{"uid":"cap_4-eg2Dg9dylIAM4JCIH5u","slug":"sitecheck-pdf-to-text-979ce530","name":"SiteCheck PDF to Text","description":"Pay-per-call tools for AI agents: image generation, speech-to-text, text-to-speech, embeddings, LLM chat, website audits and contact enrichment, web page to Markdown reader, PDF to text, sitemap URLs, tech stack detection, translation, exchange rates, e-mail pre-check, domain RDAP/DNS lookup, Solana token checks, trending tokens and wallet holdings, plus business and compliance data (EU VAT/VIES, IBAN, LEI/GLEIF, US recalls, OSHA/EPA violations, UK insolvency notices). Plus prediction-market search, briefs, quotes and unsigned buy transactions, powered by Panta. Payment: x402, USDC on Base, Solana or Arc. No signup, no API key.","url":"https://api.sitecheck-api.workers.dev/api/pdf?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"http(s) link to a PDF"},"maxChars":{"type":"integer","description":"Cut the text at this many characters, 1000-500000, default 100000"},"pdf_base64":{"type":"string","description":"Alternative: the PDF as base64"}}},"responseSchema":{"type":"json","example":{"note":"Text layer only, no OCR.","text":"Bitcoin: A Peer-to-Peer Electronic Cash System\nSatoshi Nakamoto...","chars":21220,"pages":9,"title":null,"author":null,"byPage":[{"page":1,"text":"Bitcoin: A Peer-to-Peer Electronic Cash System..."}],"creator":"Writer","subject":null,"producer":"OpenOffice.org 2.4","createdAt":"2009-03-24T11:33:15Z","truncated":true,"modifiedAt":null,"pagesReturned":9}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_xbt1Q0a9yFdLLErG1kI8s","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text content from a PDF file (by URL or base64) and returns the raw text, metadata, and per-page breakdown","exampleAgentPrompt":"Can you extract the text from this PDF — https://arxiv.org/pdf/2303.08774 — and return the full content up to 200000 characters?","exampleUseCases":[{"title":"Research paper ingestion pipeline","prompt":"Fetch this academic paper PDF at https://arxiv.org/pdf/1706.03762 and extract all the text so I can summarize it — limit it to 150000 characters."},{"title":"Legal contract text extraction","prompt":"I have a contract PDF encoded in base64 — can you extract all the text from it so I can search for the indemnification clauses? Give me up to 500000 characters."},{"title":"Automated report reading","prompt":"Pull the text out of this quarterly report PDF at https://example.com/reports/Q4-2024.pdf, page by page, so I can analyze the financial figures in each section."}],"resultDescription":"Returns a JSON object containing: the full extracted text string, total character count, page count, pages returned, truncation flag, per-page text array, and PDF metadata fields (title, author, subject, creator, producer, createdAt, modifiedAt). Note: text layer extraction only — no OCR for scanned/image-based PDFs.","failureModes":["PDF at URL is inaccessible or returns non-PDF content — error or empty text","PDF is a scanned image with no text layer — returns empty text with a note that OCR is not supported","base64 input is malformed or not a valid PDF — parse error","maxChars out of allowed range (1000–500000) — validation error","PDF is password-protected or encrypted — extraction fails","Network timeout fetching a large remote PDF — request error"],"whenToPreferThis":"Use this endpoint when you need to extract the text layer from a PDF document — either from a public URL or a base64-encoded file — and want structured output including per-page text and metadata. It is pay-per-call with no signup required, making it ideal for agent pipelines that process PDFs on demand. Note that it does not perform OCR, so it is only suitable for PDFs with an embedded text layer, not scanned image documents.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T18:42:23.496Z","isFirstParty":false,"canonicalSlug":"sitecheck-pdf-to-text-979ce530"}