Dedicated Gemini APIGemini Scraper API — Ask Google Gemini, Get JSON with Sources
Send a prompt to the real Google Gemini and get the answer back as structured JSON, with every web source it cited. Anonymous: no Google account, no Gemini API key.
No credit card required · PAYG credits never expire
# Ask the real Google Gemini and read the sources
import scrapebadger
client = scrapebadger.ScrapeBadger("sb_live_...")
answer = client.gemini.ask(
prompt="Best web scraping APIs in 2026?",
web_search="force"
){
"answer": "Several APIs stand out in 2026...",
"web_search_triggered": true,
"citation_count": 6,
"citations": [{
"url": "https://example.com/scraping-apis",
"title": "Web Scraping APIs Compared",
"domain": "example.com"
}],
"source_domains": ["example.com", "..."],
"model": "gemini-flash-lite",
"latency_ms": 24118
}Gemini API — 2 Dedicated Endpoints
Structured JSON responses with normalized data models. No HTML parsing. No proxy management. No Google account.
/v1/gemini/ask/v1/gemini/brand-visibilityMore Than an Answer String
Most Gemini scrapers hand back plain text. ScrapeBadger returns the evidence behind the answer.
The real Google Gemini, not the Gemini API
Answers come from the consumer product with web browsing, so you see what a real user sees — including the sources Gemini surfaced. No Google account, no Gemini API key, no per-token bill.
Real cited source URLs
Every citation carries the actual url, title, and domain Gemini referenced — not a bare snippet with no way to verify it. Follow the link, check the source yourself.
Did it really browse?
web_search_triggered tells you whether Gemini actually ran a web search for this prompt or answered from the model alone. Force it on or off with web_search=force|off when you need determinism.
The model is reported, not hidden
Every response includes which Gemini model answered (an anonymous Flash-Lite variant), so you know exactly what generated the text you got back.
Brand visibility built in
One call returns mention count, first position, share of voice against named competitors, whether your domain was cited, and its citation rank. AEO/GEO platforms sell this as a $99–989/mo subscription.
Pay per success only
Credits are only deducted for successful responses. Blocked, rate-limited, and upstream errors are never billed. PAYG credits never expire.
Pay Per Request. Credits Never Expire.
You only pay for successful responses — blocked, rate-limited, and upstream errors are always free. PAYG credits never expire; volume subscription tiers reduce per-credit cost further.
Simple Integration. Any Language.
Get started in minutes with Node.js, Python, or plain HTTP requests.
The scrapebadger Node.js library wraps the Gemini API with typed methods. Install with npm install scrapebadger, then start asking Gemini in a few lines of code.
import ScrapeBadger from 'scrapebadger'
const client = new ScrapeBadger({
apiKey: 'sb_live_...'
})
// Ask the real Google Gemini (takes 20-25s ungrounded, 30-70s with web search)
const res = await client.gemini.ask({
prompt: 'Best web scraping APIs in 2026?',
webSearch: 'force',
})
console.log(res.answer)
console.log(res.webSearchTriggered, res.citationCount)
// Which sources backed the answer?
for (const c of res.citations) {
console.log(c.domain, c.url)
}
// How visible is your brand in that answer?
const vis = await client.gemini.brandVisibility({
prompt: 'Best web scraping APIs in 2026?',
brand: 'ScrapeBadger',
domain: 'scrapebadger.com',
competitors: ['Bright Data', 'ScrapingBee'],
})
console.log(vis.mentioned, vis.shareOfVoicePct, vis.citationRank)Frequently Asked Questions
Common questions about scraping Gemini with the API — Node.js, Python, or REST.
What does the Gemini Scraper API return?
The /ask endpoint returns the prompt, the answer as plain text, citations (url, title, domain), source_domains, web_search_triggered, the model that answered, country, answer_length, citation_count, latency_ms, and created_at.
Is this the Gemini API or the real Google Gemini?
The real Google Gemini consumer product. Requests go in anonymously — no Google account and no Gemini API key is involved on either side. That is why answers include the web sources Gemini cited, which the Gemini API does not give you.
How long does a request take?
Gemini composes the answer live, so /ask and /brand-visibility measure 20-25s ungrounded, 30-70s with web search end to end. Size your client timeouts to at least 60 seconds.
How do I measure my brand in Gemini answers?
Call /brand-visibility with a prompt, your brand name, and optionally your domain, aliases, and competitors. You get back mentioned, mention_count, first_position, position_score (1.0 = named at the very start), share_of_voice_pct against the competitors you named, cited plus cited_urls and citation_rank for your domain, a per-competitor breakdown, and an excerpt of the answer around the first mention — alongside the answer and its citations.
How do I call the Gemini Scraper API from Node.js?
Install with `npm install scrapebadger`, initialise the client with your API key, then call client.gemini.ask({ prompt: "..." }) or client.gemini.brandVisibility({ prompt: "...", brand: "...", competitors: ["..."] }). Both accept an optional country (ISO-3166 alpha-2, default US) and web_search (auto | force | off). Plain HTTP works too — every endpoint accepts GET or POST with the X-API-Key header.
Bigger volume? Save up to 64%
Per-request credit costs are listed above. For higher monthly volume, subscription tiers reduce the per-credit rate substantially. Both Gemini endpoints — ask and brand visibility — included on every plan.
Start Scraping Gemini Today
1,000 free credits. No credit card. Get your API key in under a minute.
PAYG credits never expire · Pay only for successful requests · No Google account needed