{"uid":"cap_yI1O0Z2mx5OievEyxMRi4","slug":"crowdspark-agent-tools-ocr-from-uploaded-image-5291ffa7","name":"CrowdSpark Agent Tools – OCR from Uploaded Image","description":"Pay-per-call utilities for AI agents over x402, USDC on Base.","url":"https://agents.crowdspark.me/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":"RECEIPT Cafe Nova\nOrder #: 4821\nTOTAL $12.40"}},"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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_NiA7JG3jpU8cKigyNEPhy","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text from an uploaded PNG, JPEG, or WebP image using OCR, returning the recognized text as a string","exampleAgentPrompt":"Can you extract all the text from this receipt image I'm uploading? It's a PNG of a printed restaurant receipt and I need the itemized text pulled out.","exampleUseCases":[{"title":"Digitizing scanned invoice images","prompt":"I have a scanned JPEG invoice from a vendor — can you run OCR on it and give me all the text so I can pull out the line items and total?"},{"title":"Reading text from a screenshot","prompt":"Here's a PNG screenshot of an error message I got — can you extract the text from it so I can copy it into a bug report?"},{"title":"Extracting form data from a photo","prompt":"I took a photo of a paper form — it's a WebP image — can you read all the text off it so I can enter the data into our system?"}],"resultDescription":"A JSON object with a single field `text` containing all recognized text extracted from the image, preserving line breaks as they appear in the source image (e.g. {\"text\": \"RECEIPT Cafe Nova\\nOrder #: 4821\\nTOTAL $12.40\"}). On error, returns HTTP 400 with a descriptive hint about what went wrong; bad files are not charged.","failureModes":["HTTP 400 if the uploaded file is not a valid PNG, JPEG, or WebP (with a hint message explaining the issue)","HTTP 400 if the file exceeds the 10 MB size limit","HTTP 400 if no image body is provided or the content-type is unsupported","Poor OCR accuracy on very low-resolution, heavily skewed, or handwritten images (text returned but may contain errors)","Empty or partial text if the image has very little contrast or is mostly non-textual"],"whenToPreferThis":"Use this endpoint when you have a raw image file (PNG, JPEG, or WebP) and need to extract its textual content programmatically. It supports multiple upload formats (raw body, multipart form-data, or base64 JSON), making it flexible for different pipeline architectures. It is best suited for receipts, invoices, scanned documents, screenshots, forms, and signage. Prefer the sibling PDF-to-text endpoint for PDF files, and the one-call document parsing endpoint when you also need structured field extraction (not just raw text).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-31T18:41:15.987Z","isFirstParty":false,"canonicalSlug":"crowdspark-agent-tools-ocr-from-uploaded-image-5291ffa7"}