{"uid":"cap_xD6hpFoz_Haqn2fuxNqAs","slug":"document-extraction-hub-ocr-54b6daca","name":"Document Extraction Hub – OCR","description":"Read a picture, a scan or a screenshot: full text in reading order, typed blocks with their box on the page, tables as a matrix plus markdown, and every QR code and barcode with its decoded content.","url":"https://doc.halowerk.com/ocr","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","format":"uri","description":"Public http or https URL of the picture or PDF. Use this or \"image_base64\", not both."},"mime":{"enum":["image/png","image/jpeg","image/webp","application/pdf"],"type":"string","description":"Media type of the input. Checked against the actual bytes; a mismatch is refused rather than worked around."},"want":{"type":"array","items":{"enum":["text","tables","codes","layout"],"type":"string"},"default":["text","tables","codes","layout"],"description":"Which parts of the answer to compute. The price does not change with it; asking for less is simply faster."},"pages":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"integer","minimum":1}}],"description":"Optional page range for PDF input, for example \"1-5\" or \"2,4,7\". At most 50 pages per call. Not allowed for a single image."},"languages":{"type":"array","items":{"enum":["deu","eng"],"type":"string"},"default":["deu","eng"],"description":"Languages to read, default deu plus eng. Installed models: deu, eng."},"image_base64":{"type":"string","description":"The picture or PDF as base64. Use this or \"url\", not both."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.006","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":"$0.006/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.006","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_avIFQwsSulNmuseiDC3XR","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.006","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts full text, typed layout blocks with bounding boxes, tables as matrix and markdown, and decoded QR/barcodes from images, scans, screenshots, or PDFs.","exampleAgentPrompt":"Can you extract all the text, tables, and any barcodes from this scanned invoice image? Here's the URL: https://example.com/invoice-scan.jpg — it's a JPEG and I need both English and German text recognized.","exampleUseCases":[{"title":"Invoice text and table extraction","prompt":"I have a scanned invoice at https://example.com/invoice.jpg — it's a JPEG. Can you pull out all the text and any tables from it? It might have both English and German text."},{"title":"QR and barcode reading from product photo","prompt":"There's a product label image at https://example.com/product-label.png. Please decode any QR codes or barcodes on it and give me their content."},{"title":"PDF document text and layout parsing","prompt":"I've got a multi-page PDF at https://example.com/report.pdf and I need the full text in reading order plus any tables from pages 1 through 5 — the document is in English."}],"resultDescription":"Returns full text in reading order, layout blocks each with their bounding box on the page, tables as both a matrix and in markdown format, and every QR code and barcode with its decoded string content — scoped to whichever output types were requested via the 'want' parameter.","failureModes":["MIME type mismatch between declared mime and actual file bytes — request refused","URL is not publicly accessible or returns a non-200 status — fetch failure","PDF page range exceeds 50 pages per call — rejected","Both url and image_base64 supplied simultaneously — rejected","Neither url nor image_base64 supplied — rejected","Language not in installed models (only deu and eng supported) — unsupported language error","Payment not provided or invalid x402 payment — payment failure"],"whenToPreferThis":"Choose this endpoint when you need to extract structured content — text, tables, layout, or barcodes — from images or PDFs in a single call. It is especially useful when multiple output types (text + tables + barcodes) are needed simultaneously from a single document. Prefer it over generic OCR when bounding-box layout information or decoded barcode content is required alongside text. Supports both URL-based and base64 inputs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:34:57.854Z","isFirstParty":false}