AI Visibility Checker – ChatGPT, Perplexity & Claude

Find out whether AI search answers mention your brand. Give it the questions your buyers ask ("best CRM for small agencies"), your brand, your domain and your competitors. For every prompt × AI engine you get: is your brand mentioned, at which position among the brands named, is your website cited as a source, which competitors appear instead, sentiment, all citations, and a visibility score per engine.

Built for GEO (Generative Engine Optimization), AEO (Answer Engine Optimization), LLM SEO and brand monitoring by SEO agencies, marketers and founders.

Supported AI engines

Engine	How it is checked	Key needed
ChatGPT	OpenAI Responses API with web search	Your OpenAI key
Perplexity	Perplexity Sonar API (with citations)	Your Perplexity key
Claude	Anthropic Messages API with web search tool	Your Anthropic key

✅ Official APIs only – no scraping of the ChatGPT, Perplexity or Claude websites. Important: this measures API answers (the provider's model with web search), which are similar to but not the same as what the consumer ChatGPT, Perplexity or Claude apps show a signed-in user. You use your own key, so your provider's API terms and usage policies apply to your use of the answers. You pay the provider directly. Keys are stored encrypted (secret input) and never logged.

Google AI Overviews and Gemini are intentionally not supported: Google's terms do not permit automated access to its search results, and the Gemini API terms restrict storing and analysing results grounded with Google Search.

Why this tool

• Bring your own key – you pay your AI provider directly; without any key the run returns one free info record explaining how to start (nothing is called or charged).
• Position, not just yes/no – rank of your first mention among all tracked brands, mention count and share of voice.
• Citations vs. retrieved sources – citations are only the sources the answer actually cites; pages the search tool retrieved but the answer did not cite are listed separately in retrievedSources (brandInRetrievedSources). Google redirect links are unwrapped to the real domain.
• Competitor gaps – prompts where only competitors appear.
• Visibility score per engine (0–100) plus an overall score, mention rate, citation rate and average position.
• Fair billing – you only pay for final, completed AI answers. Empty, incomplete or search-tool-failure answers, invalid keys, rate limits and errors are free. A wrong key stops calls to that provider immediately.

Input example

{
  "prompts": ["best SEO audit tools", "semrush alternatives"],
  "brandName": "Semrush",
  "brandDomains": ["semrush.com"],
  "competitors": ["Ahrefs", "Moz", "Screaming Frog"],
  "engines": ["perplexity", "claude"],
  "perplexityApiKey": "pplx-…",
  "countryCode": "us"
}

Output example (one record per prompt × engine)

{
  "type": "result",
  "prompt": "best SEO audit tools",
  "engine": "perplexity",
  "brandMentioned": true,
  "brandPosition": 2,
  "brandMentionCount": 1,
  "brandCited": false,
  "sentiment": "positive",
  "shareOfVoice": 0.33,
  "competitorsMentioned": [{ "name": "Screaming Frog", "mentions": 1, "position": 1 }, { "name": "Ahrefs", "mentions": 1, "position": 3 }],
  "brandsMentionedInOrder": ["Screaming Frog", "Semrush", "Ahrefs"],
  "citations": [{ "rank": 1, "url": "https://…", "title": "…", "domain": "…" }],
  "organicRank": 2,
  "answerText": "The best SEO audit tools vary…"
}

Leave every brand field empty and a demo (Semrush vs Ahrefs, Moz, Screaming Frog) runs. If you set your own brand, the demo domain and competitors are not used: add your own domains explicitly.

The last record is type: "summary" with overallVisibilityScore and, per engine, coverage (checksAttempted, answered, failed, skipped) next to visibilityScore, mentionRate, citationRate, averagePosition, averageShareOfVoice, topCompetitors, topCitedDomains and promptsWhereOnlyCompetitorsAppear. Failures appear as free type: "error" records. A run without any API key returns one free type: "info" record (plus the summary).

Visibility score: each answer scores 1.0 if your brand is named first, −0.15 per position after that (minimum 0.4), 0.3 if only your domain is cited, 0 if absent; the engine score is the average × 100.

Pricing

Pay per event: $0.008 per analysed AI answer (cheaper on higher Apify plans), plus a tiny start fee. This is the Actor fee only. Your total cost = Actor fee + your AI provider's API costs Free: errors, incomplete/empty answers, summary.

• With your own keys, the AI provider bills you directly at its own prices (search/tool calls are often billed on top of tokens).

Tips

• Answers vary between runs: schedule a weekly run and track the trend rather than a single answer.
• Use real buyer questions, not your brand name – "best X for Y", "X alternatives", "X vs Y".
• Add aliases (product names, old names) so every mention counts.

Limitations

• API answers differ from the consumer ChatGPT / Perplexity / Claude apps (personalisation, model versions, UI features).
• Claude's long searches may pause a turn; the Actor continues it up to 3 times, then records it as incomplete (free).
• Sentiment is a simple lexicon around your brand mention, not a full NLP model.

Related tools by batuweb

• SEO Audit Toolkit – technical SEO crawler.
• Google Trends Scraper – interest over time, regions, related queries.