Local AI Answer Visibility Checker: ChatGPT, Perplexity, Gemini avatar

Local AI Answer Visibility Checker: ChatGPT, Perplexity, Gemini

Under maintenance

Pricing

from $30.00 / 1,000 visibility checks

Go to Apify Store
Local AI Answer Visibility Checker: ChatGPT, Perplexity, Gemini

Local AI Answer Visibility Checker: ChatGPT, Perplexity, Gemini

Under maintenance

Does ChatGPT, Perplexity or Gemini recommend your local business, or your competitors? Bring your own API keys. Get share of voice, positions, cited sources, a citation-gap list and a client-ready report.

Pricing

from $30.00 / 1,000 visibility checks

Rating

0.0

(0)

Developer

Shanmukh kiran Sagar

Shanmukh kiran Sagar

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

4 days ago

Last modified

Categories

Share

Local AI Answer Visibility Checker: ChatGPT, Perplexity & Gemini (Bring Your Own API Keys)

Does AI recommend your local business, or your competitors? Ask ChatGPT, Perplexity and Gemini the questions your customers ask ("Who is the best emergency plumber in Leeds?") and see who gets named, in what position, which sources the engines cite, and where you could get listed to show up next time. Uses your own API keys through the official APIs. Nothing is scraped.

Bring your own API keys. This actor calls OpenAI, Perplexity and Google with your keys. The providers bill you directly for that usage; the actor's own price covers the analysis and reports. Pre-launch note: the provider integrations have been tested end-to-end against mocked API responses that follow each provider's published documentation, not yet against the live APIs. Start with Demo mode or a small run (e.g. 2 questions × 1 engine) and tell us if anything looks off.

Built for local service businesses and the agencies that market them: plumbers, dentists, solicitors, salons, roofers, estate agents, gyms and the like. Most AI visibility tools are built for SaaS brands. This one is built for "best

What you get

For every question × engine:

FieldMeaning
brandMentionedDid the answer name your business? (name, aliases or domain, whole-word match)
rank / rankMethodYour position: the list position if the answer is a list, otherwise the order in which tracked businesses were first named
competitorsMentionedCompetitors named, each with its position and whether its site was cited
citedUrls / citedDomainsEvery source URL the engine cited
brandDomainCitedWas your own website cited as a source?
brandSnippet / sentimentThe sentence that names you, with a simple positive/neutral/negative/mixed keyword label
answerTextThe full answer, for your records
errorFilled only when that check failed (bad key, rate limit…). Failed checks are not charged

Plus these key-value store records for the whole run:

  • REPORT_MD: a client-ready Markdown report with a headline, share-of-voice table, results by engine, "where competitors were recommended instead of you", the citation-gap list, quotes, and a plain-English method note. Add your agency name and it says "Prepared by
  • CITATION_GAPS_CSV: the directories, review sites and articles the AI engines cited in answers that named competitors but not you, ranked by how often they appeared. This is your to-do list for getting listed. Competitors' own websites are flagged separately.
  • SHARE_OF_VOICE_CSV: share of voice and mention rate for you and each competitor, overall and per engine.
  • CHECKS_CSV: one row per check, ready for Sheets or Excel.
  • SUMMARY: the same aggregates as JSON, for automations and AI agents.

Use cases

  • Agency pitch or monthly report: show a local client whether ChatGPT, Perplexity and Gemini name them for "best
  • Citation-gap to-do list: find the directories, review sites and articles the engines cite for competitors but not for you.
  • Before/after tracking: re-run monthly with the same questions to see whether listings and content changes moved the needle.
  • Competitor benchmarking: share of voice per engine for you and up to 25 competitors.

How to use it

  1. Enter your business name, website domain and up to 25 competitors (optionally Name | domain.com).
  2. Enter your trade ("emergency plumber") and town ("Leeds"). The actor writes up to 10 buyer-style local questions for you, or you can paste your own.
  3. Paste the API key for each engine you want: OpenAI, Perplexity and/or Gemini. Engines without a key are skipped. Gemini note: Google Search grounding is not available on the Gemini API free tier for Gemini 3.x models, so the default geminiModel (gemini-3.8-flash) needs a key from a billing-enabled Google AI Studio / Cloud project (Google currently includes a monthly allowance of grounded searches, then charges per search). A free-tier key returns HTTP 429 "exceeded your current quota". Older models such as gemini-2.5-flash are no longer offered to new Google users (HTTP 404), so for most people billing on the key's project is the only route.
  4. Run. Open the Storage → Key-value store → REPORT_MD record and send it to your client, or download the CSVs.

Want to see the output first? Switch on Demo mode. It runs a sample plumber in Leeds against canned responses, needs no keys, and is never charged.

Example input

{
"brandName": "Northgate Plumbing",
"brandDomain": "northgateplumbing.co.uk",
"brandAliases": ["Northgate"],
"competitors": ["Aire Valley Plumbers | airevalleyplumbers.co.uk", "Leeds Heating Co", "QuickFix Drains"],
"category": "emergency plumber",
"location": "Leeds",
"countryCode": "GB",
"maxPrompts": 10,
"providers": ["openai", "perplexity", "gemini"],
"openaiApiKey": "sk-…",
"perplexityApiKey": "pplx-…",
"geminiApiKey": "AIza…",
"agencyName": "Your Agency"
}

How it works

EngineOfficial API used
ChatGPTOpenAI Responses API with the hosted web_search tool. Your town and country are passed as the approximate user_location, and search is forced on by default so answers are grounded like a local search
PerplexityPerplexity Agent API (/v1/agent, fast preset by default), which Perplexity documents as the replacement for Sonar
GeminiGemini Interactions API with Grounding with Google Search (default model needs a key from a billing-enabled Google project)

Analysis runs locally: whole-word matching on your name, aliases and domain; list-position detection; citation domain matching. There are no extra LLM calls, so the analysis costs you nothing and is repeatable.

Pricing (pay per event)

EventPriceWhen it's charged
visibility-check$0.03 per check ($30 per 1,000)One question answered by one AI engine and analysed successfully
  • Example: 10 questions × 3 engines = 30 checks = $0.90 per run (plus your own provider API usage, billed by the providers).
  • Failed checks (bad key, timeouts, empty answers) and demo runs are not charged.
  • The AI providers bill you directly for your own API usage, at their published rates, with no markup from us. Example: Google charges per grounded search query on Gemini 3+ models after a monthly free allowance. See each provider's pricing page.
  • Set Maximum cost per run in Apify. The actor stops cleanly when it is reached and keeps everything collected so far.

Your keys and data

  • API keys are secret inputs: Apify encrypts them, and they are never written to the dataset, the report or the logs (error messages are redacted).
  • The actor sends only your questions to the providers you select. It collects no personal data.

Honest limitations

  • Live provider calls are not yet tested. Request and response handling for OpenAI, Perplexity and Gemini follows each provider's documentation as of October 2026 and passes end-to-end tests with mocked responses, but has not been run against the live APIs yet. API shapes and model names change; if a provider rejects a request, the check fails (and isn't charged) and the error is shown in the dataset.

  • Default model names (openaiModel, perplexityPreset, geminiModel) can be retired by the providers. You can change them in the input.

  • AI answers vary between runs, accounts, locations and over time. API answers can differ from what someone sees in the ChatGPT, Perplexity or Gemini apps. Treat each run as a snapshot and re-run (e.g. monthly) to track change. This tool reports what the engines said. It does not guarantee or "rank" anything.

  • Mention detection is whole-word name matching. A very generic business name (e.g. "Best Plumbing") can produce false matches, so add a domain and specific aliases.

  • Sentiment is a simple keyword heuristic on one sentence, not a judgement of the business.

FAQ

Why not scrape ChatGPT directly? Automated extraction from chat interfaces breaks their terms. The official APIs with web search return answers with structured citations.

Can I use it for non-local brands? Yes. Leave Town empty and the generated questions become general ("What are the best CRM software options right now?"), or paste your own questions.

Does it work in other countries? Yes. Set the town and the 2-letter country code (e.g. US, IE, AU). Questions are generated in English; paste your own for other languages.


Not affiliated with OpenAI, Perplexity or Google. ChatGPT, Perplexity and Gemini are trademarks of their owners.