AI Answer Scraper: ChatGPT, Perplexity, Gemini, Google AI Mode and AI Overviews answers with citations

AI Answer Scraper asks ChatGPT, Perplexity, Gemini, Google AI Mode, Google AI Overviews and Claude your prompts and returns each answer, its cited sources and the brands it recommends, in order, as structured data, plus the web searches the engine ran. All engines are in one Actor and one table, so you can compare what each AI recommends without stitching four scrapers together. $0.015 per answer (down to $0.01 on paid Apify plans).

Already using Apify's ChatGPT, Perplexity, Gemini or Google AI Mode scraper? This Actor accepts the same input (queries, one per line, and countryCode) and adds the same output fields (query, text, sources, citationUrls), so you can switch by changing only the Actor ID. On the Apify Free plan those scrapers charge $0.20 per answer (Apify Store pricing, checked Oct 19, 2026); this one charges $0.015 and asks several engines in one run. See Switching from Apify's AI scrapers.

Use it for GEO / AEO (generative engine optimization): see which sites and brands AI assistants recommend for the questions your customers ask, and track it over time.

• 🤖 7 engines in one run: ChatGPT (web answer with search), Perplexity (Sonar), Gemini, Google AI Mode, Google AI Overviews, Claude, and ChatGPT through the official OpenAI API.
• 🔗 Citations as data: URL, domain and title for every source, plus a one-row-per-citation view.
• 🏷️ Brand extraction on every engine: brands lists each recommended product in answer order with mention count, whether the answer cites that brand's own site, and a confidence flag. first_brand is the top pick. Ready for share-of-voice counts without parsing text.
• 🔎 Fan-out queries: the searches the engines ran to answer (when reported).
• ⚡ Fast: engines run in parallel. A prompt on ChatGPT + Perplexity takes about 20-25 seconds, so it works well as a tool for AI agents through the Apify MCP server.
• ✅ Clean sourcing: no logins, no browser automation and no accounts of yours. See How the data is obtained.

Wrenfield Search Data: keyword and AI-search visibility data, priced per result

• Keyword data: Keyword Search Volume · Keyword Difficulty · Keyword Research · Autocomplete Expander · Google Trends · People Also Ask · Competitor Keywords · Keyword Gap
• AI search visibility: AI Search Visibility Tracker · Google AI Overview Scraper · AI Answer Scraper · Agency AI Visibility Reports
• Site and domain SEO: Domain Authority & Traffic · Bulk PageSpeed · SEO Toolkit · SEO Agency Report

What data do you get?

Field	What it is
prompt, engine, engine_name, model	What was asked, where, and which model answered
status	ok, no_answer (e.g. Google showed no AI Overview) or error (engine didn't respond; not charged)
answer_markdown, answer_text, answer_word_count	The answer as markdown and plain text
citations, citation_count, cited_domains	Every cited source (url, domain, title) and the unique domains in order
brands	Every recommended brand/product in answer order: name, rank, mentions, cited + cited_domain (the answer cites that brand's own site), confidence (high/low)
brands_mentioned, first_brand	High-confidence brand names in order, and the top pick
brand_entities	Raw brand list as reported by the engine (ChatGPT only)
fan_out_queries	Web searches the engine ran to build the answer (when reported)
organic_results	AI Overviews only: the top organic results on the same Google page
response_time_secs	How long the engine took

How to use it

1. Enter your Prompts, one per line, e.g. What is the best CRM for a small business?
2. Select the AI engines (default: ChatGPT and Perplexity).
3. Pick the Country and Language the answers should be localized to.
4. Click Start. Open the AI answers view for answers, or the Citations view for one row per cited source.

Input example

{
    "prompts": ["What is the best CRM for a small business?", "HubSpot vs Pipedrive for a 5-person sales team"],
    "engines": ["chatgpt", "perplexity", "gemini", "google_ai_mode"],
    "country": "United States",
    "language": "English"
}

Output example

{
    "prompt": "What is the best CRM for a small business?",
    "engine": "chatgpt",
    "engine_name": "ChatGPT",
    "model": "gpt-6",
    "status": "ok",
    "answer_text": "My top recommendation is HubSpot CRM for most small businesses, especially ...",
    "answer_word_count": 640,
    "citations": [{"url": "https://www.techradar.com/best/best-crm-for-small-business", "domain": "techradar.com", "title": "Best CRM for small business"}],
    "citation_count": 20,
    "cited_domains": ["toolradar.com", "g2.com", "techradar.com", "hubspot.com"],
    "first_brand": "HubSpot",
    "brands_mentioned": ["HubSpot", "Zoho CRM", "Pipedrive", "Bigin", "Freshsales"],
    "brands": [{"name": "HubSpot", "rank": 1, "mentions": 5, "cited": true, "cited_domain": "hubspot.com", "confidence": "high"},
               {"name": "Zoho CRM", "rank": 2, "mentions": 4, "cited": true, "cited_domain": "zoho.com", "confidence": "high"}],
    "fan_out_queries": ["small business CRM software 2026 reviews pricing comparison"],
    "country": "United States",
    "language": "English",
    "response_time_secs": 21.8
}

Pricing

This Actor uses pay-per-event pricing, with lower prices on paid Apify plans.

Event	Free plan	Bronze	Silver	Gold and above
AI answer (ai-answer), per answer returned	$0.015	$0.0135	$0.012	$0.01
Empty answer (empty-answer): the engine was checked but showed no AI answer (most often, Google showed no AI Overview)	$0.006	$0.006	$0.006	$0.006

Engine errors and cut-off answers are not charged.

Example run (Free-plan prices)	Cost
1 prompt on ChatGPT + Perplexity	$0.03
25 prompts on 4 engines (100 answers)	$1.50
Weekly tracking: 50 prompts x 6 engines	$4.50 per week

Set Maximum cost per run to cap your spend; the Actor stops cleanly at the cap.

Free Apify plan: 2 prompts and 2 engines per run.

Compared with Apify's own AI scrapers (Store prices, Oct 19, 2026)

Apify's first-party scrapers (apify/perplexity-search-scraper, apify/chatgpt-search-scraper, apify/gemini-search-scraper, apify/google-ai-mode-scraper) charge $0.20 per answer on the Free plan, then much less on paid plans. Live pricingInfos checked Oct 19, 2026:

Their Actor (event)	Free	Bronze	Silver	Gold
Perplexity (perplexity-ai-result-scraped)	$0.20	$0.013	$0.010	$0.009
ChatGPT (chatgpt-result-scraped)	$0.20	$0.005	$0.004	$0.003
Gemini (gemini-result-scraped)	$0.20	$0.005	$0.004	$0.003
Google AI Mode (ai-mode-result-scraped)	$0.20	$0.005	$0.003	$0.002
This Actor (ai-answer)	$0.015	$0.0135	$0.012	$0.01

• If you only need one engine on a paid plan, Apify's own scraper is cheaper per answer ($0.002–0.005 for ChatGPT, Gemini and AI Mode). Use it.
• Use this Actor when you need several engines compared in one table, structured brand rankings (brands, first_brand) on every engine, Claude or the official OpenAI API next to the consumer engines, or a licensed data source instead of browser scraping.
• Free plan: $0.015 vs $0.20 per answer.
• Failed and cut-off answers are free here; empty answers are $0.006.

Switching from Apify's AI scrapers

Send the input you already use for apify/perplexity-search-scraper, apify/chatgpt-search-scraper, apify/gemini-search-scraper or apify/google-ai-mode-scraper, and add engines to pick the engine (default: ChatGPT + Perplexity):

{
    "queries": "best crm for small business\nhubspot vs pipedrive",
    "countryCode": "us",
    "engines": ["perplexity"]
}

Their field	Here
queries (one per line)	Accepted as is (same as prompts)
countryCode (us, gb, ...)	Accepted as is (same as country)
perplexitySearch	Accepted; search recency, images and related questions are not supported and are ignored
Output query, text, sources, citationUrls	Added to every row when you use queries (or set apifyCompatibleFields: true)
Output relatedQuestions, images	Present, always empty

What differs: answers come from licensed data sources and official model APIs rather than from a browser session, so wording and citations can differ from what you get elsewhere (see below). Microsoft Copilot is not offered.

How the data is obtained

• All answers come from DataForSEO, a commercial data provider: its AI Optimization API for the AI assistants and its SERP API for Google AI Mode and AI Overviews. The Actor never opens a browser, never logs in to ChatGPT, Gemini, Google or any other account, and never uses your credentials.
• Perplexity, Claude and ChatGPT API answers come from the providers' official model APIs (Perplexity Sonar, Anthropic Claude, OpenAI). Pick these engines if you need answers that come only from official APIs.
• ChatGPT and Gemini answers are the web-interface answers (with web search and citations) that DataForSEO collects from those assistants. Google AI Mode and AI Overviews are read from public Google results pages.
• Answers are generated fresh for each run, so they vary between runs, just as they do for real users.

For agencies: run your whole client book

Collecting AI answers for clients? Skip the brand matching, scoring and report writing. Agency AI Visibility Reports takes one CSV row per client and returns a finished, white-label packet per client (HTML + PDF): whether ChatGPT, Perplexity, Gemini and Google AI Mode name the client, competitor share of voice, Google rankings, quoted evidence and a ranked action queue, plus one portfolio page for the whole book. Save it as a task and schedule it weekly for week-over-week change.

client,domain,competitors,category,keywords
Help Scout,helpscout.com,Zendesk | zendesk.com; Freshdesk | freshworks.com; Intercom | intercom.com,help desk software,help desk software; shared inbox software
Pipedrive,pipedrive.com,HubSpot | hubspot.com; Salesforce | salesforce.com,CRM for small business,crm for small business

$12 per client packet ($8 each for books of 20-49 clients, $7 each at 50+). The Store price box lists this as "$12,000 / 1,000 packets"; that is the same $12 per packet. Turn on Quote only for a free count of packets and the maximum price before anything runs; only completed packets are charged.

Use it through the API, on a schedule or with AI agents

One-link MCP setup: https://mcp.apify.com?tools=wrenfield-data/ai-answer-scraper (Claude, Cursor, VS Code or any MCP client). Set maxTotalChargeUsd on the run to cap what it can charge.

Call it from Python, JavaScript or any HTTP client with the Apify API, schedule it weekly to track AI visibility, or connect it to Make, Zapier, n8n and Google Sheets. AI agents can call it through the Apify MCP server. Every output field is described in the dataset schema.

curl -X POST "https://api.apify.com/v2/acts/wrenfield-data~ai-answer-scraper/run-sync-get-dataset-items?token=YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompts": ["What is the best CRM for a small business?"], "engines": ["chatgpt", "perplexity"]}'

Use it from an AI agent (MCP)

Add one line to Claude, Cursor, VS Code or any MCP client and the agent gets this Actor as a tool (it appears as wrenfield-data--ai-answer-scraper):

https://mcp.apify.com?tools=wrenfield-data/ai-answer-scraper

Try asking: Ask Perplexity and ChatGPT "What is the best CRM for a small business?" and list the domains each one cites.

Fields your agent reads: answer_markdown (the answer with links and tables kept), citations (url, domain, title), cited_domains, brand_entities, status.

Real output (one row from a run on Oct 19, 2026, trimmed):

{"prompt": "What is the best CRM for a small business?", "engine": "perplexity", "status": "ok", "answer_markdown": "**For most small businesses, HubSpot CRM is the best starting point**: ...", "cited_domains": ["salesforce.com", "pcmag.com", "techradar.com"], "citation_count": 10}

AI answers change between runs; treat one answer as a sample. Set a maximum cost per run (maxTotalChargeUsd over the API, call options over MCP) so an agent loop cannot overspend.

FAQ

Do I need ChatGPT, Perplexity or Google accounts? No. Nothing runs under your accounts.

Why is an AI Overview sometimes missing? Google shows AI Overviews only for some queries and locations. The row then has status: no_answer and the lower empty-answer price. That result is still useful for tracking AI Overview presence.

Can it tell me whether my brand is mentioned? This Actor returns the raw answers and citations. For brand-mention rates, share of voice, positions and sentiment across engines, use AI Search Visibility Tracker.

Related tools

From the same developer:

• AI Search Visibility Tracker: brand mentions, share of voice, citations and sentiment across AI engines
• People Also Ask Scraper: Google PAA questions, the prompts real people ask
• Keyword Research Tool: turn a topic into prompts and keywords with search volume
• SEO Toolkit All-in-One: authority, traffic and backlinks of the sites AI engines cite
• Google Autocomplete Keyword Expander: long-tail questions from Google autocomplete

Feedback and support

Missing a field, hit an error, or need another country or option? Open an issue on the Issues tab and include the run ID. We read every issue and reply there.

Acceptable use

• This Actor is an independent tool. It is not affiliated with, endorsed by or sponsored by OpenAI, Perplexity, Google, Anthropic or DataForSEO. Product names are used only to describe which engines are queried.
• Use the answers for research, monitoring and analysis. Don't use them to train or build AI models that compete with the engines they come from, and don't present them as the engines' official statements.
• Don't send prompts that are unlawful, that contain other people's personal data, or that try to make the engines produce harmful content.
• The Actor may not be used from, or for people or organizations in, Russia, Belarus, Cuba, Iran, Syria, Myanmar, North Korea, Crimea or the Russian-occupied territories of Ukraine.
• You are responsible for using the results lawfully.