{"uid":"cap_xh0O3yuALFoHrDJrDNe1F","slug":"visual-hugen-tokyo-3a41e326","name":"PDF Parser & Table Extractor","description":"Extract structured text, tables, and metadata from any PDF URL. Returns page-by-page text content, detected tables as JSON arrays, and document metadata (title, author, page count). No PDF library or OCR setup needed — pay per extraction. AI agent API for document intelligence and data extraction","url":"https://visual.hugen.tokyo/visual/parse","method":"GET","headers":{},"bodySchema":{"properties":{"input":{"required":["method"]}}},"responseSchema":{"type":"json","example":{"metadata":{"title":"Q1 2026 Financial Report","page_count":12,"file_size_bytes":284672},"summary_stats":{"has_text":true,"total_tables":3,"total_characters":18420}}},"example":{"request":{"url":"https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf","max_pages":1},"response":{"pages":[{"page":1,"text":"Dummy PDF file","char_count":14}],"metadata":{"title":"","author":"Evangelos Vlachogiannis","creator":"Writer","subject":"","producer":"OpenOffice.org 2.1","page_count":1,"file_size_bytes":13264,"pages_extracted":1},"extracted_at":"2026-05-29T22:39:26Z","summary_stats":{"has_text":true,"total_tables":0,"total_characters":14}}},"exampleRequest":{"url":"https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf","max_pages":1},"tags":["x402"],"displayCostAmount":"0.02","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JixvJUwSwSrDHWShFWozy","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts structured text, tables as JSON arrays, and metadata from any PDF URL on a pay-per-use basis","exampleAgentPrompt":"Can you extract all the text and any tables from this PDF — https://example.com/annual-report-2024.pdf — and give me the document metadata like title, author, and page count?","exampleUseCases":null,"resultDescription":"Returns page-by-page text content, all detected tables as JSON arrays (rows and columns), and document metadata including title, author, and total page count — all structured and ready to use programmatically.","failureModes":["Invalid or inaccessible PDF URL returns an error","Password-protected PDFs cannot be parsed","Very large PDFs may time out","Non-PDF URLs will fail or return unexpected results","Scanned image-only PDFs may yield empty text if no OCR is performed"],"whenToPreferThis":"Use this endpoint when you need to extract structured content from a PDF hosted at a public URL without setting up any local PDF libraries, OCR infrastructure, or browser automation. Ideal for document intelligence pipelines, data extraction from reports, invoices, research papers, or any PDF with tabular data.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:31:52.748Z","isFirstParty":false}