{"uid":"cap_PKDufD9xLr5ryIIKc4l0S","slug":"api-x402node-dev-d52cd9a6","name":"PDF Extract — Page-Level Text & Metadata","description":"pdf parser, pdf to structured json, pdf page extractor, pdf chunker, pdf RAG indexer, pdf document parser. Extract structured text from any PDF URL with page-level chunks and metadata. Returns per-page text array, char counts, info dict (title, author, creator, dates). For AI agents doing document QA, RAG indexing, contract analysis, citation extraction. Accepts payment on Base or Solana — either network works.","url":"https://api.x402node.dev/pdf/extract","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","properties":{"url":{"type":"string","description":"Target URL (optional)"}}}},"additionalProperties":false}}},"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_LHcxBuNVHpOJWiHeiFl7v","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":"Extracts structured text from a PDF URL, returning per-page text chunks with character counts and document metadata (title, author, creator, dates)","exampleAgentPrompt":"Can you extract all the text from this PDF — https://example.com/contract.pdf — and give me the content broken out page by page along with the document title, author, and creation date?","exampleUseCases":null,"resultDescription":"Returns a JSON object with a per-page text array (one entry per page), character count per page, total page count, and an info dictionary containing document metadata fields such as title, author, creator, creation date, and modification date.","failureModes":["PDF URL is unreachable or returns a non-200 status — endpoint returns an error indicating the fetch failed","URL points to a non-PDF resource — parser fails and returns an error","Password-protected or encrypted PDF — text extraction fails or returns empty pages","Scanned/image-only PDF — returns empty text per page since OCR is not performed","Malformed or corrupted PDF — parser may return partial results or an error"],"whenToPreferThis":"Use this endpoint when you need page-level granularity from a PDF for RAG indexing, document QA, contract analysis, or citation extraction. It is ideal when precise context-window management matters and you need both content and document metadata in a single call. Prefer this over generic web scrapers when the input is specifically a PDF URL and structured per-page output is required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:58:29.829Z","isFirstParty":false}