{"uid":"cap_SG_qi2CMC9HLckiS4K7_z","slug":"hydratrader-document-extract-31b9401d","name":"HydraTrader Document Extract","description":"Extract fields from a PDF or long document into JSON matching your schema. Every returned field carries a source quote and page number, checked against the document text; fields whose quote isn't found are dropped, not guessed. Input: public PDF/HTML URL or pasted text, up to 40 pages. Use for invoices, spec sheets, RFPs, filings. Not for scanned/image PDFs (no OCR), login/paywalled sources, or financial/legal advice. Errors aren't charged. No API key.","url":"https://x402.hydratrader.ai/v1/document-extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"pages":{"type":"string","description":"Optional PDF page selection like '1-20,25' (≤40 pages; required when the PDF has >40 pages)"},"schema":{"type":"object","description":"JSON Schema (type=object) for the record you want; 1–40 top-level properties; nested objects/arrays allowed"},"source":{"type":"object","required":["type"],"properties":{"url":{"type":"string","pattern":"^https?://","description":"Public http(s) PDF, HTML or text URL (type=public_url); ≤10 MB"},"text":{"type":"string","maxLength":160000,"description":"Pasted document text (type=text)"},"type":{"enum":["text","public_url"],"type":"string"}}},"client_ref":{"type":"string"},"instructions":{"type":"string","maxLength":1000,"description":"Optional formatting hints (e.g. 'amounts in USD')"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.3","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":"$0.3/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.3","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.3","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_a7w-5sGnN7hVnALv5WNpF","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.3","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts structured JSON fields from a PDF or document into a caller-defined schema, returning each field with a verified source quote and page number","exampleAgentPrompt":"Pull these fields from this annual report PDF at https://example.com/annual-report-2024.pdf — company name, total revenue, net income, CEO name, and headquarters address — and give me a verified quote and page number for each field.","exampleUseCases":[{"title":"Extract fields from 10-K filing","prompt":"I need you to extract the following fields from this SEC 10-K filing at https://sec.gov/files/company-10k.pdf into structured JSON: company name, fiscal year, total revenue, operating income, total assets, and risk factors summary. Include the exact source quote and page number for each field."},{"title":"Parse contract key terms","prompt":"Can you pull the key terms out of this contract PDF at https://example.com/contract.pdf? I want: party names, effective date, contract value, termination clauses, and governing law — all with the exact quote and page number from the document so I can verify each one."},{"title":"Structure research paper metadata","prompt":"Extract the following fields from this research paper PDF at https://arxiv.org/pdf/2401.12345.pdf: title, authors, abstract, methodology summary, dataset used, and main findings. Return each field with the exact quote and page number it came from."}],"resultDescription":"A JSON object matching the caller's provided schema, where each top-level field is populated with the extracted value plus a source_quote (verbatim text from the document) and page_number indicating where the value was found. Fields that cannot be located return null with an appropriate note.","failureModes":["PDF is scanned/image-only (no text layer) — OCR not supported, returns error","Source URL requires login, paywall, or authentication — cannot access, returns error","Document exceeds 40 pages and no page range is specified — returns validation error","Schema has more than 40 top-level properties — rejected","URL is not publicly accessible or times out — returns fetch error","Pasted text exceeds 160,000 character limit — returns validation error","Requested fields are not present in the document — fields return null","PDF is malformed or corrupted — returns parse error"],"whenToPreferThis":"Choose this endpoint when you need to extract specific, named fields from a text-based PDF or document and require verifiable source citations (quote + page number) for each extracted value. It is ideal for compliance, auditing, legal, or research workflows where traceability matters. Prefer it over generic LLM extraction when you need a structured JSON schema output with provenance. Not suitable for scanned/image PDFs, documents behind authentication, or sources requiring OCR.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T12:30:09.802Z","isFirstParty":false,"canonicalSlug":"hydratrader-document-extract-31b9401d"}