{"uid":"cap_-WLlC1T0VOJqBJ4AZa0s7","slug":"tanod-docs-ocr-ec5f16b2","name":"Tanod Docs OCR","description":"Documents: DOCX template fill, Office to PDF, any file to Markdown, PDF to Word, OCR, PDF pipeline.","url":"https://docs.tanod.dev/v1/ocr?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","maxLength":2048,"description":"Public http(s) URL of a PNG, JPEG, WebP, GIF (first frame) or single-page TIFF image (at most 10 MB and 40 megapixels)."},"lang":{"type":"string","default":"eng","pattern":"^[a-z][a-z_]{1,15}(\\+[a-z][a-z_]{1,15}){0,2}$","maxLength":50,"minLength":3,"description":"Tesseract language code (installed: eng)."}}},"responseSchema":{"type":"json","example":{"url":"https://tesseract-ocr.github.io/tessdoc/images/eurotext.png","lang":"eng","text":"The (quick) [brown] {fox} jumps!\nOver the $43,456.78 <lazy> #90 dog\n& duck/goose, as 12.5% of E-mail\nfrom aspammer@website.com is spam. ...","width":640,"words":66,"format":"png","height":500,"final_url":"https://tesseract-ocr.github.io/tessdoc/images/eurotext.png","truncated":false,"confidence_mean":90.2,"untrusted_content":true}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0025","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":"$0.0025/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Xm_amv8M1ppeF_d7tJsoN","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0025","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text from an image URL using Tesseract OCR, returning the recognized text, confidence score, and metadata.","exampleAgentPrompt":"Can you extract all the text from this image — https://example.com/scanned-receipt.png — using English OCR and tell me the confidence score?","exampleUseCases":[{"title":"Digitizing scanned invoice text","prompt":"I have a scanned invoice image at https://example.com/invoice.png — can you run OCR on it in English and give me all the text so I can process it programmatically?"},{"title":"Extracting text from a screenshot","prompt":"Please pull all the text out of this screenshot I uploaded to https://cdn.mysite.com/screenshot.jpg — I need the raw text so I can search through it."},{"title":"Reading printed form fields","prompt":"There's a filled-out paper form at https://storage.example.com/form-scan.png — can you OCR it in English and return the recognized text along with how confident the OCR engine was?"}],"resultDescription":"Returns a JSON object containing the extracted text string, image dimensions (width/height), number of recognized words, image format, the final resolved URL, a boolean indicating whether the output was truncated, mean OCR confidence score (0–100), and an untrusted_content flag.","failureModes":["Image URL is not publicly accessible or returns a non-200 response","Image exceeds 10 MB or 40 megapixel limit — likely 4xx error","Unsupported image format (e.g. multi-page TIFF, SVG, PDF) — will fail","Requested language code not installed (only 'eng' is listed as installed)","Low confidence result when image quality is poor or text is handwritten","Network timeout fetching the remote image URL"],"whenToPreferThis":"Choose this endpoint when you need to extract machine-readable text from a raster image (PNG, JPEG, WebP, GIF, single-page TIFF) hosted at a public URL. It is ideal for processing scanned documents, receipts, screenshots, or printed forms where Tesseract OCR accuracy (confidence score included) is sufficient. It is distinct from full PDF pipelines or multi-page document workflows available on the same platform.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:46:09.744Z","isFirstParty":false,"canonicalSlug":"tanod-docs-ocr-ec5f16b2"}