{"slug":"x402-agent-tools-nerolabs-workers-dev-ocr-8c4ac6","title":"Reads the text in images (PNG, JPEG, WebP, TIFF and more) and scanned or born-di","host":"x402-agent-tools.nerolabs.workers.dev","method":"POST","resource":"https://x402-agent-tools.nerolabs.workers.dev/ocr","category":"image","description":"Reads the text in images (PNG, JPEG, WebP, TIFF and more) and scanned or born-digital PDFs with OCR, in 100+ languages, and returns the text per file and per page with confidence scores. Up to 10 files a call. Priced per page allowance: files x maxPagesPerFile (default 5, at most 20) x $0.005. Runs ","price_listed":0.005,"price_asked":0.005,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":38,"reported_calls_30d":0,"reported_payers_30d":0,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"fileUrls":["https://nerolabs-samples.nerolabs.workers.dev/sample-receipt.png"],"maxPagesPerFile":1},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"dpi":{"default":200,"description":"Resolution used to render PDF pages before recognition. 200 suits most scans; 300 helps small print and takes about twice as long; 150 is faster for large clean type. Images are used at their own resolution, enlarged when small and capped at 4000 pixels on the longest side.","maximum":400,"minimum":100,"type":"integer"},"fileUrls":{"description":"A plain list of image (PNG, JPEG, WebP, GIF, BMP, TIFF) or PDF links, for a quick one-off run with no spreadsheet. Use the dataset, file or Google Sheet inputs above to keep your own columns alongside the results.","type":"array"},"includePageText":{"default":false,"description":"Add a 'pages' array with each page's text, method (OCR or copied text layer), confidence and word count, on top of the combined text. Useful for citing a page number, and it makes rows larger.","type":"boolean"},"languages":{"description":"Tesseract language codes, one per line, for example eng, deu, fra, spa, por, ita, nld, pol, rus, jpn, chi_sim, chi_tra, ara, hin, kor. Several codes read mixed documents. English is built in; any other language is downloaded once at the start of the run (5 to 15 MB each). Picking the right language ","type":"array"},"maxPagesPerFile":{"default":20,"description":"Pages read from each PDF before stopping. This is also your cost ceiling per file: a 300-page scan cannot run up a bill you did not expect. Images always count as one page.","maximum":500,"minimum":1,"type":"integer"},"minWordConfidence":{"default":0,"description":"Drop words the engine is less sure about than this, from 0 to 100. Leave at 0 to keep everything and judge by the reported confidence instead. Raising it cuts noise out of poor scans at the cost of real words.","maximum":100,"minimum":0,"type":"integer"},"pageSegmentation":{"default":"auto","description":"How the engine should look for text. 'Automatic' handles documents, receipts and letters. 'Sparse' finds scattered text on screenshots, slides and product photos. 'Single block' suits a cropped paragraph, 'single column' a narrow receipt, 'single line' a cropped field.","enum":["auto","sparse","single_block","single_column","single_line"],"type":"string"},"usePdfTextLayer":{"default":true,"description":"A born-digital PDF page already contains its text. When this is on, such pages are copied exactly and charged at the low text-layer rate instead of being rendered and recognised. Turn it off to force OCR on every page, for example when a PDF's text layer is known to be garbage.","type":"boolean"}},"required":["fileUrls"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-21","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.005,"price_match":true,"latency_ms":38,"error":null}],"description_full":"Reads the text in images (PNG, JPEG, WebP, TIFF and more) and scanned or born-digital PDFs with OCR, in 100+ languages, and returns the text per file and per page with confidence scores. Up to 10 files a call. Priced per page allowance: files x maxPagesPerFile (default 5, at most 20) x $0.005. Runs nerolabs/bulk-ocr-image-pdf-to-text; can take a minute or two.","last_updated":"2026-10-21T14:37:43.255Z","schemes":["exact"]}