{"uid":"cap_g0-tYWc_aZ9zB1kmH0cDc","slug":"well-001-extract-table-pdf-table-extractor-3dc04899","name":"well-001-extract-table PDF Table Extractor","description":"Extract tables from a PDF ($0.01 USDC via x402). Pass pdf_base64 or a https pdf_url. Optional schema maps headers. Optional max_pages (1-10). Returns JSON { pages, tables: [{ page, headers, rows }], warnings }. Text PDFs are parsed in-worker; scans require HOSTED_PARSER_URL. Provided as is, with no warranty or guarantee of accuracy or fitness. Nothing is stored.","url":"https://well-001-extract-table.mmelnyk2000.workers.dev/api/extract-table-from-pdf?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"schema":{"type":"string","description":"Optional header mapping. Object maps extracted header -> output name; array replaces headers in column order."},"pdf_url":{"type":"string","description":"https URL of a PDF. Provide this or pdf_base64. Max 8 MB."},"max_pages":{"type":"integer","description":"Max pages to read. Capped at 10."},"pdf_base64":{"type":"string","description":"Raw PDF encoded as base64 (optionally a data: URL). Provide this or pdf_url."}}},"responseSchema":{"type":"object","additionalProperties":true},"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_JJlobEu9Qpsnie0fcJybX","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 tabular data from PDF documents (text or scanned) and returns structured JSON with headers and rows, billed at $0.01 USDC per call via x402.","exampleAgentPrompt":"Can you extract all the tables from this PDF report for me? Here's the URL: https://example.com/quarterly-report.pdf — pull up to 5 pages and map the 'Item' column to 'product_name' and 'Qty' to 'quantity'.","exampleUseCases":[{"title":"Invoice line-item extraction","prompt":"I have an invoice PDF at https://example.com/invoice-2024.pdf — can you pull out the table of line items and give me the product names, quantities, and prices as structured data? Check the first 3 pages."},{"title":"Financial statement table parsing","prompt":"Here's a base64-encoded PDF of a bank statement. Extract all the transaction tables from it, mapping the 'Date' column to 'transaction_date' and 'Amount' to 'value', and scan up to 10 pages."},{"title":"Research report data extraction","prompt":"I need the data tables from this academic PDF at https://university.edu/study-results.pdf — can you extract them as JSON with headers and rows so I can analyze the numbers?"}],"resultDescription":"Returns a JSON object with: 'pages' (total pages processed), 'tables' (array of objects each containing 'page' number, 'headers' array, and 'rows' array of arrays), and 'warnings' (array of any issues encountered, e.g. scanned pages requiring hosted parser).","failureModes":["PDF URL is not HTTPS or exceeds 8 MB — request rejected","max_pages exceeds 10 — capped silently or rejected","Scanned/image-based PDF without HOSTED_PARSER_URL configured — warnings returned, no table data","Malformed base64 input — parse error returned","No tables detected in the PDF — empty tables array returned","Network timeout fetching remote PDF URL"],"whenToPreferThis":"Choose this endpoint when you need to extract tabular data from a PDF document in a single lightweight API call billed per-use at $0.01 USDC. It handles both text-based PDFs natively in-worker and supports optional header remapping for clean output schemas. Prefer it over heavyweight document processing pipelines for quick, ad-hoc table extraction tasks without storage or data retention concerns.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:32:34.842Z","isFirstParty":false,"canonicalSlug":"well-001-extract-table-pdf-table-extractor-3dc04899"}