{"uid":"cap_lAw9Xg6Tj89-4e7E3gxgC","slug":"agent-tools-ocr-from-uploaded-image-bytes-836aaab5","name":"Agent Tools OCR from Uploaded Image Bytes","description":"OCR from uploaded bytes: send a raw PNG/JPEG image body (max 10 MB) and get its text back.","url":"https://agent-tools.jbarkules.workers.dev/v1/ocr/upload?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","required":[],"properties":{}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"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":{"type":"json","example":{"text":"Hello Agent Tools"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.0038/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0038","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0038","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_wzDMM0MK8TixR0zcAL2jO","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0038","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text from a raw PNG or JPEG image uploaded as bytes (up to 10 MB) using optical character recognition.","exampleAgentPrompt":"I have a PNG scan of a receipt — can you extract all the text from it? Here's the image file.","exampleUseCases":[{"title":"Receipt total extraction for expense tracking","prompt":"I photographed a paper receipt from my lunch — can you read all the text out of this JPEG image so I can log the total and line items in my expense report?"},{"title":"Scanned form digitization","prompt":"I have a scanned PNG of a paper intake form. Can you pull all the text out of it so I can import the fields into our database?"},{"title":"Handwritten note transcription","prompt":"I took a photo of my handwritten meeting notes as a JPEG — can you read and transcribe all the text from the image?"}],"resultDescription":"A JSON object containing a 'text' field with all the recognized text extracted from the uploaded image as a single string (e.g. {\"text\": \"TOTAL $12.40\"}).","failureModes":["Image exceeds 10 MB size limit — request rejected","Unsupported image format (non-PNG/JPEG) — parsing failure or error response","Corrupt or unreadable image bytes — OCR returns empty string or error","Handwriting or low-resolution images may yield partial or inaccurate text","Network timeout if image upload is slow"],"whenToPreferThis":"Choose this endpoint when you have a raw PNG or JPEG image file (up to 10 MB) and need to extract its text content quickly via a single API call. It is ideal for receipts, scanned documents, photos of forms, and any image-to-text pipeline. Prefer this over PDF-based endpoints when your input is already a raster image rather than a PDF. For PDFs, use the sibling PDF-to-text endpoint instead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T06:31:05.421Z","isFirstParty":false,"canonicalSlug":"agent-tools-ocr-from-uploaded-image-bytes-836aaab5"}