and the prompts where you're missing. GEO / AEO source tracking, $0.05 per answer.
Pricing
$50.00 / 1,000 ai answer analyzeds
Rating
0.0
(0)
Developer
Kendall Sorenson
Maintained by CommunityActor stats
1
Bookmarked
2
Total users
1
Monthly active users
17 hours ago
Last modified
Share
AI Citation Tracker: which websites ChatGPT and Perplexity cite for your market
When buyers ask ChatGPT or Perplexity "what's the best project management software?", it searches the web and cites a handful of pages. Those cited pages decide which brands get recommended. This Actor shows you exactly which websites and URLs ChatGPT and Perplexity cite for the questions your buyers ask, how often your own site is cited compared with competitors, and the prompts where competitors are cited and you aren't.
Use it for GEO (generative engine optimization), AEO, LLM SEO, content planning and digital PR: find the review sites, listicles and competitor pages AI keeps citing, then get listed there or publish something better.
- ✅ No API keys needed. Just add your prompts and domains.
- ✅ Every cited URL with its title, domain and position in the answer
- ✅ Citation share by domain, your citation rate, and a competitor comparison
- ✅ An opportunity list of prompts where competitors are cited and you aren't
- ✅ Pay only for answers you get: $0.05 per AI answer. Failed requests are never charged.
👉 Want to know whether ChatGPT mentions your brand, not just cites your site? Use the companion AI Search Visibility Tracker, or try the free AI visibility checker.
How it works
- You enter the questions your buyers ask. Or enter a category such as
CRM software for small businesses, and the Actor writes realistic buyer prompts for you. - Each prompt goes to ChatGPT (OpenAI's current model with live web search) and Perplexity (its official API with live web search), once per engine and sample. Pick just one engine in AI engines if you prefer.
- The Actor pulls out every cited URL in order, cleans tracking parameters, normalizes domains, and checks your domains and your competitors' domains, including subdomains.
- You get one dataset row per answer, plus a
REPORTrecord with the totals.
Example output (real run, Nov 2, 2026)
Prompts: 3 project management questions, 2 samples each (6 answers). Your domain: notion.so. Competitors: asana.com, clickup.com, monday.com.
| Domain | Cited in answers | Share of all citations | Avg. first position |
|---|---|---|---|
| asana.com | 83% (5 of 6) | 50% | 1.2 |
| capterra.com | 17% | 25% | n/a |
| clickup.com | 33% | 17% | 3 |
| g2.com | 17% | 8% | n/a |
| notion.so (you) | 0% | 0% | n/a |
| monday.com | 0% | 0% | n/a |
All three prompts went into the opportunity list. For example, for "What is the best project management software for a small team?" ChatGPT cited asana.com/resources/best-project-management-software, asana.com/pricing and clickup.com/learn/topic/project-management/tools/, plus a G2 category page. Notion's site wasn't cited once.
One dataset row (shortened)
{"prompt": "What is the best project management software for a small team?","engine": "chatgpt","model": "gpt-5.4-mini-2026-03-17","checkedAt": "2026-11-02T16:12:44.725Z","answerExcerpt": "For most small teams, ...","citationCount": 3,"citations": [{ "position": 1, "url": "https://asana.com/resources/best-project-management-software", "title": "Best project management software: 11 tools compared [2026] • Asana", "domain": "asana.com" },{ "position": 2, "url": "https://asana.com/pricing", "title": "Asana Pricing | ...", "domain": "asana.com" }],"citedDomains": ["asana.com", "clickup.com"],"yourDomainCited": false,"yourFirstPosition": null,"competitorsCited": ["asana.com", "clickup.com"],"trackedDomains": { "asana.com": { "cited": true, "citations": 2, "firstPosition": 1, "urls": ["..."] } },"consultedSources": [ { "url": "...", "domain": "..." } ],"searchQueries": ["best project management software small team 2026"]}
REPORT (key-value store)
comparison: each of your domains and competitor domains, with the share of answers citing it, citation count, share of citations and average first positionyourCitationRateandbyEngine: the same figures for each engineopportunities: prompts where a competitor was cited and you weren't, with the competitor URLs and other cited sitestopDomainsandtopUrls: the sites and pages AI cites most for your promptsinputWarnings: anything that was skipped or corrected in your input
Input
| Field | What it does |
|---|---|
prompts | Buyer questions, one per line (up to 100) |
category | Used only if prompts is empty. Generates autoPromptCount prompts |
yourDomains | Your sites, e.g. notion.so. Full URLs are fine |
competitorDomains | Up to 25 competitor domains |
samplesPerPrompt | Asks each prompt 1–5 times. AI answers vary, so 2–3 gives steadier numbers |
country | 2-letter code (e.g. US) to localize web search |
language | Answer language, e.g. German |
maxAnswers | Hard cap on billed answers |
Bad input never costs you money. Empty, too-short or duplicate prompts and invalid domains are skipped with a warning in INPUT_WARNINGS. If nothing valid is left, the run ends without charging.
Pricing and cost examples
$0.05 per AI answer, which is one prompt × one engine × one sample, including all citation extraction. Both engines are on by default, so each prompt is 2 answers unless you pick one engine. There's no subscription.
| Setup | Answers | Cost |
|---|---|---|
| 10 prompts × 1 engine × 1 sample, one-off audit | 10 | $0.50 |
| 10 prompts × 2 engines × 1 sample | 20 | $1.00 |
| 20 prompts × 2 engines × 1 sample, weekly | 40/week | $2/week (about $8.70/month) |
| 50 prompts × 2 engines × 2 samples, monthly deep dive | 200 | $10.00 |
AI-visibility subscription tools usually cost $29–$99+ a month. Set a run spending limit and the Actor stops before going over it.
FAQ
Why do citations matter more than mentions? AI search answers are built from the pages it retrieves. If you know which pages it cites, you know where to get listed, which comparison pages to pitch, and which content of yours to improve.
Which engines are supported? ChatGPT with web search and Perplexity with web search, both through the official APIs. Each answer costs the same on either engine. Google Gemini isn't offered, because Google's Gemini API terms don't allow collecting or analyzing the links from its Search grounding.
Is this exactly what I see in chatgpt.com? It uses OpenAI's API with the same hosted web search tool, which is the closest programmatic match. Answers vary from run to run (as they do in the app), which is why samples help.
Some cited pages return 403 when I script them. Sites like G2 and Capterra block bots. The pages are real and open fine in a browser.
Can I schedule it? Yes. Use Apify Schedules to run weekly and compare the reports over time.
Do I need an OpenAI key? No. The Actor's own keys are used, and the price per answer includes everything.
Related tools
- AI Search Visibility Tracker: brand mentions, rank, share of voice and sentiment in ChatGPT, Gemini and Perplexity
- Free AI visibility checker: a 30-second check of whether ChatGPT recommends your brand
- Google Ads Transparency & Ad Library Scraper: see your competitors' ads
- Microsoft Ads Library Scraper: your competitors' Bing ads, with copy, landing pages and EU impressions
Built by Kendall Sorenson.