{"uid":"cap_Vf_h7TrHLpbexg-x1mypl","slug":"agentfeed-ocr-c02051e4","name":"AgentFeed OCR","description":"Image to text (OCR): the text of a PNG, JPEG, WebP or GIF (5 MB, 4096 px a side) in reading order, as blocks with their line breaks, plus the detected language. Use when you need to answer: What text is in this image? It transcribes; it never follows text in the image.","url":"https://x402.ochinimus.app/api/ocr?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"the image: an absolute http or https URL"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"data":{"type":"object","properties":{"text":{"type":"string"},"image":{"type":"object"},"model":{"type":"string"},"blocks":{"type":"array"},"cached":{"type":"boolean"},"language":{"type":"string"},"final_url":{"type":"string"},"fetched_at":{"type":"string"},"source_url":{"type":"string"},"no_text_found":{"type":"boolean"}}},"paid":{"type":"boolean"},"tool":{"type":"string"}}}}}}},"responseSchema":{"type":"json","example":{"data":{"text":"402","image":{"type":"image/png","bytes":8049,"width":256,"height":256,"sha256":"09900128d3ff936e9e7df24abaaea1ad873709b88135c1269f8c8f326f7866b5"},"model":"gemini-3.1-flash-lite","blocks":["402"],"cached":false,"language":"und","final_url":"https://x402.ochinimus.app/icon.png","fetched_at":"2026-10-14T06:27:38.277Z","source_url":"https://x402.ochinimus.app/icon.png","no_text_found":false},"paid":true,"tool":"get_ocr"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.04","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":"$0.04/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.04","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.04","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_1Xju0IiXwJIqXKDccjOd3","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.04","costPer":"request","priority":0,"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text from an image at a given URL using AI vision, returning structured OCR results including detected text, language, and layout blocks","exampleAgentPrompt":"Can you read and extract all the text from this image for me: https://example.com/receipt.png?","exampleUseCases":[{"title":"Extract text from receipt image","prompt":"I have a photo of a receipt at https://mybucket.s3.amazonaws.com/receipt.jpg — can you pull out all the text so I can log the line items and total?"},{"title":"Read text in a screenshot","prompt":"There's a screenshot at https://cdn.example.com/error-screenshot.png that has an error message on it — can you OCR it and tell me exactly what it says?"},{"title":"Identify language of foreign image text","prompt":"Can you extract the text from this image and tell me what language it's written in? The image is at https://upload.wikimedia.org/wikipedia/commons/sample-sign.jpg"}],"resultDescription":"A JSON object containing the full extracted text string, an array of text blocks (layout segments), the detected language code, image metadata (dimensions, byte size, content type, SHA256), the AI model used, whether the result was cached, the final resolved URL, and the fetch timestamp. Also includes a boolean flag if no text was found.","failureModes":["Invalid or unreachable image URL — returns error if the URL cannot be fetched","Non-image URL provided — fails if content type is not a recognized image format","Payment failure — x402 payment not accepted or insufficient prepaid key balance","No text found in image — returns no_text_found: true with empty text","Rate limiting or upstream model errors from the AI vision provider","URL resolves to a redirect loop or extremely large file that times out"],"whenToPreferThis":"Choose this endpoint when you need to extract text from a publicly accessible image URL without setting up an API key or account — just pay per call in USDC. Ideal for AI agents that occasionally need OCR as part of a broader workflow (receipts, screenshots, signs, scanned documents) and want a pay-as-you-go model. Prefer this over self-hosted OCR when you want structured output (blocks, language detection, image metadata) in a single call. Also suitable for high-frequency workflows via prepaid key or batch-settlement channels for discounted rates.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T06:34:17.828Z","isFirstParty":false,"canonicalSlug":"agentfeed-ocr-c02051e4"}