ChatGPT Brand Visibility Tracker (AI SEO / GEO)

Find out whether ChatGPT recommends your brand. The Actor asks ChatGPT the questions your buyers ask (for example "What are the best CRM tools for a small business?"). For each answer it reports whether your brand was mentioned, at what position, with what sentiment, whether your site was cited, and how you compare with your competitors.

It runs on the official OpenAI API (Responses API with the built-in web_search tool, the same kind of search-grounded answer ChatGPT gives). There is no browser scraping and no login, and you do not need your own API key.

Not affiliated with, endorsed by or sponsored by OpenAI. "ChatGPT" is a trademark of OpenAI and is used here only to describe the data source.

What you get

One dataset row per check (one check is one prompt × one sample):

Field	Meaning
brandMentioned, brandPosition	Whether your brand appears, and its rank among all brands the answer names (1 = first)
brandSentiment	positive / neutral / negative / mixed
brandCited, brandCitationRank	Whether a URL on your domain is among the answer's citations, and its rank
brandsNamed	Every brand in the answer, in order, with sentiment, including competitors you did not list
competitors	The same metrics for each competitor you track
citations, citedDomains, sourceUrls, searchQueries	Clickable cited URLs with titles, the sources consulted, and the search queries ChatGPT ran
answer, brandExcerpt	The full answer text and the passage where your brand appears
estimatedOpenAiCostUsd, usage	Tokens and the estimated API cost of the check (for transparency)
diff	Your previous mention rate and position for this prompt (when a history store is used)

A run summary (key-value store record OUTPUT) contains:

• mention rate, average position, top-1 and top-3 rates
• visibility score (0–100) = the average over all checks of 1/position, scored 0 when the brand is not mentioned
• share of voice = your mentions ÷ mentions of all tracked brands
• citation rate, top cited domains, and the prompts where you are missing
• a change report against your last run

The checks and the share-of-voice table are also saved as CSV (CHECKS.csv, SHARE_OF_VOICE.csv).

Input

{
  "brand": "HubSpot | hubspot.com",
  "competitors": ["Salesforce | salesforce.com", "Pipedrive | pipedrive.com", "Zoho CRM | Zoho | zoho.com"],
  "keywords": ["CRM software for small businesses"],
  "prompts": ["What is the easiest CRM for a 10-person sales team?"],
  "promptVariants": 3,
  "country": "US",
  "language": "en",
  "webSearch": true,
  "samplesPerPrompt": 1,
  "baselineStoreName": "my-brand-ai-visibility"
}

• Brand format: Name | alias | domain.com. Aliases improve matching. The domain is used to detect citations of your site.
• Keywords are turned into realistic buyer prompts (English, Portuguese and Spanish templates). Your brand is never put into the prompt, so the answer is not biased toward it.
• samplesPerPrompt: AI answers vary from one request to the next. Sampling each prompt 2–3 times gives a steadier mention rate.
• webSearch: on gives a search-grounded answer with citations. Off gives an answer from the model's own knowledge, which is a cheaper check.
• baselineStoreName: a named key-value store in your account. Each run is compared with the previous run saved there. Schedule the Actor weekly to track trends.
• Demo mode (mockMode): produces realistic synthetic answers so you can preview the output for free. Demo answers are not real ChatGPT data.

Pricing

Pricing is pay per event: you pay per successful check, and checks that fail (OpenAI errors, timeouts, empty answers) are not charged. A check made with web search costs more than one made without it (see the Pricing tab). The run stops before your max total charge is reached, so a check that cannot be billed is never sent. On the Apify free plan, each run is limited to a few demo checks.

How this compares (Apify Store, checked 2026-10-31)

	This Actor	apify/chatgpt-search-scraper	santhej/ai-rank-tracker-pro
How answers are obtained (per Store description)	Official OpenAI API	"Scrape ChatGPT Search results at scale without an API"	"No API keys"
Price shown on Store (2026-10-31)	see Pricing tab	$0.20 per result on the free tier, $0.005 on Bronze	$0.05 per platform check + $0.25 per report
Run success rate shown on Store (30 days, 2026-10-31)	new	88.2%	98.4%
Engines	ChatGPT	ChatGPT	5 AI platforms

Figures for other Actors are quoted from their public Apify Store pages/API on 2026-10-31 (success rate = succeeded ÷ total runs in the last 30 days) and may have changed since.

Limits and notes

• AI answers are non-deterministic, so read the results as samples. Use samplesPerPrompt and scheduled runs to see trends.
• The answers come from the API with web search. They can differ from what a logged-in ChatGPT user sees, which depends on memory, personalization and the app version.
• Position counts every brand the AI names. With analysisMode: "rules", only your tracked brands are counted.
• Citations are returned exactly as given by the API. If you display results publicly, keep the citations visible and clickable.