{"uid":"cap_RpZnF67etlIBO8wbQr3Z7","slug":"pdf-text-extraction-api-pay-per-call-6a20a829","name":"PDF Text Extraction API (pay-per-call)","description":"Crypto market data and web tools for autonomous agents: read web pages, PDFs and YouTube transcripts, check domains and tokens. Every `/api/v1/*` call is paid per call: **$0.003** for simple reads, **$0.005-$0.01** for aggregates, **$0.02-$0.03** for token risk checks and reports (USDC or USDT). Each route's price is in `x-payment-info`.\n\n**x402 agents:** pay automatically. The 402 response carries a standard `PAYMENT-REQUIRED` header (x402 v2, USDC on Base or Solana, USDT on Solana); retry with `PAYMENT-SIGNATURE`.\n\n**Manual (legacy) flow:** call the endpoint, read the HTTP 402 JSON (`pay_to`, `asset`, `price`), send the USDT transfer, then repeat the call with header `X-Payment-Tx: <signature>`. One signature pays for one call; signatures older than the `max_tx_age_seconds` value are rejected.\n\nMachine-readable spec: `/openapi.json`. LLM summary: `/llms.txt`. MCP server: `POST /mcp`.","url":"https://194-28-85-99.sslip.io/api/v1/pdf?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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":"http(s) URL of a PDF"},"max_chars":{"type":"integer","maximum":200000,"minimum":500},"max_pages":{"type":"integer","maximum":300,"minimum":1}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://bitcoin.org/bitcoin.pdf","text":"--- page 1 ---\nBitcoin: A Peer-to-Peer Electronic Cash System...","title":"Bitcoin: A Peer-to-Peer Electronic Cash System","truncated":false,"pages_read":9,"pages_total":9}},"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":"down","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_aQadHKJdcKdEnLiPij2jQ","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":"Fetches a PDF from a public URL and returns its full text content, page by page, with title and pagination metadata.","exampleAgentPrompt":"Can you read the PDF at https://bitcoin.org/bitcoin.pdf and extract all 9 pages of text so I can review the full content?","exampleUseCases":[{"title":"Research paper extraction for analysis","prompt":"Grab the full text from this research PDF — https://arxiv.org/pdf/2301.07041.pdf — I want to read through all its pages and summarize the key findings."},{"title":"Crypto whitepaper due diligence","prompt":"Pull the text out of this token whitepaper PDF at https://example.com/whitepaper.pdf, up to 50 pages, so I can check what the project is actually claiming."},{"title":"Legal or compliance document review","prompt":"Read the PDF at https://sec.gov/filing/document.pdf and give me the extracted text — limit it to 100,000 characters so it fits in context."}],"resultDescription":"Returns a JSON object with the extracted text (formatted page by page), the document title, total pages in the PDF, number of pages actually read, and a truncated flag indicating whether the output was cut short due to max_chars or max_pages limits.","failureModes":["Invalid or inaccessible PDF URL returns an error (non-200 HTTP from origin, auth-gated PDF)","PDF exceeds max_pages or max_chars — response will be truncated (truncated: true)","Corrupted or non-standard PDF format may fail to parse","Payment not provided or invalid signature returns HTTP 402 with payment instructions","Signature older than max_tx_age_seconds is rejected","Very large PDFs with 300+ pages may hit limits"],"whenToPreferThis":"Use this endpoint when you need to extract plain text from a publicly accessible PDF, especially for research papers, whitepapers, legal documents, or reports that your agent needs to read and process. Prefer this over general web-scraping endpoints when the target is specifically a PDF file. It handles page-by-page formatting, title extraction, and pagination metadata natively.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-17T07:28:19.038Z","isFirstParty":false,"canonicalSlug":"pdf-text-extraction-api-pay-per-call-6a20a829"}