{"uid":"cap_YWowkOrm1j83QYk6Earbf","slug":"workbot1-oddsys-org-high-page-count-ocr-deep-f5876530","name":"workbot1.oddsys.org High-Page-Count OCR (Deep)","description":"High-page-count OCR: scanned PDF into clean text (Tesseract, English, machine-printed documents), up to 100 pages per call — four times the /ocr cap. Runs under a 240s wall-clock budget; slower documents return the completed pages with truncatedReason \"time-budget\". Text-layer PDFs are extracted the fast way at the same price.","url":"https://workbot1.oddsys.org/ocr-deep?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"maxPages":{"type":"number","description":"Pages to OCR from the start of the document (1-100, default: all up to 100)."},"pdfBase64":{"type":"string","description":"Base64-encoded PDF file (scanned/image PDFs; machine-printed text, English)."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.03","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_CNTuEfH6sybCnwlTTEO7z","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Performs OCR on scanned PDFs up to 100 pages using Tesseract (English, machine-printed), with a 240-second time budget and graceful partial-result truncation.","exampleAgentPrompt":"Can you OCR this 80-page scanned PDF for me and give me the clean extracted text? It's a machine-printed English document.","exampleUseCases":[{"title":"Digitizing a scanned legal contract","prompt":"I have a 90-page scanned legal contract in PDF format — can you run OCR on it and extract all the text so I can search through it?"},{"title":"Archiving old printed reports","prompt":"I've got a stack of scanned annual reports from the 1990s compiled into a single 75-page PDF. Can you extract the text from all of them so I can index and search the content?"},{"title":"Processing a scanned academic thesis","prompt":"Please extract the text from this 100-page scanned PhD thesis PDF — it's printed English text and I need the full content in plain text form."}],"resultDescription":"Returns clean extracted text for each successfully processed page. If the 240-second time budget is exhausted before all pages are done, returns the completed pages alongside a truncatedReason field set to 'time-budget'. Text-layer PDFs bypass OCR and are extracted directly at the same price.","failureModes":["Time budget exceeded (240s): partial result returned with truncatedReason='time-budget'","PDF exceeds 100-page limit: request rejected","Non-English or handwritten documents: poor OCR accuracy","Corrupted or password-protected PDF: processing failure","Image quality too low for Tesseract to reliably extract text"],"whenToPreferThis":"Choose this endpoint when you need to OCR more than 25 pages per call (up to 100) and can tolerate a longer processing window (up to 240 seconds). Prefer this over the standard /ocr endpoint for large documents. Use the standard /ocr endpoint for smaller documents where speed matters more. For PDFs with an existing text layer, this endpoint still works efficiently by bypassing OCR.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T00:31:31.848Z","isFirstParty":false,"canonicalSlug":"workbot1-oddsys-org-high-page-count-ocr-deep-f5876530"}