{"uid":"cap_8vOUGN_fxNHiquASVhiZo","slug":"pdf-to-structured-json-pages-paragraphs-tables-geometry-8d40dc1e","name":"PDF to Structured JSON (Pages, Paragraphs, Tables, Geometry)","description":"Extract normalized pages, paragraphs, tables, sections, and geometry from a supplied PDF.","url":"https://manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io/api/v1/content/pdf-to-json","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"pages":{"type":"string","pattern":"^[1-9]\\d*(?:-[1-9]\\d*)?(?:,[1-9]\\d*(?:-[1-9]\\d*)?)*$","maxLength":512,"minLength":1},"locale":{"type":"string","pattern":"^[A-Za-z]{2,3}(?:-[A-Za-z0-9]{2,8})*$","maxLength":32,"minLength":2},"pdfBase64":{"type":"string","pattern":"^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?$","maxLength":13981016,"minLength":8}}},"responseSchema":{"type":"json","example":{"pages":[{"lines":[],"pageNumber":1,"selectionMarks":[]}],"tables":[],"content":"Example document text.","sections":[],"pageCount":1,"paragraphs":[],"processedPages":[1],"contentCharacters":22}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JPsT_m_Ay2ZwcyEx_HoX4","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts and normalizes pages, paragraphs, tables, sections, and geometric layout from a base64-encoded PDF into structured JSON.","exampleAgentPrompt":"Parse this PDF for me and give me the structured content — pages, paragraphs, tables, and geometric layout — as JSON; here's the file in base64, and I only need pages 1-5.","exampleUseCases":[{"title":"Extract tables from financial report","prompt":"I have a quarterly earnings PDF — can you extract all the tables and paragraph content from pages 1 through 10 as structured JSON so I can pull out the revenue figures programmatically?"},{"title":"Parse legal contract sections","prompt":"Take this base64-encoded contract PDF and break it down into its sections, paragraphs, and geometry in JSON format — I need to identify all the clause boundaries."},{"title":"Structured data pipeline from scanned PDF","prompt":"I'm building a data pipeline and need to convert this PDF into structured JSON with normalized pages, paragraphs, and table data — please process all pages and use locale en-US."}],"resultDescription":"A structured JSON object containing normalized document components including pages (with page numbers and dimensions), paragraphs (with text content and positions), tables (with rows, columns, and cell data), sections, and geometric bounding box information for each element.","failureModes":["Invalid base64 encoding returns a 400 error","PDF exceeds maximum size limit (base64 string over ~10MB) returns a 413 or 400 error","Malformed page range pattern returns a 400 validation error","Corrupted or password-protected PDFs may fail to parse","Invalid locale format returns a 400 validation error","Payment not fulfilled returns a 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you need rich, structured JSON output from a PDF with geometric layout metadata (bounding boxes, positions) in addition to text — especially when downstream processing requires table extraction, section identification, or paragraph-level structure. Prefer this over the PDF-to-Markdown endpoint when you need machine-parseable JSON with spatial geometry rather than human-readable Markdown, and over OCR endpoints when the PDF has a parseable internal structure (not just a scanned image).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-16T00:39:22.024Z","isFirstParty":false}