{"uid":"cap_qiWcAraP2Pkxnwabzr3bg","slug":"agent-tools-document-extract-upload-20e0de22","name":"Agent Tools Document Extract Upload","description":"Pay-per-call utilities for AI agents over x402, USDC on Base.","url":"https://agents.crowdspark.me/v1/document/extract/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":{"kind":"image","text":"TOTAL $12.40","pages":null,"fields":{"totals":[{"label":"total","value":"$12.40"}],"amounts":["$12.40"]}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.012","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":"$0.012/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.012","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.012","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_MFoyY3dI_Qjt1PoH1iAgT","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.012","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Parses an uploaded PDF or image file (raw bytes, multipart, or base64) and extracts structured text, dates, amounts, totals, IDs, and tables","exampleAgentPrompt":"Can you parse this PDF invoice I'm uploading and pull out all the line items, dates, totals, and any reference IDs from it?","exampleUseCases":[{"title":"Invoice line-item extraction for accounting","prompt":"I just received a supplier invoice as a PDF — can you upload it and extract all the line items, totals, and invoice date so I can log them in our accounting system?"},{"title":"Receipt OCR for expense reporting","prompt":"I have a photo of a restaurant receipt in JPEG format. Can you run OCR on it and pull out the total amount, date, and any itemized charges so I can submit my expense report?"},{"title":"Scanned form field parsing","prompt":"We have a scanned PNG of a patient intake form. Can you extract all the filled-in field values, dates, and any ID numbers from it?"}],"resultDescription":"A JSON object containing a 'kind' field (pdf or image), the full extracted 'text', a 'pages' count (null for images), and a 'fields' object with structured sub-arrays: totals (label+value pairs), amounts (currency strings), dates, IDs, and tables parsed from the document.","failureModes":["HTTP 400 with a hint message if the file is corrupt, unsupported format, or exceeds size limits (20 MB for PDF, 10 MB for images)","HTTP 400 if no text layer is present in a PDF and OCR is not applicable","HTTP 400 if the content-type header is missing or mismatched","Empty or partial extraction if the document has very low image quality or non-standard encoding","Timeout or error for extremely large multi-page PDFs near the size limit"],"whenToPreferThis":"Choose this endpoint when you need to upload a raw document file (PDF or image) directly as bytes, multipart, or base64, and receive structured field extraction including dates, amounts, totals, IDs, and tables in a single call. Prefer it over URL-based document parsing endpoints when the file is already in memory or on disk rather than accessible via a public URL. It is especially suited for invoices, receipts, statements, and scanned forms where structured financial and metadata fields are needed alongside raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-31T18:40:02.543Z","isFirstParty":false,"canonicalSlug":"agent-tools-document-extract-upload-20e0de22"}