{"uid":"cap_hadmez0q_6VAFR9ofMImd","slug":"pdf-text-and-table-extraction-ac847223","name":"PDF Text and Table Extraction","description":"Extract text and ruled tables from a PDF (10 MiB, 20 pages, no OCR).","url":"https://api.dekist42.com/v1/extract","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"pdf_base64":{"type":"string","title":"Pdf Base64","maxLength":13981016,"minLength":1,"description":"Base64 PDF bytes; maximum 10 MiB and 20 pages. No URLs."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.1","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":"$0.1/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Y6VCWqjFZfT3497YrmAnY","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.1","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts plain text and ruled tables from a PDF document (up to 10 MiB / 20 pages) without OCR","exampleAgentPrompt":"Extract all the text and any tables from this PDF — I'll send it as a base64-encoded string, it's under 10 MB and fewer than 20 pages.","exampleUseCases":[{"title":"Invoice data extraction for accounting","prompt":"I have a supplier invoice as a PDF — can you pull out all the text and table rows from it so I can process the line items? Here's the base64-encoded file."},{"title":"Research report parsing for analysis","prompt":"Extract all the text and any structured tables from this research report PDF so I can search and analyze the content — it's about 15 pages and I'll give you the base64 of the file."},{"title":"Contract clause extraction for review","prompt":"Can you pull all the text out of this legal contract PDF so I can find specific clauses? It's a standard contract, under 20 pages — here's the base64-encoded version."}],"resultDescription":"Returns extracted plain text from all pages of the PDF, along with structured table data parsed from ruled (bordered) tables found within the document. Does not perform OCR, so scanned or image-only PDFs will yield limited or no output.","failureModes":["PDF exceeds 10 MiB — request rejected","PDF exceeds 20 pages — request rejected","Empty or invalid base64 string — validation error","Scanned/image-only PDF — no text extracted (no OCR support)","Corrupt or password-protected PDF — parsing failure","Malformed PDF structure — extraction error"],"whenToPreferThis":"Choose this endpoint when you need to programmatically extract text or tabular data from a native (non-scanned) PDF with up to 10 MiB and 20 pages. It is ideal for structured documents like invoices, reports, and contracts where the PDF contains actual embedded text and ruled tables. Avoid it for scanned documents requiring OCR, very large PDFs, or when you need to extract images from the PDF.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:33:58.462Z","isFirstParty":false}