{"uid":"cap_uDMLTVaPlmG82qNL7T2uC","slug":"quant-agent-shop-ocr-130ca9d4","name":"Quant Agent Shop OCR","description":"Image text (OCR). Send an image URL or base64 (PNG, JPEG, WebP or GIF, up to 5 MB and 8000 px a side); returns the text in reading order, one line per line, and with layout on, where each line sits in the image, plus truncated when the text ran past the reply limit. Use for screenshots, receipts, signs and scanned pages. Not for PDFs that have a text layer (use /v1/pdf-text) or for describing pictures. Typical response 2 to 6 s. Failed calls are not charged.","url":"https://quantagentshop.com/v1/ocr?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","properties":{"layout":{"type":"boolean","title":"Layout","default":false,"description":"Also return each line with where it sits in the image, such as top-left."},"image_url":{"anyOf":[{"type":"string","format":"uri","maxLength":2083,"minLength":1},{"type":"null"}],"title":"Image Url","default":null,"description":"Public http or https URL of a PNG, JPEG, WebP or GIF image."},"image_base64":{"anyOf":[{"type":"string","maxLength":6900000,"minLength":8},{"type":"null"}],"title":"Image Base64","default":null,"description":"The image as base64, up to 5 MB decoded. Send image_url or image_base64."}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vl6nIHYhRCO6S3aIl-Ir6","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text from images (PNG, JPEG, WebP, GIF) via URL or base64, returning text in reading order with optional layout coordinates","exampleAgentPrompt":"Can you read all the text out of this receipt image for me? Here's the URL: https://example.com/receipt.jpg — and I'd also like to know where each line sits in the image.","exampleUseCases":[{"title":"Digitize printed receipt","prompt":"I've got a photo of a restaurant receipt at https://example.com/receipt.jpg — can you extract all the text from it, including the line items and totals, and tell me where each line appears in the image?"},{"title":"Read text from street sign photo","prompt":"Here's a base64-encoded JPEG of a street sign I photographed — can you pull out all the text you can see in it?"},{"title":"Transcribe scanned form","prompt":"I have a scanned form image at https://example.com/form_scan.png — please extract all the text from it in reading order so I can process the fields programmatically."}],"resultDescription":"Returns the extracted text in reading order, one line per line. When the layout option is enabled, each line also includes its position within the image (e.g. top-left coordinates or region). A truncation flag is included if the text exceeded the reply limit. Failed calls are not charged.","failureModes":["Image URL is not publicly accessible or returns a non-200 response","Image format not supported (only PNG, JPEG, WebP, GIF accepted)","Image exceeds 5 MB or 8000 px per side","No text detected in the image (blank or purely graphical image)","Base64 payload malformed or exceeds size limit","Text output truncated if image contains very large amount of text"],"whenToPreferThis":"Use this endpoint when you need to extract text from raster image files (PNG, JPEG, WebP, GIF). Prefer this over /v1/pdf-text when the input is an image rather than a PDF, or when the PDF lacks a text layer (i.e. it is a scanned image PDF). Do not use this for describing image contents visually or for PDFs with embedded text layers.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T12:43:21.741Z","isFirstParty":false,"canonicalSlug":"quant-agent-shop-ocr-130ca9d4"}