{"uid":"cap_HGfQX9sMK16VrFMW6R5jW","slug":"visual-api-pdf-ocr-text-extraction-c00bb9d5","name":"Visual API – PDF OCR & Text Extraction","description":"OCR extraction from scanned PDF documents (English). Uses Tesseract to read text from image-based pages that have no embedded text layer. Returns structured text and metadata. Ideal for invoices, receipts, contracts, and legacy documents. $0.05 per extraction.","url":"https://visual.hugen.tokyo/visual/ocr","method":"GET","headers":{},"bodySchema":{"properties":{"input":{"required":["method"]}}},"responseSchema":{"type":"json","example":{"metadata":{"page_count":3,"file_size_bytes":1548290},"summary_stats":{"has_text":true,"ocr_pages":3,"total_characters":2840}}},"example":{"request":{"url":"https://example.com","max_pages":1},"response":{"pages":[{"page":1,"text":"Example\nDomain\nThis domain\nis for use in\ndocumentation\nexamples\nwithout\nneeding\npermission.\nAvoid use in\noperations.\nLearn more","char_count":127}],"metadata":{"title":"Example Domain","author":"","creator":"","subject":"","producer":"","page_count":1,"file_size_bytes":559,"pages_extracted":1},"extracted_at":"2026-06-12T04:44:15Z","summary_stats":{"has_text":true,"ocr_pages":0,"total_tables":0,"total_characters":127}}},"exampleRequest":{"url":"https://example.com","max_pages":1},"tags":["x402"],"displayCostAmount":"0.05","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":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_-W5aN0f4E6Yz-YmdutKfa","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text and metadata from a PDF at a given URL using OCR, returning page count, character count, and parsed content.","exampleAgentPrompt":"Extract all the text from this PDF — https://example.com/report.pdf — and give me the page count and total character count, checking up to 100 pages.","exampleUseCases":null,"resultDescription":"Returns a JSON object with metadata (page_count, file_size_bytes), summary_stats (has_text boolean, ocr_pages count, total_characters count), and the extracted text content from the PDF.","failureModes":["URL is not a valid or accessible PDF — returns error or empty result","PDF exceeds max_pages limit causing partial extraction","Scanned PDF with no detectable text returns has_text: false with zero characters","Network timeout reaching the provided PDF URL","PDF is password-protected or encrypted and cannot be parsed"],"whenToPreferThis":"Use this endpoint when you need to extract text from a PDF available at a public URL without setting up any browser or document-processing infrastructure. It is especially useful for scanned PDFs requiring OCR. Prefer it over screenshot endpoints when the goal is textual content extraction rather than visual capture.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:41:01.089Z","isFirstParty":false}