LLM Mentions Tracker: your brand's share of voice in ChatGPT and Google AI Overviews

See every recorded ChatGPT and Google AI Overview answer that mentions your brand, from a database of 416.8 million real AI answers in 94 countries: the question people asked, the sentence where the AI names you, your position among the brands it names, the sites it cites (and whether yours is one) and the monthly search volume behind each question. There are no prompts to write and no guessing which questions matter: these are the questions people asked.

Add competitors and get your share of voice in AI answers, plus the questions where AI names a competitor and leaves you out, ranked by search volume: your content gaps. Add your website to count how many AI answers cite it, and a topic (CRM, running shoes, VPN) to keep every count inside your market. Each run also lists the pages AI cites most in answers about you and a month-by-month trend since August 2025.

Built for marketing and SEO teams, PR and brand managers, GEO/AEO agencies and AI agents. Every run writes a one-page AI visibility report (open it from the run's Output tab) to read or send.

What you get

Field	What it holds
AI answers (dataset)	type (mentions-you, or competitor-only: names a competitor but not you), brand, question, brandInQuestion, platform, model, aiSearchVolume, mentionContext (the sentence that names the brand), trackedBrandsInAnswer (in order), yourPosition, yourSiteCited, yourCitationRank, citedDomains, sources (rank, title, site, link), brandsNamed and fanOutQueries (ChatGPT), answer (markdown), alsoAskedAs (other questions given the same answer, with their volume), aiMonthlySearches, firstSeen, lastSeen
Overview	answers that mention you, the monthly searches they reach, split by platform; the sites cited most; the brands named alongside you and their categories (ChatGPT)
Site citations	answers that cite your website (subdomains included), by platform, and the sites cited next to it
Share of voice	answers and searches reached for you and up to 9 competitors, each brand's share and rank, and the sites cited most for each
Competitor gaps	how many answers name each competitor but not you, and the top ones as rows
Cited pages	the pages AI cites most in answers about you, with answers and searches reached
Trend	answers mentioning you and searches reached, month by month since August 2025 (the current month marked as partial)
REPORT.html	all of the above on one page

What people use it for

• AI share of voice: how often AI names you against your competitors, on ChatGPT and on Google
• Content gaps (GEO): the high-volume questions where AI recommends a competitor and not you: write the page that answers them
• Citation building: the sites and pages AI trusts for your market: where to be listed, reviewed or published
• Brand monitoring: how AI describes you, in its own words, and whether people even asked about you
• Reporting: a monthly AI visibility report per client or brand, from a schedule
• AI agents: AI visibility numbers inside any workflow

How to use it

1. Enter your brand (and your website to count citations).
2. Add up to 9 competitors and, to keep counts in your market, a topic.
3. Pick the country and platform, set how many answers you want, and click Start. Open the Report from the Output tab.

Input

Field	Example	Notes
Your brand	HubSpot	As people write it
Your website	hubspot.com	Optional: counts and marks the answers that cite it
Competitors	Salesforce, Pipedrive	Up to 9
Topic	CRM	Optional: every answer must also contain it
Country	US	94 countries; ChatGPT answers: United States
AI platform	both	With both, the answer lists take half from each platform
AI answers mentioning you	100	Up to 5,000, highest search volume first
Answers naming a competitor but not you	25	Per competitor; 0 = skip
Cited pages	20	0 = skip
Overview, share of voice, monthly trend	on	One database query each
Only questions that don't name the brand	off	Shows where AI brings the brand up by itself
Minimum searches a month	0	Leave out low-volume questions
Order of answers	highest search volume	Or most recently recorded

Output

Each result is one row in the run's dataset (download it as JSON, CSV, Excel, XML or HTML, or read it through the API). An example row (values shortened):

{
  "type": "mentions-you",
  "brand": "HubSpot",
  "question": "solution help desk",
  "brandInQuestion": false,
  "platform": "Google AI Overview",
  "aiSearchVolume": 301000,
  "mentionContext": "Best for CRM & Sales: Salesforce Service Cloud and HubSpot Service Hub excel at linking CRM data to customer service for personalized support.",
  "trackedBrandsInAnswer": [
    "Salesforce",
    "HubSpot"
  ],
  "yourPosition": 2,
  "yourSiteCited": false,
  "citedDomains": [
    "www.solarwinds.com",
    "www.sysaid.com",
    "www.helpdesk.com",
    "www.kustomer.com",
    "www.techradar.com"
  ],
  "sources": [
    {
      "rank": 1,
      "title": "IT Help Desk Software - SolarWinds",
      "domain": "www.solarwinds.com",
      "url": "https://www.solarwinds.com/solutions/it-help-desk",
      "sourceName": "SolarWinds"
    }
  ],
  "answer": "...",
  "firstSeen": "2025-09-11",
  "lastSeen": "2026-04-18",
  "country": "US",
  "language": "en"
}

The run's key-value store also holds SUMMARY (the overview, site citations, share of voice, competitor gaps, cited pages and trend as JSON, with notes and what was charged) and REPORT.html, the same as a web page (the Report link in the Output tab). In a run on 13 October 2026 (United States, both platforms, no topic) HubSpot was in 53,323 recorded AI answers (45,178 Google AI Overviews, 8,145 ChatGPT answers), against 103,176 for Salesforce: a 34% share of voice. Its monthly count rose from 7,112 in August 2025 to 16,997 in September 2026.

Pricing

• $0.008 per AI answer written ($8 per 1,000)
• $0.40 per database query: the overview, site citations, share of voice, cited pages and trend are one query each; each competitor's gap list is one query; answers come up to 1,000 a query (with both platforms: one query each)
• $0.004 per cited page in the cited-pages list
• Sections you switch off cost nothing, and neither does a query that fails

What typical jobs cost at the list price:

Job	Cost
Overview only	$0.40
Share of voice against 9 competitors only	$0.40
Overview and 100 answers mentioning you (both platforms)	$2.00
The form's example (site, 2 competitors, topic, 20 answers, 10 gaps each, 10 cited pages, trend)	$3.96
5 competitors, 100 answers, 25 gaps each, 20 cited pages, site, trend	$6.68
1,000 ChatGPT answers mentioning you	$8.40

On Apify's Scale and Business plans the per-event prices are lower (Store discounts). Set Maximum cost per run and the Actor stops cleanly when it is reached: you never pay more than that.

Tips

• Use a topic. Without one a brand counts wherever it is named: the 13 October run counted 83,018 answers that name Salesforce and not HubSpot, many about the Salesforce Tower or the CRM share price.
• Turn on 'Only questions that don't name the brand' to see where AI brings you up unprompted: that is the number GEO work moves.
• The competitor-only rows are a content brief: each has the question, the brands AI named instead and the sources it relied on.
• Schedule it monthly. The database adds answers continuously and refreshes in full about every 60 days; compare share of voice in SUMMARY run by run.

Use it through the API

Python

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("zaiq/llm-mentions-tracker").call(run_input={"brand": "HubSpot", "domain": "hubspot.com", "competitors": ["Salesforce", "Pipedrive"], "topic": "CRM", "maxMentions": 20})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(row)

JavaScript

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('zaiq/llm-mentions-tracker').call({"brand": "HubSpot", "domain": "hubspot.com", "competitors": ["Salesforce", "Pipedrive"], "topic": "CRM", "maxMentions": 20});
const { items } = await client.dataset(run.defaultDatasetId).listItems();

HTTP (one call, results back)

curl -X POST 'https://api.apify.com/v2/acts/zaiq~llm-mentions-tracker/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{"brand": "HubSpot", "domain": "hubspot.com", "competitors": ["Salesforce", "Pipedrive"], "topic": "CRM", "maxMentions": 20}'

Integrations and schedules

• Schedules: run it every hour, day or week from the Apify Console (Schedules) and keep a history of results.
• Make, Zapier, n8n, Google Sheets, Slack, Airtable: connect it through Apify's integrations, or send each finished run to a webhook.
• Datasets: results stay in the run's dataset; export them or read them by API whenever you need them.

Use it with AI agents (MCP)

Add Apify's MCP server (https://mcp.apify.com) to Claude, ChatGPT, Cursor, VS Code or any MCP client. The agent can find this Actor and run it for you: ask it for "how often ChatGPT and Google AI Overviews mention our brand compared with our three main competitors, and which questions they win without us". AI agents can also pay for runs directly through Apify's agentic payments.

Limits

• These are recorded answers to questions people asked, not live prompts. To check your own prompts live, use the AI Visibility Tracker (below).
• ChatGPT answers are recorded for the United States in English; Google AI Overview answers cover 94 countries.
• Brand names are matched as words ("Apple" also finds the fruit): use the full brand name and a topic, and check mentionContext.
• Brands named alongside you and fan-out queries come from ChatGPT answers only.
• Apify's free plan: how many AI answers mention you, and the top 10 (one query).

FAQ

How is this different from tools that prompt ChatGPT?

Prompt trackers ask the questions you write. This reads the answers to questions people actually asked, across millions of them, with the search volume behind each. Use both: our AI Visibility Tracker runs your own prompts live.

Where does the data come from?

A search-data provider's database of recorded ChatGPT and Google AI Overview answers: 416.8 million answers in 94 countries in October 2026, with questions, full answers, cited sources and search volume.

What does 'searches reached' mean?

The monthly search volume of the questions behind the answers, added up. For Google AI Overviews it is the question's Google search volume; for ChatGPT it is modelled from People Also Ask data.

Do I need a ChatGPT or OpenAI account?

No account and no API key.

How many brands can I compare?

You and up to 9 competitors in share of voice. The answers list and cited pages are for your brand; the gap rows are per competitor.

Can I track another country?

Yes: choose any of 94 countries (Google AI Overview answers in the country's languages). ChatGPT answers are recorded for the United States.

Related Actors from Zaiq

• ai-answer-tracker: your own prompts, live, in ChatGPT, Perplexity, Gemini, Claude and Grok
• ai-search-volume: how often keywords are used in AI search, and the questions people ask
• google-ai-mode-tracker: Google AI Mode's answers for your questions
• keyword-research: Google search volume, CPC and difficulty

Support

Questions, a site that changed, or a field you need? Open an issue on this Actor's Issues tab: we answer there, usually within a day.

---

Also found as: llm mentions, ai brand mentions, chatgpt brand mentions, ai share of voice, ai visibility, generative engine optimization, geo tool, aeo tool, ai overview tracking, brand monitoring in ai, ai citations, profound alternative, peec ai alternative, otterly alternative.