← All headings
Web scraping & browsers
2,168 listings from 1,017 providers, 1,715 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 426–450, one row per provider, those answering first · names and descriptions as their source publishes them
- AgentWork Web Evidenceapi.agentwork.runWebpage text extraction: clean text or Markdown from a public URL (title, headings, links, SHA-256). Free fixed sample: GET /v1/web/sample (no payment). $0.003 per URL Base ($0.006 Algorand); batch of 2-10 $0.003/URL ($0.006); render=true $0.01/URL ($0.02). Web read / fetch URL / scrape URL to markdown. Synchronous JSON, no account; respects robots.txt; failed reads not settled.Livechecked Evidence 1/4x402x402 Bazaar5 payers1 more from agentwork.run
- stall-rowstall-row-production.up.railway.appFetch one web page and return its main content as clean Markdown with title and word count, extracted server-side; a reader-proxy fallback retries pages that refuse the direct fetch (marked in-band). Private and loopback targets are refused. Pays per call or with one Toolkit Pack credit. Use this when an agent needs to read a page inside a workflow without a browser and without wading through navigation and boilerplate.Livechecked Evidence 1/4x402x402 Bazaar5 payers
- x402.openwebninja.com/website-contacts-scraper/scrape-contactsx402.openwebninja.comLivechecked Evidence 1/4x402x402 Bazaar5 payers
- AISkills402: Web to Markdownapi.aiskills402.comWeb to Markdown API: reads one public web page from the Cloudflare edge (static HTML, robots.txt respected, no JavaScript rendering) and returns clean markdown or plain text of the main content (nav and footer dropped; scope: page keeps all) with title, description, language and links. $0.005 USDC per page; you pay only when the page text is returned - refusals cost nothing. POST JSON {url, format?, links?, scope?}; free example at https://api.aiskills402.com/v1/run/web-to-markdown/exampleLivechecked Evidence 1/4x402x402 Bazaar5 payers14 more from aiskills402.com
- CompliAPIapi.compliapi.comScreen a website URL or domain against OFAC SDN and other global sanctions lists. Call before paying, advertising on, or integrating with a website to check for sanctions associations. Returns per-list matches with source URLs.Livechecked Evidence 1/4x402x402 Bazaar5 payers
- Sift Web Toolssift.srv1996466.hstgr.cloudList a website's URLs from its sitemaps. Reads robots.txt and sitemap indexes (gzip supported) and returns up to 2000 URLs with lastmod dates.Livechecked Evidence 1/4x402x402 Bazaar5 payers1 more from srv1996466.hstgr.cloud
- x402-web-extract.senpi-agent.workers.dev/fetchx402-web-extract.senpi-agent.workers.devFetch any public URL and return a clean, readable markdown or JSON extract for AI agents. Pass the target as ?url=<encoded>. Ideal when you need to read webpages, docs, or articles without a browser. Blocks script/style tags, normalizes links and images, strips HTML.Livechecked Evidence 1/4x402x402 Bazaar4 payers
- agent-web-readerx402.charliemorrison.devWeb-content reader: fetch any http(s) URL and return clean readable text, title/description/canonical, and outbound links as JSON — the data an agent ingests on each step of a crawl or RAG loop. Input: url.Livechecked Evidence 1/4x402x402 Bazaar4 payers
- vps.phoneagent.xyz/catalogvps.phoneagent.xyzVpsAgent — rent disposable VPS compute via x402, no signup required. Two product lines: ephemeral sandboxes (1h / 6h / 24h, 1 vCPU / 1 GB RAM / 25 GB SSD, $0.50–$5.00) for code execution, CI runs, browser automation; persistent servers (small / medium / large, 30-day or 365-day, $14.99–$449.99) with 4–8 vCPU / 8–24 GB RAM / 100–300 GB SSD, 200–600 Mbit/s unmetered for hosting agents, services, dev environments. Deployable in 9 regions — EU is the default and free; other regions add $3–$18/moLivechecked Evidence 1/4x402x402 Bazaar4 payers
- Scrapling x402 Data Storescraplingdata.xyzAny web page as clean, LLM-ready Markdown with boilerplate stripped, plus JSON-LD, tables and links; live fetch. REQUIRED: url (e.g. GET /v1/scrape?url=https://example.com&tier=static_scrape, or POST JSON {"url":...}). Optional tier: auto|cached_intel|static_scrape|stealth_browser. Price $0.001-$0.025 by tier ($0.005 typical); no charge on failureLivechecked Evidence 1/4x402x402 Bazaar4 payers2 more from scraplingdata.xyz
- VIA API Comparevia-router.floot.appCompare APIs and software services for a task (PDF text extraction, OCR, web scraping, weather, email, translation). Returns one recommendation plus up to three alternatives with prices. Pay per request in USDC on Base, no account or API key.Livechecked Evidence 1/4x402x402 Bazaar4 payers1 more from floot.app
- Read Web Page as Textweb.tollkit.devRead any web page as clean text: give a URL, get the visible text rendered in a real browser, with the title and final URL. For scraping, RAG and research.Livechecked Evidence 1/4x402x402 Bazaar3 payers3 more from tollkit.dev
- publish.sornkan.com/renderpublish.sornkan.comRender any public URL in a real browser (Chromium): markdown text plus screenshot and evidence URLs. $0.005 USDC on Base per call.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- MimirAPImimirapi.comDeterministic 1200x630 social-card SVG from a title and optional subtitle, dark or light theme. Same input, byte-identical output — an agent building pages gets an Open Graph image in one call with no headless browser and no font pipeline.Livechecked Evidence 1/4x402x402 Bazaar3 payers1 more from mimirapi.com
- Web Page to Markdownapi.stablecoingateways.comWeb page to markdown: give a public URL, get its main content as clean Markdown for LLMs (navigation, footers and scripts removed) with title, canonical URL, language, publish date and links. Use when an agent needs to read, quote or summarise a page. Respects robots.txt, ai.txt and noai; no paywall bypass; refusals are not charged. Signed receipt.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- skill-auditeltociear-skill-audit.hf.spaceAudit text for malicious AI-skill patterns. Requires `content`. Nothing to audit — crawling, or discovering this endpoint cold? POST /audit/registry runs the same scanner over the newest servers in the official MCP registry: no input required, $0.005.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- agentx.sale/x402/agent-cardagentx.saleSite Agent-Readiness Verdict Card: grade a domain's agent-facing files (llms.txt, A2A, MCP card, OpenAPI), TLS, headers and AI-crawler policyLivechecked Evidence 1/4x402x402 Bazaar3 payers1 more from agentx.sale
- Website technology detectorapi.vextorium.comDetect the technologies behind a website: CMS (WordPress, Shopify...), frameworks (Next.js, React...), server and CDN, analytics, payments, chat, cookie manager, captcha and fonts, from HTML and headers. For lead generation and competitive research.Livechecked Evidence 1/4x402x402 Bazaar3 payers5 more from vextorium.com
- fetchdelta.com/api/resolvefetchdelta.comFetchDelta: fetch one public web page as Markdown with title, headings, links and source timestamp. Use for current docs, changelogs or policy text. HTML only; no JavaScript rendering or login. Preview source readability for free before paying.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- agentdata-api.sander-van-aard.workers.dev/web/crawlagentdata-api.sander-van-aard.workers.devCrawl one site in one paid call: start URL + max_pages (2-20); we follow same-host links breadth-first, returning each page as clean markdown (same extraction as /web/contents). Priced at $0.002 per requested page, quoted as max_pages up front — finding fewer pages is still a complete delivery. Failed pages are skipped and listed in skipped[]; the call still settles. Only an unreadable start page is a 400, no charge. USDC on Base, no account, no API key.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- Forest Webhttp--forest-gas-station-mainnet--lcjl27p8lmjs.code.runDiscover machine-readable integration documentation from a public developer/docs page: llms.txt, Markdown alternates, API/auth docs, OpenAPI or Swagger specifications, and MCP candidates. Candidates are returned only after bounded verification. Maximum 10 HTTP requests; no JavaScript, recursive crawl or authenticated content. Base mainnet USDCLivechecked Evidence 1/4x402x402 Bazaar3 payers
- archtools.dev/v1/tools/browser-taskarchtools.devFetch a public page and extract its text or HTML, optionally by CSS selector (static HTML only: no JavaScript, clicking or typing). Pay per call with USDC (x402) or credits - archtools.devLivechecked Evidence 1/4x402x402 Bazaar3 payers2 more from archtools.dev
- windtrapdata.dev/v1/arbitrage/snapshotwindtrapdata.devCached developer documentation and API reference Markdown scraper ($0.002 USDC) — Fast L1/R2 cached documentation and webpage Markdown extraction.Livechecked Evidence 1/4x402x402 Bazaar3 payers1 more from windtrapdata.dev
- Actor, API & Scraper Monitordatasourcepulse.comCatch drift when everything still looks green. Check available Apify Actor run history and sampled output for schema drift and unexpected empty results. Additional checks cover HTTP responses, credential validity and available quota. One paid call returns a timestamped verdict and supporting details. A successful run or valid credential does not guarantee useful data. This endpoint checks once; it does not send alerts.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- Context Relaycontext-relay.contextrelay.workers.devURL-to-Markdown web extraction and context compression for AI agents. Fetch a public web page and return clean, task-relevant, citation-verifiable LLM context with exact excerpts, locators, hashes, and estimated tokens saved. Use before an agent summarizes, answers questions from, or cites a long or noisy URL. Deterministic and model-free. Public HTML only; no PDFs, logins, or JavaScript-only pages.Livechecked Evidence 1/4x402x402 Bazaar3 payers