{"uid":"cap_wTGpHRMLSn28UYsApfHfW","slug":"x402-orthogonal-scrapegraphai-extract-f70d2a25","name":"x402 Orthogonal ScrapeGraphAI Extract","description":"LLM-driven extraction from a URL, HTML, or markdown input with a prompt and optional JSON schema.","url":"https://x402.orthogonal.com/scrapegraphai/api/extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"URL to extract from"},"html":{"type":"string","description":"Raw HTML to extract from"},"mode":{"type":"string","description":"Content mode: normal, reader, or prune"},"prompt":{"type":"string","description":"Extraction prompt (1-10000 chars)"},"schema":{"type":"object","description":"JSON schema for structured output"},"markdown":{"type":"string","description":"Markdown to extract from"},"contentType":{"type":"string","description":"Force content type"},"fetchConfig":{"type":"object","description":"Fetch options: mode, stealth, timeout, wait, headers, cookies, country, scrolls"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.025","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.025/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.025","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.025","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vEKBWp7DuqFhySaO_DeNg","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.025","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"LLM-driven structured data extraction from a URL, raw HTML, or markdown using a natural language prompt and optional JSON schema.","exampleAgentPrompt":"Go to https://www.ycombinator.com/companies and extract a list of company names, one-line descriptions, and website URLs — use reader mode and return the results as structured JSON with fields: name, description, url.","exampleUseCases":[{"title":"Extract product specs from e-commerce page","prompt":"Scrape https://www.bhphotovideo.com/c/product/1234567/sony_a7iv.html and extract the product name, price, key specs, and availability into structured JSON — use reader mode to clean up the page first."},{"title":"Parse job listings from a careers page","prompt":"Extract all job listings from https://stripe.com/jobs/search into a JSON array with fields: title, location, team, and url — use the page's HTML and give me structured output."},{"title":"Pull article metadata from news site","prompt":"From this HTML I'm giving you, extract the article title, author, publish date, summary, and tags — here's the raw HTML: <html>...</html> — return it as structured JSON matching this schema: {title: string, author: string, date: string, summary: string, tags: array}."}],"resultDescription":"Returns structured JSON containing the fields extracted from the source content (URL, HTML, or markdown) as guided by the prompt and optional JSON schema. When a schema is provided, the output conforms to that schema. Without a schema, the LLM determines the output structure based on the prompt.","failureModes":["URL is inaccessible or returns a non-200 status — extraction fails with a fetch error","Prompt is too vague — LLM returns partial or poorly structured data","No matching content found on the page for the requested fields — returns empty or null values","Rate limiting or bot detection on target site blocks fetch — returns fetch timeout or blocked error","Invalid JSON schema provided — schema validation error returned","HTML or markdown input is malformed or too large — parsing error or truncation"],"whenToPreferThis":"Choose this endpoint when you need LLM-driven, prompt-guided extraction that returns structured JSON from arbitrary web content. It is superior to raw HTML scrapers when you want semantic extraction (not just DOM parsing), and better than generic search APIs when you already have a specific page to extract from. The optional JSON schema enforcement makes it ideal for agent pipelines that require consistent output shape. Use it when you need flexibility across URL, raw HTML, and markdown inputs in a single endpoint.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-01T12:50:51.940Z","isFirstParty":false,"canonicalSlug":"x402-orthogonal-scrapegraphai-extract-f70d2a25"}