{"uid":"cap_XpEmupiiRAsWSRFfl_cUy","slug":"pixo-tools-pdf-ocr-google-gemini-26d639dc","name":"Pixo Tools PDF OCR (Google Gemini)","description":"OCR a scanned PDF via Google Gemini — priced per page (sends content to a third party)","url":"https://api.pixo.tools/v1/pdf/ocr","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_xu7YPsGu7tBw1OG0_OKm-","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":"Performs OCR on a scanned PDF using Google Gemini to extract readable text, priced per page","exampleAgentPrompt":"Can you OCR this scanned PDF for me and give me the extracted text? Here's the file — it's a scanned contract that isn't selectable.","exampleUseCases":null,"resultDescription":"Returns the OCR-extracted text content recognized from the scanned PDF pages, processed via Google Gemini's vision model. Output is text data derived from the visual content of each page. Note that document content is sent to Google Gemini as a third party.","failureModes":["File is not a valid PDF — returns 400 or format error","PDF has no scanned/image content (already text-based) — may return empty or trivial output","File too large or page count exceeds limits — returns 413 or quota error","Google Gemini API unavailable — returns 502 or timeout","Payment not completed or insufficient USDC balance — returns 402 Payment Required","Corrupt or password-protected PDF — returns processing error"],"whenToPreferThis":"Use this endpoint when you have a scanned or image-based PDF (not a text-selectable PDF) and need AI-powered OCR to extract the text. Prefer this over the plain text extraction endpoint (which works in-process) when the PDF is image-only or when Gemini's superior handwriting/layout recognition is needed. Choose this over the structured JSON extraction endpoint when you just want raw OCR text rather than schema-mapped data.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:34:55.934Z","isFirstParty":false}