{"uid":"cap_4GQL3uB6ec2OLZB2_aXGC","slug":"vaaya-image-ocr-via-google-lens-2186ab15","name":"Vaaya Image OCR via Google Lens","description":"Text in an image `url` via Google Lens: paragraph, sentence and word-level detections with bounding boxes. Optional `language`. Cheap OCR for screenshots, receipts, signs, slides.","url":"https://vaaya.ai/api/run/openwebninja/image-ocr?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["url"],"properties":{"url":{"type":"string","format":"uri","maxLength":2000},"language":{"type":"string","maxLength":5,"minLength":2}},"additionalProperties":true},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"pathParams":{"type":"object"}},"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":"registry","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_iqXLw8YS1h5UsbXT3P01X","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text from an image URL using Google Lens, returning paragraph, sentence, and word-level detections with bounding boxes.","exampleAgentPrompt":"Can you extract all the text from this screenshot — https://example.com/screenshot.png — and give me the words with their positions in the image?","exampleUseCases":[{"title":"Receipt text extraction for expense tracking","prompt":"I have a photo of a receipt at https://example.com/receipt.jpg — can you pull out all the text from it, including the line items and totals, so I can log it as an expense?"},{"title":"Slide content extraction for note-taking","prompt":"Here's a link to a screenshot of a presentation slide: https://example.com/slide.png — please read all the text off it so I can add it to my notes."},{"title":"Street sign reading for location context","prompt":"I've got an image of a street sign at https://example.com/sign.jpg — can you tell me what text is on it, ideally with word positions?"}],"resultDescription":"Returns structured text detections from the image, organized at paragraph, sentence, and word levels, each accompanied by bounding box coordinates indicating their location within the image.","failureModes":["Invalid or inaccessible image URL returns an error (image must be publicly reachable)","Unsupported image format may yield no detections","Image with no discernible text returns empty detection arrays","Language hint mismatch may reduce accuracy for non-Latin scripts","Very low-resolution or heavily distorted images may produce incomplete or garbled text"],"whenToPreferThis":"Choose this endpoint when you need cheap, fast OCR with spatial layout information (bounding boxes at word/sentence/paragraph level) from a publicly accessible image URL. It is particularly well-suited for screenshots, receipts, signs, and slides where positional context matters. Prefer it over generic OCR tools when you need Google Lens-grade recognition quality via a simple pay-per-call API without managing your own vision infrastructure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-17T06:42:18.465Z","isFirstParty":false,"canonicalSlug":"vaaya-image-ocr-via-google-lens-2186ab15"}