{"uid":"cap_aFIbIuQ8Mw-VXSmZkdhDQ","slug":"pdf-extract-api-4f367594","name":"PDF Extract API","description":"Extract structured JSON data from a PDF document.","url":"https://pdf-extract-api.pdfextractapi.workers.dev/extract","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":{"required":["file"],"properties":{"file":{"type":"string","format":"binary"},"schema":{"type":"string"}}},"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":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_AgfICJPbt3eGO3ejzWh4D","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts structured JSON data from a PDF document using a configurable schema","exampleAgentPrompt":"Extract all structured data from this PDF invoice and return it as JSON — pull out fields like vendor name, invoice number, line items, totals, and dates.","exampleUseCases":[{"title":"Invoice data extraction pipeline","prompt":"I have a PDF invoice I need to extract into structured JSON — get me the vendor name, invoice number, date, line items, and total amount due."},{"title":"Resume parsing for HR automation","prompt":"Parse this candidate's PDF resume and extract their name, contact info, work experience, education, and skills into a structured JSON object."},{"title":"Contract clause extraction","prompt":"Extract the key terms from this PDF contract into JSON, including parties involved, effective date, payment terms, and termination clauses."}],"resultDescription":"A JSON object containing structured data extracted from the provided PDF, with fields matching the optionally supplied output schema or inferred from the document content. The response includes named fields and values parsed from the PDF's text and layout.","failureModes":["Invalid or corrupted PDF file returns an error","Unsupported file format (non-PDF binary) causes parsing failure","Overly complex or image-only scanned PDFs may return incomplete extraction if OCR is not supported","Schema mismatch between requested output fields and available PDF content may yield null or empty fields","File size limits may cause rejection of very large PDFs","Network timeout on large file uploads"],"whenToPreferThis":"Choose this endpoint when you need to extract structured, machine-readable JSON from a PDF document — especially for invoices, forms, resumes, contracts, or reports where specific fields need to be captured programmatically. It is well-suited for automation pipelines that receive PDFs and need to feed structured data downstream. Prefer this over general-purpose LLM document parsing when a lightweight, cost-effective per-call approach is sufficient and the PDF contains selectable text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:31:18.273Z","isFirstParty":false}