Google AI Mode Scraper - AI Answers with Sources
Pricing
from $29.75 / 1,000 google ai mode answer delivereds
Google AI Mode Scraper - AI Answers with Sources
Scrape Google AI Mode answers to search queries, no login: full answer in markdown and plain text, cited sources with URL, title and domain, citations per passage, optional brand check, by country and language. US$ 0.035 per answer, errors free.
Pricing
from $29.75 / 1,000 google ai mode answer delivereds
Rating
0.0
(0)
Developer
Scrapewise Data
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
a day ago
Last modified
Share
Google AI Mode Scraper
Google AI Mode Scraper collects what Google AI Mode answers to a search query, without login. Give it a list of queries (best AI coding assistants for developers, is the iPhone 17 worth upgrading from the iPhone 15, Notion vs Obsidian) and get back, for each one, the full AI Mode answer in Markdown and plain text, every source Google cited (URL, title, domain, site name, snippet, position), and the citations passage by passage (which sources back which part of the answer). One clean row per query, ready for a spreadsheet, a dashboard or an AI pipeline.
US$ 0.035 per answer (US$ 35 per 1,000), plus US$ 0.005 once per run. No monthly fee. Error rows are free.
At a glance
- Price per answer: US$ 0.035 on the Free plan, down to US$ 0.02975 on Gold and above, plus US$ 0.005 once per run
- Engine: Google AI Mode, the "AI Mode" tab of Google Search, logged-out (what a visitor sees)
- Answer: Markdown with headings, bullet lists, bold and tables, plus a plain text copy
- Sources: Every cited URL with position, title, domain, site name and snippet, flagged
citedInAnswer, tracking parameters removed - Citations: Each cited passage with its text and the sources behind it
- Location: Any country with a 2-letter code (US, GB, DE, FR, JP...) and any language; Google localizes brands, stores and sources
- Brand check (optional): Mentioned or not, mention count, rank, domain cited as a source, same price
- Error rows: Free, with a
statusand anerrorCode
Why this Actor
- Price. An AI Mode answer with its sources and passage citations costs US$ 0.035 here. Ten thousand answers cost US$ 350 on the Free plan and less on paid plans, with no charge for errors.
- Answers you can read.
answerkeeps the structure Google shows (section headings, bullet lists, bold product names, comparison tables) as clean Markdown.answerTextis the same answer as plain text for spreadsheets, NLP and embeddings. - Real source URLs. Sources come straight from the page data, so you get the publisher URL, not a Google redirect link, plus the title and the snippet Google used.
- Which source backs which sentence.
citationsmaps each passage of the answer to the sources behind it, so you can see exactly what a site is credited for. - Inputs that just work. Country and language are free text:
US,us,Germany,en-GBall work, and an unknown value falls back to US with a log line instead of failing the run. - Clear failures. A query that could not be answered becomes a free error row with a reason, so you never pay for an empty result.
Switching from another Google AI Mode actor? Your existing input works
The input names used by other AI Mode and AI search actors are accepted as they are, so you can paste your current input:
| You send | Read as |
|---|---|
queries, prompts, searchQueries, questions, query, prompt, keywords, searchTerms | Search queries (a list or a single string) |
country, countryCode, gl, location, region | Country (code or name) |
language, languageCode, lang, hl | Language |
maxItems, maxResults, limit, maxQueries | Maximum answers per run |
One real row
Query best AI coding assistants for developers, country US (collected in the Apify cloud on 2026-10-09; answer and lists shortened here):
{"type": "answer","status": "OK","query": "best AI coding assistants for developers","answer": "The choice of the best AI coding assistant depends entirely on your specific workflow, the complexity of your repository, and your team's security requirements. As of **late 2026**, the ecosystem has shifted from simple line completions to advanced **autonomous agents** ...\n\n### The Absolute Top Tier: Best for Day-to-Day Development\n\n- **Cursor**: **Best overall AI-first IDE** for complex, multi-file projects ...\n- **GitHub Copilot**: **Best for seamless editor integration** and standard pair programming ...","answerText": "The choice of the best AI coding assistant depends entirely on your specific workflow ...","answerLength": 3597,"sourceCount": 5,"citedSourceCount": 5,"sources": [{"position": 1,"url": "https://www.shakudo.io/blog/best-ai-coding-assistants","title": "Best AI Coding Assistants as of October 2026 | Shakudo Blog","domain": "shakudo.io","siteName": "Shakudo","snippet": "Closed-source assistants: GitHub Copilot. Devin (autonomous software engineer); Cursor ...","citedInAnswer": true},{"position": 3,"url": "https://www.faros.ai/blog/best-ai-coding-agents-2026","title": "Best AI Coding Agents for 2026: Real","domain": "faros.ai","siteName": "Faros AI","snippet": "Copilot (Agent Mode): the pragmatic default Cline: VS Code agent for developers who want control ...","citedInAnswer": true},{"...": "3 more"}],"citedDomains": ["shakudo.io", "replit.com", "faros.ai", "zapier.com", "axify.io"],"allDomains": ["shakudo.io", "replit.com", "faros.ai", "zapier.com", "axify.io"],"citationCount": 8,"citations": [{"position": 3,"text": "GitHub Copilot: Best for seamless editor integration and standard pair programming ...","sources": [{"url": "https://www.faros.ai/blog/best-ai-coding-agents-2026", "title": "Best AI Coding Agents for 2026: Real", "domain": "faros.ai"}]},{"...": "7 more"}],"model": "Google AI Mode (logged-out)","country": "US","language": "en","responseSeconds": 18.3,"scrapedAt": "2026-10-09T16:56:32Z","error": null,"errorCode": null}
What you can do with it
- AI search visibility (GEO / AEO): see which brands and domains Google AI Mode recommends and cites for the queries that matter in your market, by country and language.
- Brand monitoring: add your brand and your competitors to
brandsand get, for every answer, whether each one was mentioned, in what order, and whether its site was cited. - Content and SEO research: find the pages Google trusts enough to cite in AI Mode, compare them with the classic results, and see which passages they are credited for.
- Product and market research: collect how AI Mode compares products, prices and features in a category, in Markdown that keeps the tables and lists.
- Datasets for analysis: build a dated record of AI answers and citations, run after run, to track how they change.
Input
| Field | What it does |
|---|---|
queries | Search queries, up to 300 characters each, one answer per query |
maxItems | Maximum answers in this run. Default 50 |
country | Country Google localizes the answer for. Default US |
language | Answer and interface language. Empty follows the country |
brands | Optional: brands or domains to check in each answer (Cursor | cursor.com) |
{"queries": ["best AI coding assistants for developers", "is the iPhone 17 worth upgrading from the iPhone 15"],"country": "US","maxItems": 50}
With no input at all, the Actor runs one example query, so a test run always returns data.
This Actor is built for search queries. Content generation requests (write, generate, translate, code...) and queries over 300 characters are returned as free INVALID_INPUT rows. Queries are asked one at a time, each in a fresh AI Mode search, with a short pause between them.
Brand check example
{"queries": ["best AI coding assistants for developers", "best AI code review tools"],"brands": ["Cursor | cursor.com", "GitHub Copilot | github.com", "Windsurf"]}
Each row then carries brands (one entry per brand with mentioned, mentionCount, firstMentionRank, cited, citationPosition), brandsMentioned and brandsCited. The dataset also has a ready "Brand check" view.
Output fields
type, status, query, answer (Markdown), answerText (plain text), answerLength, sourceCount, citedSourceCount, sources (position, url, title, domain, siteName, snippet, citedInAnswer), citedDomains, allDomains, citationCount, citations (position, text, sources), model, country, language, responseSeconds, scrapedAt, error, errorCode.
The dataset has three views: Google AI Mode answers (one line per query), Sources (one line per source) and Brand check. Export as JSON, CSV, Excel or through the API.
Status and error codes (errors never charged)
| status / errorCode | Meaning |
|---|---|
OK | Answer delivered and charged |
INVALID_INPUT | Query over 300 characters, or a content generation request |
NO_ANSWER | Google loaded but did not show an AI Mode answer for this query |
BLOCKED | Google did not answer after several retries; run again later |
NOT_REACHED, UNEXPECTED | The run timeout arrived, or something unforeseen broke; only that query is lost |
Pricing
| Event | Free plan | Gold and above |
|---|---|---|
| Google AI Mode answer delivered | US$ 0.035 | US$ 0.02975 |
| Run started (once per run that asks at least one valid query) | US$ 0.005 | US$ 0.00425 |
100 queries in one run cost US$ 3.505 on the Free plan. Error rows are free, a run with only invalid queries pays nothing, and the proxy is included.
Use it from code, Make, Zapier or an AI agent
Call it from the Apify API, the Python or JavaScript client, Make, Zapier, n8n or any MCP client. Example with the Python client:
from apify_client import ApifyClientclient = ApifyClient("<YOUR_APIFY_TOKEN>")run = client.actor("scrapewise/google-ai-mode-scraper").call(run_input={"queries": ["best AI coding assistants for developers"],"country": "US",})for row in client.dataset(run["defaultDatasetId"]).iterate_items():print(row["query"], row["sourceCount"], row["citedDomains"])
Schedule the same input daily or weekly to follow how the answers and the cited sites change.
Limitations
- Answers are what a logged-out visitor sees in Google AI Mode. AI answers vary from one run to the next; compare several runs before drawing conclusions.
- Each answer takes about 30 seconds, one query at a time, so 50 queries take around 25 to 30 minutes. Keep the default run timeout or raise it for long lists; queries the timeout does not reach come back as free
NOT_REACHEDrows. - AI Mode is not offered for every query, country or language. When Google shows no AI answer, the row comes back as a free
NO_ANSWER. - Country and language localize the answer through Google's own region and language settings.
- This Actor reads public answers only and respects the sites' terms.
FAQ
Do I need a Google account or an API key? No. The Actor reads AI Mode as a logged-out visitor.
Is it the same as the AI Overview? No. AI Overview is the short summary on top of normal results; AI Mode is the full conversational answer in its own tab, longer and with more sources.
Can I get the answer in another language? Yes. Set language (for example de) and write the query in that language.
Changelog
- 2026-10-09, 0.1: first release. Google AI Mode answers in Markdown and plain text, cited sources with title and snippet, passage-level citations, any country and language, optional brand check, input names of other AI Mode actors accepted, free error rows.