ChatGPT Search & Gemini Scraper: AI Answers, Sources, Brands
Pricing
from $104.00 / 1,000 answers
ChatGPT Search & Gemini Scraper: AI Answers, Sources, Brands
Ask ChatGPT and Gemini your questions and get the answers a user sees: full Markdown answer, cited sources, web results, brands mentioned with their rank, per country and language. Track your brand and competitors in AI answers (GEO / AI search visibility).
Pricing
from $104.00 / 1,000 answers
Rating
0.0
(0)
Developer
Quarra Labs
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 days ago
Last modified
Share
ChatGPT Search & Gemini Scraper: AI Answers, Sources & Brand Mentions (GEO)
Ask ChatGPT and Gemini your questions and get what a user sees: the full answer in Markdown, the sources it cites, the web results behind it, and the brands it names, in order. Choose the country and the language. Give it your brand and your competitors and each answer says whether they are mentioned, at which rank, and whether their site is cited. Built for GEO / AI search visibility, SEO and marketing teams that track how AI engines talk about them.
$130 per 1,000 answers (one answer = one question on one engine), plus a small start fee per run. An answer that cannot be delivered is never charged.
Quick start
- Type your questions, as a user would ask them.
- Pick the engines (ChatGPT, Gemini or both), the country and the language.
- Optionally add the brands to track, then click Start and read the answers in the Output tab.
It also runs from the Apify API, on a schedule, and connects to webhooks, Make, Zapier, n8n or Apify's MCP server. Run the same questions every week to see how your visibility moves.
What it is used for
- Brand visibility in AI answers: is your brand mentioned, at which rank, next to which competitors.
- Source tracking: which sites ChatGPT and Gemini cite for your topics, and whether yours is among them.
- Content gaps: the questions where you are absent and who is cited instead.
- Market research: how each engine answers in each country and language.
What you get
| Full answer as Markdown | yes |
| Sources: title, link, domain | yes |
| Web results the engine looked at | ChatGPT |
| Related searches | when the engine gives them |
| Brands named in the answer, with rank | yes |
| Your tracked brands: mentioned, rank, position in the list, cited in sources, in web results | when you give brands |
| Model that answered, country, language, time | yes |
Inputs
- Questions: up to 5,000 per run, repeats are asked once. Each question is asked once per engine.
- Engines:
chatgpt,geminior both (default). - Country: a two-letter code (
US,GB,FR...) or the name (United Kingdom,UK,USA...). Language: a code (en,fr,de,pt-BR,zh-CN,zh-TW...) or the name. - ChatGPT web search: on by default, so answers carry sources like most users see.
- Brands to track: names, or objects with
name,aliasesanddomains. Up to 100. - Speed: Auto answers up to 40 answers one by one (about 20 seconds each, in parallel) and sends bigger lists as a batch. A batch needs about 9 minutes of run time left; with a shorter run timeout the questions are asked one by one instead. The default timeout (1 hour) fits big lists; a run that reaches its timeout stops cleanly and says how many were not asked.
- Maximum answers and Apify's Maximum cost per run: the run stops before going over either.
Output
One record per question and engine. Main fields: prompt, engine, country, language, answerMarkdown,
sources (title, url, domain), webResults, brandsMentioned (name, rank, category),
brandTracking (brand, mentioned, rank, listPosition, citedInSources, citedSourceUrls), scrapedAt.
Questions that cannot be answered come as free error records with the reason and whether asking again may work. The
run summary (OUTPUT) gives counts per engine and, when you track brands, mention rate, average rank and citations per
brand and engine.
Pricing
Pay per event:
| Event | Price |
|---|---|
| Answer delivered | $130 per 1,000 |
| Run start | $0.015 per run |
Higher Apify plans pay less per answer. Never charged: questions that fail, error records, repeats, notices.
Limits
- An answer is what the engine gives at that moment. The same question can get a different answer an hour later; that is how these engines work.
- Countries and languages: ChatGPT is served in more than 190 countries and 128 languages, Gemini in 213 countries and 95 languages. A combination an engine does not serve returns a free error record.
- Gemini gives sources but no web results or related searches.
- Brands named by the engine are the ones ChatGPT recognises and that appear in the text. Gemini does not give this
list, so for Gemini
brandsMentionedholds only your tracked brands: add the brands you care about. - Tracked brands are found by name and aliases in the text.
mentionscounts them in the text you read: links, citation chips and images are not counted (a cited site shows incitedInSources). - Questions are limited to 2,000 characters.
FAQ
Do I need a ChatGPT or Gemini account? No.
Is anything different on Apify's free plan? Live answers need a paid Apify plan. On the free plan, the prefilled
example (the two questions, ChatGPT and Gemini, US, English, no other option) returns a stored sample, marked
sample: true with its date. Any other input asks nothing and says so in the run. Only the run start is charged.
What if a run is restarted by the platform? It resumes where it was: answers already delivered are not asked or charged again.
Does the Actor send anything to Quarra? Only when a run fails or runs out of time: the Actor, its build, the error type, the line of our code where it happened, and the memory and time the run was given, so we can fix it fast. Never your questions, your results, your account or the run ID.