AI Rank Tracker GEO/AEO: ChatGPT, Perplexity Brand Mentions

Track whether ChatGPT, Perplexity, Gemini and Claude mention and rank your brand when people ask buyer questions such as "best CRM for small business" or "best running shoes".

For SEO and GEO agencies, marketers and brands who need to know where AI assistants rank them, and who they rank first instead.

About $0.05 per check (one of your questions asked on one AI), AI usage included at Apify's paid-plan rates. Checking 10 buyer questions on all four AIs (40 checks) costs about $2.10. Your first run with the example input (1 question on 4 AIs) costs about $0.21 and takes under a minute.

Give it the questions your buyers ask AI ("best CRM for small business"), your brand and your competitors. It asks each question on ChatGPT, Gemini, Claude and Perplexity with their own live web search and returns one row per question and AI, starting with a plain answer such as "HubSpot is #1 of 6 options in Gemini's answer. Tone: positive. Your site is cited." Then come your rank in the answer's list (1st, 2nd, 3rd...), whether you are mentioned, how you are described (positive, neutral or negative), every cited source, whether your website is cited, and each competitor's rank. The last row is a run summary: "HubSpot is mentioned in 94% of 16 AI answers, average rank 2.25, ranked #1 in 50%, share of voice 26%...", with the numbers per AI.

No login, no API keys, no subscription. You pay per check.

What you get per check

One check = one question answered by one AI.

Field	What it holds
verdict	The result in plain words: your rank, the #1 option, tone, competitors ahead, whether your site is cited
prompt, engine, model, country	The question, the AI (chatgpt, gemini, claude, perplexity), the exact model and the searcher's country
brandRank	Your position in the answer's list of options: 1 = recommended first. null if you are not in the list
brandMentioned, brandMentions	Whether the answer names your brand, and how many times
brandSentiment	How the answer describes you: positive, neutral or negative
brandContext	The sentence where the answer first names you
domainCited, domainCitedUrls, domainCitationPosition	Whether the answer cites your website, which pages, and the first one's position among the sources
topPick, listLength, rankedList	The option ranked #1, how many options the answer lists, and all of them in order (including brands you did not list)
competitors	Per competitor: rank, mentioned, mentions, sentiment, cited, citedUrl
competitorsAhead	Competitors ranked above you in this answer
sources, citedDomains, sourceCount	Every source the AI used (position, URL, title, domain, cited in the answer or not) and the cited sites in order
answer	The full answer text
webSearches, truncated, aiUsageUsd, checkedAt	Searches the AI ran, whether the answer hit the length limit, the AI usage for this check, and the time

The run summary (last row, free)

rowType: "summary", also saved as the SUMMARY record in the run's key-value store, and shown as the run's status message:

• verdict: the run in two or three plain sentences.
• overall and byEngine: mention rate, average rank, top-1 and top-3 rates, citation rate of your domain, tone counts and share of voice (your share of all mentions of your brand and your competitors, one count per answer).
• competitors: the same numbers for each competitor.
• mostRecommended: the 25 options AI recommends most often across all answers, with average rank. This shows who AI ranks first when it is not you.
• topCitedDomains: the sites the AIs cite most. These are the pages to get your brand onto.
• brandMissingFrom: the questions and AIs where you were not mentioned, with who was ranked #1 instead.

Pricing

About $0.05 per check on a paid Apify plan, made of two parts:

• This Actor: $0.035 per check. Apify's tier discounts apply: Bronze $0.03325, Silver $0.0315, Gold and above $0.028. Failed checks and the run summary are free.
• The AI's own usage: about $0.017 per check on average, billed to your Apify account by Apify's OpenRouter gateway at the AI providers' rates. It depends on the AI:

AI	AI usage per check (typical)	Full cost per check (about)
Perplexity	$0.006	$0.041
Claude	$0.012	$0.047
ChatGPT	$0.022	$0.057
Gemini	$0.02 to $0.035 (one or two Google searches)	$0.055 to $0.07

The AI figures were measured over 47 test checks and include the small ranking step (about $0.0003). Each row's aiUsageUsd shows that check's AI usage.

What typical jobs cost (paid plan, all four AIs unless stated):

Job	Checks	This Actor	AI usage (about)	Total (about)
First run: the example input, 1 question	4	$0.14	$0.07	$0.21
10 questions	40	$1.40	$0.70	$2.10
50 questions	200	$7.00	$3.40	$10.40
100 questions	400	$14.00	$6.80	$20.80
25 questions on ChatGPT and Gemini, weekly	50 a week	$1.75	$1.30	$3.05 a week

No surprise bills: set Apify's maximum cost per run before you start and the run stops cleanly at that amount.

Apify free plan: each run checks your first 8 question and AI pairs (two questions on all four AIs), enough to see your ranks. A paid Apify plan removes the limit. The OpenRouter gateway also lists a higher AI rate for free-plan accounts (about 10 times the model price), so a paid plan is much cheaper for this Actor.

How to use it

1. Add your prompts: the questions your buyers type into AI assistants, one per line.
2. Add your brand and, if you want the citation check, your website domain.
3. Add competitors as Name | domain.com, a name or a domain.
4. Pick the engines (all four by default) and the country.
5. Start. Download the rows as JSON, CSV or Excel, or read them through the API.

Input example

{
  "prompts": [
    "What are the best CRM tools for a small business?",
    "What are the best HubSpot alternatives?",
    "best free CRM software"
  ],
  "brand": "HubSpot",
  "domain": "hubspot.com",
  "competitors": ["Salesforce | salesforce.com", "Pipedrive | pipedrive.com", "Zoho CRM | zoho.com"],
  "engines": ["chatgpt", "gemini", "claude", "perplexity"],
  "country": "US"
}

Optional: brandAliases (other names that count as your brand, for example "HubSpot CRM") and maxConcurrency (checks at a time, default 8).

Output example (one check, shortened)

{
  "verdict": "HubSpot is #1 of 4 options in ChatGPT's answer. Tone: positive. Your site is cited.",
  "rowType": "check",
  "prompt": "What are the best CRM tools for a small business?",
  "engine": "chatgpt",
  "engineName": "ChatGPT",
  "model": "openai/gpt-6-luna",
  "country": "US",
  "brand": "HubSpot",
  "brandRank": 1,
  "brandMentioned": true,
  "brandMentions": 3,
  "brandSentiment": "positive",
  "brandContext": "HubSpot Getting started; sales and marketing together Free plan includes contact management and deal pipelines...",
  "domain": "hubspot.com",
  "domainCited": true,
  "domainCitedUrls": ["https://www.hubspot.com/products/crm"],
  "domainCitationPosition": 1,
  "topPick": "HubSpot",
  "listLength": 4,
  "rankedList": ["HubSpot", "Zoho CRM", "Pipedrive", "Salesforce"],
  "competitors": [
    {"name": "Zoho CRM", "domain": "zoho.com", "rank": 2, "mentioned": true, "mentions": 3, "sentiment": "positive", "cited": true, "citedUrl": "https://www.zoho.com/crm/zohocrm-pricing-calculator.html"},
    {"name": "Pipedrive", "domain": "pipedrive.com", "rank": 3, "mentioned": true, "mentions": 2, "sentiment": "positive", "cited": true, "citedUrl": "https://www.pipedrive.com/en/pricing"},
    {"name": "Salesforce", "domain": "salesforce.com", "rank": 4, "mentioned": true, "mentions": 1, "sentiment": "neutral", "cited": false, "citedUrl": null}
  ],
  "competitorsAhead": [],
  "citedDomains": ["hubspot.com", "zoho.com", "pipedrive.com"],
  "sources": [
    {"position": 1, "title": "Streamline Your Entire Business With a Free CRM | HubSpot", "url": "https://www.hubspot.com/products/crm", "domain": "hubspot.com", "citedInAnswer": true}
  ],
  "sourceCount": 3,
  "answer": "There isn't one best CRM for every small business...",
  "webSearches": 1,
  "status": "ok",
  "checkedAt": "2026-10-13T07:41:21Z"
}

Track your AI rank weekly

AI answers change from week to week, and from run to run. To see the trend:

1. Save your input as a task (the Tasks tab, or "Save as a new task" in the input form).
2. Add an Apify Schedule to that task, for example every Monday at 08:00.
3. Send each run's rows to Google Sheets, Slack, a webhook, Make, Zapier or n8n through Apify's integrations, or read them through the API.

Compare byEngine in each week's summary row to see your share of voice and average rank move.

Use with AI agents (MCP)

This Actor works as a tool in Apify's MCP server, so Claude, ChatGPT, Cursor or any MCP client can run it. Add the Actor to your Apify MCP server configuration and ask, for example:

"Use moggedhq/ai-rank-tracker to check where HubSpot ranks against Salesforce and Pipedrive in ChatGPT and Gemini answers to 'best CRM for small business', then tell me which competitor is ranked ahead most often."

The input is plain (prompts, brand, domain, competitors, engines, country) and each row is self-contained, so an agent can read the rank, sentiment and citations without extra parsing. The summary row gives the agent one place to read share of voice and average rank.

How it works

• Each prompt goes to the engine's model through its official API with the engine's own web search switched on, reached through Apify's OpenRouter gateway: ChatGPT uses OpenAI's web search, Gemini uses Google Search grounding, Claude uses Anthropic's web search and Perplexity uses its Sonar search.
• Models: ChatGPT = OpenAI GPT Luna, Gemini = Gemini Flash, Claude = Claude Haiku, Perplexity = Sonar. The newest release in each family is picked automatically; each row names the exact model.
• Country: ChatGPT, Gemini and Claude are told the user's approximate location and search from that country. Perplexity gets "(I'm searching from ...)" added to the prompt for any country other than the United States, because it builds its search from the prompt.
• Gemini is asked to ground its answer with Google Search and to answer for the user's country, because without that it often answers from memory, with no sources and for the United States.
• Ranking: a small AI model (no web search) reads each answer and lists the options it presents, in order. Rank is the position in the answer's main list or table (item 3 of a numbered list is rank 3); options presented elsewhere follow in the order they are first named. Options grouped in one item ("Nedbank, Standard Bank and FNB") share that item's rank. Names the answer advises against, and the product a prompt asks alternatives to, are mentioned but not ranked. Every rank and mention is checked against the answer text, so a name the answer never uses is never reported.
• Mentions match your brand name, your aliases and your domain as whole words, case-insensitively. Citations count your domain and its subdomains.

Honest limits

• Answers come from the models' APIs with web search, not from the chat apps. They mirror what ChatGPT, Gemini, Claude and Perplexity show (same model families, same search providers), but they are not a copy of the app page: no logged-in history or memory, no shopping cards, maps or ads, and the apps may run a different model from the one used here.
• Answers vary from run to run. The same prompt can rank you 2nd today and 4th tomorrow. Track several prompts over several runs and read the averages, not one answer.
• Rank depends on the answer's format. Lists and tables rank cleanly. In prose answers, rank is the order in which options are first named. An answer that names you only as the subject ("best HubSpot alternatives") mentions you without ranking you, so brandRank is null there.
• Sentiment is coarse. It is one label for how the whole answer describes you.
• Some answers have no sources. Gemini and others sometimes answer without searching; those rows have status: "no-sources" and are still charged, because the answer and the ranks are delivered.
• Common-word brand names (for example "Close" or "Monday") can be hard to match. Add aliases, and the domain, so the check can tell your brand from the word.
• If a rank cannot be read from an answer, the row falls back to the order of first mention among your brand and competitors (rankSource: "first-mention").

FAQ

Is this affiliated with OpenAI, Google, Anthropic or Perplexity? No. This Actor is independent and is not affiliated with, sponsored by or endorsed by OpenAI, Google, Anthropic or Perplexity. Their product names are used only to say which AI engine answered.

Do I need API keys or accounts? No. The AI calls go through Apify's OpenRouter gateway with your Apify account; you need nothing else.

Why is AI usage billed separately? Apify's gateway bills each model's actual usage to the account that runs the Actor, at OpenRouter's rates. You see the real cost of each engine (aiUsageUsd per row) instead of a padded flat price, and cheaper engines such as Perplexity cost you less.

How many questions can I check? Up to 1,000 questions per run, on up to four AIs (on Apify's free plan, the first 8 checks per run). Checks run 8 at a time by default; 50 prompts on four engines usually finish in about 5 to 10 minutes.

Can I track several brands? Run once per brand, or put the other brands under competitors: every competitor gets its own rank, sentiment and citation per answer, and its own line in the summary.

What does a failed check cost? Nothing. If an engine fails after retries, the row says why (status: "error") and is not charged.

Which countries are supported? 50 countries, including the United States, United Kingdom, Canada, Australia, Germany, France, India, Brazil and South Africa.