{"uid":"cap_yI9xAAtleYMetrcbwN4wl","slug":"sift-web-tools-pdf-text-extraction-f1209b0b","name":"Sift Web Tools – PDF Text Extraction","description":"Extract text from a PDF URL, page by page. Text of a PDF (up to 25 MB, first 50 pages) page by page, with document metadata and a hint when the PDF is a scan.","url":"https://sift.srv1996466.hstgr.cloud/v1/pdf?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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"PDF URL"},"max_pages":{"type":"integer","description":"Max pages (1-50, default 50)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"pages":[{"page":1,"text":"Dummy PDF file"}],"page_count":1}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.004","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":"$0.004/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.004","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.004","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_mp0bpDI0DQpcLeVoRYpdx","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.004","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts and returns the text content of a remote PDF file, page by page, as structured JSON","exampleAgentPrompt":"Pull the text from this PDF — https://example.com/report.pdf — and give me all the pages, up to 20 pages max.","exampleUseCases":[{"title":"Research paper ingestion pipeline","prompt":"Grab the full text of this academic paper PDF at https://arxiv.org/pdf/2310.12345 so I can summarize and analyze its findings."},{"title":"Contract review text extraction","prompt":"Extract all the text from the contract PDF at https://legal.example.com/contract.pdf — I need the raw text from every page so I can review the terms."},{"title":"Invoice data retrieval","prompt":"Read the text out of this invoice PDF at https://billing.acme.com/invoice-1042.pdf — just the first 5 pages — so I can pull out the line items."}],"resultDescription":"Returns a JSON object with a 'pages' array (each entry has 'page' number and 'text' string) and a 'page_count' integer reflecting the total number of pages extracted. Only pages within the requested max_pages limit are returned.","failureModes":["URL is not a valid or accessible PDF — returns error","PDF is password-protected or encrypted — text extraction fails","PDF exceeds max_pages cap (50) — only up to the limit is returned","Network timeout fetching the remote PDF — call fails and no charge is made","PDF contains only scanned images with no embedded text — returns empty page text"],"whenToPreferThis":"Use this endpoint when you have a direct URL to a PDF file and need its text content structured page-by-page. It is preferable to generic web-fetch endpoints when the target is specifically a PDF, as it handles PDF parsing natively and returns per-page structured output. The pay-per-call USDC model means you only pay $0.004 on success, making it cost-effective for occasional or on-demand PDF reading without a subscription.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T18:39:51.940Z","isFirstParty":false,"canonicalSlug":"sift-web-tools-pdf-text-extraction-f1209b0b"}