{"uid":"cap_y6o9pQPEpw5tWK87iHqrU","slug":"agentwork-pdf-text-extraction-ba251fbc","name":"AgentWork PDF Text Extraction","description":"PDF text extraction — extract text from a public digital PDF into page-numbered JSON for RAG (no OCR). $0.01 USDC Base or Algorand. Caps 20 pages / 5 MiB / 100k chars; source + text SHA-256. No passwords or table reconstruction. Failed extractions not settled.","url":"https://api.agentwork.run/v1/pdf/read?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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","required":["url"],"properties":{"url":{"type":"string","description":"Public HTTP/HTTPS URL (URL-encoded)"}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"ok":true,"text":"Dummy PDF file","pages":[{"page":1,"text":"Dummy PDF file","characters":14}],"warnings":["Embedded text only; images and table structure are not extracted."],"page_count":1,"ocr_performed":false}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_D6Y1_yvDUWrmSzsfuvMGJ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts embedded text from a public PDF URL into page-numbered JSON, including SHA-256 hashes and warnings, for RAG pipelines and document ingestion.","exampleAgentPrompt":"Can you extract all the text from this PDF — https://example.com/report.pdf — and give it back to me organized by page number so I can index it for search?","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"I need to ingest this public PDF into my RAG system — can you pull out all the embedded text from https://arxiv.org/pdf/2301.00001.pdf and return it organized by page so I can chunk and embed it?"},{"title":"Research paper content extraction","prompt":"Can you read the full text of this research paper PDF at https://example.com/whitepaper.pdf and give me all the content page by page, including any warnings if some pages are empty?"},{"title":"Contract text retrieval for analysis","prompt":"I have a contract at https://company.com/contracts/agreement.pdf — please extract all the text from it with page numbers so I can search through the clauses."}],"resultDescription":"A JSON object with ok status, the full extracted text as a single string, an array of page objects each containing page number, page text, and character count, plus page_count, ocr_performed flag (always false), source and text SHA-256 hashes, and a warnings array flagging empty pages or truncation if the document exceeds 20 pages, 5 MiB, or 100,000 characters.","failureModes":["PDF is password-protected — extraction fails and no charge is made","URL is not publicly accessible or requires authentication — request rejected","PDF contains only scanned images with no embedded text — returns empty or near-empty pages with warnings","Document exceeds 20 pages, 5 MiB, or 100,000 characters — content is truncated with a warning","URL points to a non-PDF resource — extraction fails","Network timeout or unreachable URL — extraction fails with no settlement"],"whenToPreferThis":"Choose this endpoint when you need reliable, page-numbered plain-text extraction from a digitally-created (not scanned) public PDF for downstream RAG, search indexing, or document analysis. It is ideal when you need SHA-256 hashes for deduplication or change detection, and when you do not need OCR, table reconstruction, or image understanding. Prefer this over general web scrapers when your source is specifically a PDF file.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T06:43:28.890Z","isFirstParty":false,"canonicalSlug":"agentwork-pdf-text-extraction-ba251fbc"}