{"uid":"cap_XrGg7ZP8mH48T3X6511Az","slug":"freshproof-pdf-to-markdown-converter-149a8782","name":"FreshProof PDF to Markdown Converter","description":"Convert a public text-based PDF into page-referenced Markdown with document metadata, page boundaries, retrieval evidence, and a content hash for AI agents. OCR is not supported.","url":"https://freshproof-api-mainnet.up.railway.app/v1/pdf-to-markdown","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","pattern":"^https?://","maxLength":4096},"options":{"type":"object","default":{"maxPages":50},"required":["maxPages"],"properties":{"maxPages":{"type":"integer","default":50,"maximum":50,"minimum":1}},"additionalProperties":false}}},"responseSchema":{"type":"json","example":{"data":{"pages":[{"markdown":"Dummy PDF file","pageNumber":1,"characterCount":14}],"source":{"finalUrl":"https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf","statusCode":200,"contentType":"application/pdf","retrievedAt":"2026-08-03T08:00:00.000Z","requestedUrl":"https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf","redirectChain":[]},"document":{"title":"Dummy PDF file","pageCount":1,"processedPageCount":1},"markdown":"# Page 1\n\nDummy PDF file","warnings":["TABLE_STRUCTURE_NOT_GUARANTEED"],"truncated":false,"contentHash":"dddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd"},"success":true}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/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_neNdmhSVjXHf6FEU9BnPf","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts a public text-based PDF URL into page-referenced Markdown with document metadata, page boundaries, retrieval evidence, and a content hash","exampleAgentPrompt":"Can you convert this PDF into markdown for me — https://example.gov/annual-report-2024.pdf — and include up to 30 pages with page markers so I know where each section came from?","exampleUseCases":[{"title":"Research paper ingestion for RAG pipeline","prompt":"I need to feed this academic paper into my RAG system — can you convert https://arxiv.org/pdf/2401.12345.pdf to markdown with page references, up to 50 pages, so I can chunk it properly?"},{"title":"Government document content extraction","prompt":"Pull the text out of this public government PDF at https://regulations.gov/docs/rule-2024-001.pdf and give it to me as markdown with page boundaries — just the first 20 pages."},{"title":"Verifiable PDF snapshot for compliance audit","prompt":"Convert https://sec.gov/filings/10k-2024.pdf to markdown and make sure I get the content hash and retrieval evidence so I can prove what the document said at the time I retrieved it."}],"resultDescription":"Returns page-referenced Markdown content of the PDF, including document metadata (title, author, page count), explicit page boundary markers, retrieval evidence (source URL, timestamp, access details), and a deterministic content hash for verification. OCR is not performed — only text-layer PDFs are supported.","failureModes":["PDF requires OCR (scanned/image-based) — not supported, returns error","URL is not publicly accessible or requires authentication — fails to retrieve","PDF exceeds maxPages limit — only up to 50 pages processed","URL does not point to a valid PDF — returns parsing error","Network timeout or upstream PDF server unavailable — returns retrieval error","PDF is encrypted or password-protected — conversion fails"],"whenToPreferThis":"Choose this endpoint when you need structured, page-referenced Markdown from a publicly accessible text-layer PDF, especially when retrieval provenance and a content hash are required for auditability or AI grounding. It is ideal for RAG pipelines, compliance workflows, or any agent task that needs verifiable PDF content. Prefer it over generic PDF parsers when evidence metadata and deterministic hashing matter. Do not use it for scanned PDFs requiring OCR, private/authenticated PDFs, or non-PDF documents (use the sibling HTML/web endpoint for those).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:30:08.982Z","isFirstParty":false}