{"uid":"cap_oQYdH_Xq6Hz5VSk_hZhAD","slug":"agentreader-pdf-extractor-1ea7feb1","name":"AgentReader PDF Extractor","description":"Extract the full text of a PDF from a URL. Returns plain text, page count and word count. Handles reports, papers and documentation up to 25 MB.","url":"https://agent-reader.agent-reader.workers.dev/pdf","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Absolute http(s) URL of the PDF"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"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":"$0.01/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_BnHTwLwTjjWFyCNuYqTAW","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 full plain text, page count, and word count from a PDF document given its URL","exampleAgentPrompt":"Can you pull out all the text from this PDF for me? Here's the link: https://arxiv.org/pdf/2301.07041.pdf — I want to read through the full content, see how many pages it is, and get the word count.","exampleUseCases":[{"title":"Research paper analysis pipeline","prompt":"I need you to read this academic paper at https://arxiv.org/pdf/2301.07041.pdf and extract all the text so I can summarize the key findings."},{"title":"Corporate report content ingestion","prompt":"Can you pull the full text out of this annual report PDF at https://example.com/reports/annual-2023.pdf? I want to know how many pages it is and get the raw text so I can search through it."},{"title":"Technical documentation extraction","prompt":"I have a product documentation PDF at https://docs.example.com/manual-v2.pdf — please extract all the text from it so I can look up specific instructions."}],"resultDescription":"Returns the full plain text content of the PDF, along with the total page count and word count. Handles documents up to 25 MB.","failureModes":["URL is not accessible or returns a non-200 status — extraction fails with an error","File exceeds the 25 MB size limit — request rejected","URL points to a non-PDF file — parsing error returned","PDF is encrypted or password-protected — text extraction may fail or return empty","Network timeout fetching the remote PDF — error returned","Malformed or corrupt PDF — parsing error or incomplete text returned"],"whenToPreferThis":"Use this endpoint when you need to programmatically read the text contents of a PDF document given only its URL, especially for reports, academic papers, and documentation up to 25 MB. Prefer this over generic web scrapers when the target is specifically a PDF file and you need structured output including page and word counts alongside the text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:37:02.255Z","isFirstParty":false}