ClawFetch

Endpoints (8 live)

• POST /parse — Document parsing: convert office documents (docx, pptx, xlsx, pdf, odt, ods, odp, rtf, epub, csv, doc, ppt) to clean GitHub-Flavored Markdown. Pass a document URL or base64-encoded bytes. Deterministic local Rust converter (Firecrawl anydoc) — fast, typed structure preserved (headings, tables, lists), no OCR for scanned/image-only PDFs. (0.005 USDC on Base)
• POST /extract — Structured data extraction returning typed JSON from 17 specialized site extractors: Twitter/X, GitHub, CoinGecko, Hacker News, YouTube, Wikipedia, npm, PyPI, crates.io, Product Hunt, IMDb, Amazon, Crunchbase, SEC EDGAR, Zillow, Redfin, and news articles. Auto-detects the right extractor from the URL — no scraping selectors required. (0.008 USDC on Base)
• POST /research — Multi-source web research and company/topic intelligence: runs a live web search, visits the top sources, and returns ranked results with titles, URLs, and content snippets. One call replaces a search-then-scrape pipeline for deep research agents. (0.02 USDC on Base)
• POST /domains/suggest — Domain name brainstorming and availability screening: combine keywords into candidate domains across chosen TLDs, then live-WHOIS-check them and return only the available ones. Naming research in a single call. (0.003 USDC on Base)
• POST /domains/check — Bulk domain name availability lookup via live WHOIS: check many domains across many TLDs in one call and get a per-domain available true/false. Useful for naming, brand screening, and squatting checks. (0.003 USDC on Base)
• POST /render — Headless browser rendering for JavaScript-heavy pages and SPAs: full stealth Chromium render, then clean markdown plus title, meta description, and canonical URL. Use when a plain fetch returns an empty shell or a bot wall. (0.005 USDC on Base)
• GET /extractors — Discovery endpoint listing all 17 available structured-data extractors and the domains each one supports, so an agent can decide whether /extract can handle a given URL before paying for it. (0.001 USDC on Base)
• POST /fetch — Web scraping / URL fetch: retrieve any web page and return clean, LLM-ready markdown text. Strips boilerplate, ads, and navigation. Stealth HTTP client bypasses common bot blocks. Cheapest way to read a webpage. (0.001 USDC on Base)