{"uid":"cap_X3wqp0Dk-hLHvqfbdh10u","slug":"pixo-tools-pdf-table-extractor-12409b82","name":"pixo.tools PDF Table Extractor","description":"Extract tables from a PDF as JSON via Google Gemini — priced per page (sends content to a third party)","url":"https://api.pixo.tools/v1/pdf/tables","method":"POST","headers":{},"bodySchema":{"type":"object","required":["file"],"properties":{"file":{"type":"string","description":"PDF up to 30 pages"}}},"responseSchema":{"type":"object"},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.03","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_zapRMTrz4zmewQ55sV8hS","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts tables from a PDF file and returns them as structured JSON, powered by Google Gemini AI","exampleAgentPrompt":"Can you extract all the tables from this PDF and give them back to me as JSON? Here's the file: quarterly_report.pdf — it has financial summary tables I need to process programmatically.","exampleUseCases":[{"title":"Parse vendor invoice tables into database","prompt":"I've got a bunch of vendor invoices in PDF format that I need to pull line item data from. Can you extract all the tables from these PDFs and give me the structured JSON so I can load them into our accounting system? The files are invoices_batch_2024.pdf and they contain pricing and quantity tables."},{"title":"Convert research report tables to JSON","prompt":"I'm working with a market research PDF that has a bunch of data tables comparing competitor pricing and features. Can you pull out all those tables and convert them to JSON format? I need it structured so I can analyze and compare the data programmatically. The file is market_analysis_report.pdf."},{"title":"Extract spreadsheet data from scanned documents","prompt":"We have some older scanned financial reports in PDF that contain summary tables with quarterly performance metrics. Can you extract those tables and give me back structured JSON with the rows and columns intact? I need the data in a format I can easily import into our analytics tool. Here's the file: fy2023_financial_summary.pdf"}],"resultDescription":"Returns JSON containing the tables found in the PDF, with rows, columns, and cell values structured for programmatic use. Each table is represented as structured JSON with headers and data rows extracted via Google Gemini AI analysis.","failureModes":["PDF has no tables — returns empty array or null table data","PDF is password-protected — requires decryption first via the unlock endpoint","File is not a valid PDF — returns 400 or format error","Gemini AI fails to parse complex or low-quality scans — partial or inaccurate table extraction","File too large or too many pages — may exceed limits or increase cost","Network or third-party Gemini API unavailability — returns 502 or timeout","Payment not included or insufficient — returns 402 Payment Required"],"whenToPreferThis":"Use this endpoint when you need to extract structured tabular data specifically from a PDF and get it back as JSON for programmatic processing. Prefer this over generic OCR or text extraction when the target content is tables (financial data, reports, spreadsheets embedded in PDFs). If you need custom structured extraction with your own schema, use the sibling schema-based extraction endpoint instead. Note that content is sent to Google Gemini, so avoid for sensitive/confidential documents.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:36:47.225Z","isFirstParty":false}