Ad library API for AI agents: from $0.001 per call ($1 per 1,000), no subscription
Whizbrew's Ad library API costs from $0.001 per call ($1 per 1,000 calls); a typical call is $0.003 ($3 per 1,000). Only a call that returns data is charged: an empty or failed call is free. There is no subscription and no monthly fee. A new account starts with $2 of free credit, with no card.
It reads the ads a brand runs, read from the public ad libraries: 39 tools, live at the moment of the call, over one API key or one MCP server (https://whizbrew.com/mcp). It is an API, not a scraper you run: no proxies, no browser and no scraping code on your side. The same key reaches 893 tools for other platforms (all APIs, all tools, pricing).
Pricing
| Tool | What it returns | Per call that returns data | Per 1,000 calls |
|---|---|---|---|
ads.app | Ads an app is running, read from the public ad libraries. When there are none, the answer is {ads: [], total_by_platform, note} and says which libraries have ads for the app. When the tracker is slow the answer is {ads, partial: true, note, retry_after_s}: the ads that could be read in time, and what is missing (none in time: status no_answer_in_time, free). | $0.006 | $6 |
meta_ads.search | Search Facebook and Instagram ads by keyword in the public ad library; match exact searches the words as one phrase, language keeps ads written in one language. One page per call: up to 30 ads first, then about 10 per page: send the same arguments plus cursor = next_cursor. total (first page only) is the library's count of matching ads. A next page can answer rate_limited; ask again. limit cuts a page, the cursor still moves past the whole page. | $0.006 | $6 |
meta_ads.advertiser | Ads one advertiser (Facebook page) is running, from the public ad library, by page id or straight from a brand name or website (name: the page is found first and returned as advertiser). One page per call: up to 30 ads first, then about 10 per page: send the same arguments plus cursor = next_cursor. total (first page only) is the library's count of that page's ads. A next page can answer rate_limited; ask again. limit cuts a page, the cursor still moves past the whole page. | $0.006 | $6 |
meta_ads.find_advertiser | Find advertisers by name in the public Facebook and Instagram ad library and get their page ids. | $0.003 | $3 |
meta_ads.ad | One Facebook or Instagram ad by its ad library id or URL, with who paid for it and its EU and UK audience and reach when published. | $0.006 | $6 |
tiktok_ads.top | Top performing TikTok ads in a country. Returns the first page only (up to 20 ads). | $0.006 | $6 |
tiktok_ads.top_detail | One top TikTok ad: brand, landing page, countries, engagement and video files. | $0.006 | $6 |
tiktok_ads.top_analytics | Performance of one top TikTok ad: click-through by second, keyframes, CTR percentile and engagement. | $0.006 | $6 |
tiktok_ads.filters | Industries, objectives, countries, languages and periods that tiktok_ads.top accepts. | $0.003 | $3 |
tiktok_ads.sponsored_posts | TikTok posts that creators marked as commercial (a brand partnership or promotion), newest first, for one creator or a whole country. EU/EEA countries and Brazil only. | $0.003 | $3 |
tiktok_ads.trending_video | One trending TikTok video from tiktok_ads.trending_videos, with its metrics and top comments. | $0.003 | $3 |
snapchat.ad_library_search | Snapchat ads of one advertiser in a European country, from Snapchat's public ads library: status, impressions, targeting, media and landing page. | $0.003 | $3 |
google.ad_advertisers | Find advertisers by name in Google's Ads Transparency Center and get their ids, country and rough number of ads. | $0.003 | $3 |
google.ads_by_advertiser | Google ads (Search, YouTube, Display) of one advertiser or one website, from Google's Ads Transparency Center, 40 per page with dates and format. | $0.003 | $3 |
google.ad_creative | One Google ad in full, from Google's Ads Transparency Center: every variation of its creative (image or preview), its format, and each country it was shown in with the last day shown. | $0.003 | $3 |
apple_ads.search | Find an app or a developer by name in Apple's App Store ad repository and get the id that apple_ads.app_ads and apple_ads.developer_ads take. European Union only. | $0.002 | $2 |
apple_ads.app_ads | The App Store ads of one app (search results, Today tab, Search tab, product pages) from Apple's ad repository: placement, format, country, first and last day shown, targeting used, texts and screenshots. European Union storefronts, last year only, at most 100 ads per call. | $0.003 | $3 |
apple_ads.developer_ads | The App Store ads of every app of one developer, from Apple's ad repository: which apps the developer advertises, where, since when and with which creatives. European Union storefronts, last year only, at most 100 ads per call. | $0.003 | $3 |
microsoft_ads.search | Search the ads shown on Bing and Microsoft's network in the European Economic Area by words, from the Microsoft ad library: title, text, display URL, landing page, advertiser. 24 per page; the count stops at 1000. | $0.003 | $3 |
microsoft_ads.advertisers | Find advertisers by name in the Microsoft (Bing) ad library and get their ids, country and whether Microsoft verified them. | $0.002 | $2 |
microsoft_ads.advertiser_ads | The Bing and Microsoft network ads of one advertiser in the European Economic Area, from the Microsoft ad library: title, text, display URL, landing page and pictures. 24 per page; the count stops at 1000. | $0.003 | $3 |
microsoft_ads.ad | One ad of the Microsoft (Bing) ad library in full: who paid, first and last day, the range of impressions, the share of impressions per country and the targeting criteria used. | $0.003 | $3 |
amazon_ads.search | Search the ads shown on Amazon's European stores (sponsored products, brands and display) by words, from Amazon's ad library: advertiser, who paid, dates, targeting methods, the range of people reached per store and the advertised product pages. 50 per page. | $0.003 | $3 |
amazon_ads.ad | One ad of Amazon's European ad library by its id: advertiser, who paid, dates, targeting methods, people reached per store and the advertised pages. | $0.002 | $2 |
pinterest_ads.search | The Pinterest ads of one advertiser shown in one country, from Pinterest's ads repository: pin, text, image or video, dates, the range of people reached per country, and the targeting (ages, genders, interests, audience lists). 24 per page. | $0.003 | $3 |
pinterest_ads.advertisers | Find the advertiser names Pinterest's ads repository knows that start with or contain a word; pinterest_ads.search takes the exact name. | $0.001 | $1 |
pinterest_ads.ad | One Pinterest ad from Pinterest's ads repository by its pin id: advertiser name, text, media, dates, people reached per country and the targeting. | $0.002 | $2 |
google.political_advertisers | Advertisers of election ads on Google and YouTube with their number of ads and total spend, from Google's political advertising report (a public data file, new every day). Search by name, filter by region, biggest spender first. Covers the countries where Google verifies election advertisers (US, IN, BR, AU, GB, MX and others). | $0.003 | $3 |
google.political_spend_by_region | Election ad spend on Google and YouTube by country, or by state and electoral district of one country, from Google's political advertising report. | $0.002 | $2 |
google.political_weekly_spend | One advertiser's election ad spend on Google and YouTube week by week, newest first, with the total, from Google's political advertising report. | $0.003 | $3 |
snapchat.political_ads | Political and advocacy ads on Snapchat in one year, worldwide, from Snapchat's public political ads library: spend, impressions, dates, organisation and payer, targeting and the creative. Most impressions first. | $0.003 | $3 |
snapchat.political_advertisers | Who paid for political and advocacy ads on Snapchat in one year: each organisation and payer with its number of ads, total spend and impressions, from Snapchat's public political ads library. Most impressions first. | $0.003 | $3 |
domain.sellers_json | The sellers.json file of an ad exchange or ad network: how many publishers and intermediaries it sells for, and the sellers that match a name, a domain or an account id (seller id, name, domain, type). Google's file is too large to read. | $0.002 | $2 |
domain.ads_txt_check | Checks a site's ads.txt (or app-ads.txt) against the sellers.json files of the ad systems it names: for each line whether the ad system really lists the account, and as a publisher (DIRECT) or an intermediary (RESELLER). Returns the count per ad system and the lines with a problem. | $0.006 | $6 |
ads.publisher_sellers | Which large ad exchanges sell a publisher's ad space: looks the publisher's domain up in the sellers.json files of 14 exchanges (Magnite, OpenX, PubMatic, Index Exchange, Xandr, TripleLift, Sovrn, Equativ, Sharethrough, 33Across, Media.net, Yieldmo, Teads, Amazon) and returns its seller accounts in each. | $0.006 | $6 |
ads.app_ads_txt | The ad sellers an app authorizes (its app-ads.txt), found the way ad buyers find it: the developer website named in the app's App Store or Google Play listing. Returns the exchanges, account ids and direct or reseller. | $0.002 | $2 |
ads.find_advertiser | Where does a brand advertise? Looks one brand name or website up in eight ad libraries at once (Google, Meta, Apple App Store, Microsoft Bing, Snapchat, Amazon, Pinterest, TikTok) and returns for each whether it was found, the matching advertisers with their ids, the number of ads where the library gives one, and the tool that lists the ads there. | $0.009 | $9 |
ads.new_since | The ads an advertiser started on or after a date, for a weekly look at a competitor: reads Google's ad library (by website or advertiser id) and Meta's (by Facebook page id), keeps the ads whose own start date is on or after the day, newest first, and says how many each library has. One page per library (Google up to 40 ads, Meta up to 30); has_more tells when there are more. ads.find_advertiser finds the ids for a brand name. Free when no new ad is found. | $0.006 | $6 |
ads.shared_sellers | The ad-seller accounts that two to five sites all authorize in their own ads.txt files, to see whether sites belong together: the same DIRECT account on several sites means one publisher or one sales house sells the ad space of all of them. Per shared account: exchange, account id and how each site lists it; per pair of sites: shared accounts, shared DIRECT accounts, the share of the smaller file and whether both name the same owner domain; per site: its account counts, owner and manager domains. Shared RESELLER accounts are common between unrelated sites and say little. Reads each site's /ads.txt now (domain.ads_txt lists one file in full). No account in common is free. | $0.002 | $2 |
Example calls
ads.app ($0.006 per call): Ads an app is running, read from the public ad libraries
curl -s -X POST https://whizbrew.com/v1/call/ads.app \
-H "Authorization: Bearer $WHIZBREW_KEY" -H "content-type: application/json" \
-d '{"app_id":"570060128","limit":3}'
meta_ads.search ($0.006 per call): Search Facebook and Instagram ads by keyword in the public ad library; match exact searches the words as one p
curl -s -X POST https://whizbrew.com/v1/call/meta_ads.search \
-H "Authorization: Bearer $WHIZBREW_KEY" -H "content-type: application/json" \
-d '{"country":"US","limit":3,"query":"duolingo"}'
meta_ads.advertiser ($0.006 per call): Ads one advertiser (Facebook page) is running, from the public ad library, by page id or straight from a brand
curl -s -X POST https://whizbrew.com/v1/call/meta_ads.advertiser \
-H "Authorization: Bearer $WHIZBREW_KEY" -H "content-type: application/json" \
-d '{"limit":3,"page_id":"141935472517297"}'
Over MCP the same call is call_tool with {"tool": "<name>", "arguments": {…}}. How often each tool works, measured from real calls: https://whizbrew.com/status.
Start
- An agent on its own: read https://whizbrew.com/agents.md. It asks for a free quote (
GET https://whizbrew.com/v1/agent/guide?goal=<the task in plain words>), then one request (POST https://whizbrew.com/v1/agent/start) gives it a key that works at once with the free credit, with no email and no sign-up form. Its human claims the account later. - A chat app (ChatGPT, Claude, Gemini): add the MCP server
https://whizbrew.com/mcpas a custom connector and sign in. No key to copy. - An agent with a shell (Claude Code, Codex, Cursor): read https://whizbrew.com/llms.txt. The agent starts a pairing with one request, its user approves with one click, and the agent holds its own key.
- Plain HTTP: create an account at https://whizbrew.com/app#signup, make a key, then
POST https://whizbrew.com/v1/call/<tool>withAuthorization: Bearer <key>.