AI Search Visibility Tracker: ChatGPT, Perplexity, Gemini

Find out whether AI assistants recommend your brand. Give this actor a list of prompts your buyers might ask, your brand name and your domain. It sends each prompt to ChatGPT (OpenAI with web search), Perplexity and Gemini (with Google Search grounding), then reports for every answer:

• whether your brand is mentioned, how often, and where it ranks against the competitors you track
• its position in the answer's list of recommendations
• whether your website is cited as a source, and at which citation position
• which competitors were named or cited
• every cited source with its domain
• a visibility score from 0 to 100 and your share of voice

It finishes with a summary per engine and overall: mention rate, citation rate, average score, average rank, top competitors and the domains the engines cite most. That is the data you need for generative engine optimization (GEO) and AI SEO reporting.

Bring your own API keys

You supply your own OpenAI, Perplexity and Gemini API keys. They are stored encrypted by Apify as secret inputs, sent only to the engine they belong to, and never written to the log or the output. Each provider bills you directly at its own rates, so you always pay list price for the model calls, with no markup. The actor charges only a small fee for the orchestration and the analysis.

Use one, two or all three engines. An engine without a key is skipped.

Try it free: run the actor with no keys at all and it analyzes bundled sample answers so you can see exactly what the output looks like. Demo runs are never charged.

Input example

{
    "prompts": [
        "What are the best project management tools for small teams?",
        "Which Kanban app is easiest for a marketing team?"
    ],
    "brandName": "Trello",
    "brandDomain": "trello.com",
    "brandAliases": ["Trello by Atlassian"],
    "competitors": ["Asana (asana.com)", "monday.com (monday.com)", "ClickUp (clickup.com)", "Notion (notion.so)"],
    "engines": ["openai", "perplexity", "gemini"],
    "openaiApiKey": "your OpenAI key",
    "perplexityApiKey": "your Perplexity key",
    "geminiApiKey": "your Gemini key",
    "country": "US"
}

Field	What it does
prompts	The questions to ask, up to 500 per run
brandName, brandAliases	Names that count as a mention of your brand (whole word, case insensitive)
brandDomain	Your site. A citation of this domain or any subdomain counts as cited
competitors	Names to track, each optionally followed by its domain in brackets for citation tracking
engines	openai, perplexity, gemini
openaiModel, perplexityModel, geminiModel	Defaults: gpt-4.1-mini, sonar, gemini-2.5-flash
country	Optional two letter country code for localized search where the engine supports it
includeAnswerText	Keep the full answer in the output (default on)

Output example

One row per prompt per engine:

{
    "recordType": "result",
    "prompt": "What are the best project management tools for small teams?",
    "engine": "openai",
    "model": "gpt-4.1-mini-2025-04-14",
    "brandName": "Trello",
    "brandDomain": "trello.com",
    "brandMentioned": true,
    "brandMentionCount": 2,
    "brandRank": 2,
    "brandListPosition": 2,
    "brandCited": true,
    "brandCitationPosition": 2,
    "shareOfVoice": 0.333,
    "visibilityScore": 93,
    "competitorsMentioned": [
        { "name": "Asana", "domain": "asana.com", "mentionCount": 2, "rank": 1, "listPosition": 1, "cited": true, "citationPosition": 1, "visibilityScore": 100 }
    ],
    "citations": [
        { "position": 1, "url": "https://asana.com/pricing", "title": "Asana pricing", "domain": "asana.com", "isBrand": false, "competitor": "Asana" },
        { "position": 2, "url": "https://trello.com/pricing", "title": "Trello pricing", "domain": "trello.com", "isBrand": true, "competitor": null }
    ],
    "answerText": "Here are some of the best project management tools for small teams: ...",
    "error": null,
    "demo": false
}

Plus summary rows (recordType is summary), one per engine and one with engine set to all:

{
    "recordType": "summary",
    "engine": "all",
    "brandName": "Trello",
    "answersAnalyzed": 3,
    "mentionRate": 1,
    "citationRate": 0.667,
    "averageVisibilityScore": 79.3,
    "averageRankWhenMentioned": 2.3,
    "averageShareOfVoice": 0.333,
    "topCompetitors": [{ "name": "Asana", "answers": 3 }],
    "topCitedDomains": [{ "domain": "asana.com", "answers": 2 }]
}

The same summary is saved to the key value store as SUMMARY.

How the visibility score works

Part	Points
Brand mentioned	40
Mention prominence: 20 if named first among tracked brands, 15 if second, 10 if third, 5 if fourth	up to 20
Brand site cited as a source	30
Citation prominence: 10 if the first source, 2 fewer for each later position	up to 10

brandRank is the order in which your brand first appears among all the names you track. brandListPosition is the numbered or bulleted list item where it first appears, if the answer is a list. shareOfVoice is your mentions divided by all tracked mentions in the answer.

Pricing

Pay per event:

Event	Price
One prompt answered and analyzed on one engine	$0.02

Example: 20 prompts on 3 engines is 60 analyses, which costs $1.20 here, plus whatever OpenAI, Perplexity and Google bill you for the calls on your own keys (usually a few cents per prompt for small models). Failed calls, rejected keys, summary rows and demo runs are free. You can cap your spend with the maximum charge setting on each run.

Limits

• AI answers vary from run to run. Track the same prompts on a schedule and read the trend, not one run.
• API answers can differ from what a signed in user sees in the ChatGPT, Perplexity or Gemini apps, which add personalization and memory. The API with web search is the closest repeatable, rule abiding view.
• Gemini returns cited sources as Google redirect links with the source domain as the title; the actor reports the domain, so page level URLs are not available for Gemini.
• Mentions are matched as whole words. Very short or generic brand names (for example "Go" or "Apple") can match unrelated uses; add aliases or a distinctive name.
• Google AI Overviews are not covered, because there is no official API for them.
• Not affiliated with OpenAI, Perplexity or Google.

FAQ

Is my API key safe? Keys are secret inputs, encrypted at rest by Apify, sent only over HTTPS to the matching provider, and never printed to the log or saved to the dataset.

Why bring my own keys? You pay the providers' own prices with no markup, you control your models and limits, and your usage stays in your own accounts.

Which models can I use? Any OpenAI model that supports the web search tool in the Responses API, any Perplexity Sonar model, and any Gemini model that supports Google Search grounding.

Can I track many brands? Run the actor once per brand, or list rival brands as competitors to see them side by side in one run.

Can I schedule it? Yes. Use Apify schedules to run weekly and connect the dataset to Google Sheets, Looker Studio or a webhook.

Found a problem? Open an issue on the Issues tab. Issues are answered quickly.