{"uid":"cap_F5ILrqyeVsgIHzLTF5Exq","slug":"falcon-sol-pdf-to-text-markdown-51e103eb","name":"falcon.sol PDF to Text/Markdown","description":"Bank statement extraction for agents: transactions and underwriting metrics from bank-statement PDFs, plus invoice/receipt/W-9 extraction. Paid per call with x402.","url":"https://falcon-docs.falcon-sol.workers.dev/v1/pdf-text?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"Public https URL of a PDF"},"type":{"enum":["auto","invoice","receipt","purchase_order","w9","bank_statement","generic"],"type":"string"},"format":{"enum":["json","csv","xlsx"],"type":"string"},"file_base64":{"type":"string","description":"Base64 PDF (alternative to url, or send multipart 'file' / raw application/pdf)"}}},"responseSchema":{"type":"json","example":{"text":"INVOICE\nInvoice # INV-1042 ...","pages":2,"words":140,"format":"text","method":"text_layer","page_texts":[{"page":1,"chars":812,"method":"text_layer"}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0025","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":"$0.0025/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vbblk0J7pIy6oeFY-5saJ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0025","costPer":"request","priority":0,"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts a PDF (via URL or base64) to plain text or markdown with page-by-page extraction, including automatic OCR for scanned pages","exampleAgentPrompt":"Can you extract the text from this PDF — https://example.com/report.pdf — and give it back to me in markdown format so I can use it in my RAG pipeline?","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"I have a PDF at https://docs.mycompany.com/policy-manual.pdf — can you pull out all the text page by page in markdown format so I can index it into my vector database?"},{"title":"Scanned invoice text extraction","prompt":"I've got a scanned invoice as a base64 PDF that needs OCR — can you extract the text from it so I can parse the line items and totals?"},{"title":"Research paper ingestion for AI","prompt":"Please convert this academic paper PDF at https://arxiv.org/pdf/2301.00001.pdf into plain text, preserving reading order, so my agent can summarize the key findings."}],"resultDescription":"Returns a JSON object with the full extracted text, total page count, word count, output format used, extraction method (text_layer or OCR), and an array of per-page objects each containing character count and method used. For markdown format, headings, bullet points, and table rows are preserved.","failureModes":["PDF exceeds 60 pages or 4 MB size limit — request rejected","Invalid or inaccessible URL — returns error if PDF cannot be fetched","Corrupt or password-protected PDF — extraction fails or returns empty","Completely blank PDF returns empty result (not charged)","base64 encoding errors cause parse failure","Network timeout if remote PDF URL is slow to respond"],"whenToPreferThis":"Choose this endpoint when you need fast, low-cost PDF text extraction for AI pipelines — especially when you need per-page text in reading order, automatic OCR fallback for scanned pages, or markdown output with structure preserved. Ideal for RAG document ingestion workflows where cost per document matters ($0.0025 USDC). Prefer over generic document parsers when you need both text-layer and OCR in a single call without managing infrastructure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-31T18:36:02.440Z","isFirstParty":false,"canonicalSlug":"falcon-sol-pdf-to-text-markdown-51e103eb"}