{"slug":"x402-agentindex-world-pdf-39ce63","title":"Extract a public PDF (by HTTPS URL or base64) into clean Markdown","host":"x402.agentindex.world","method":"POST","resource":"https://x402.agentindex.world/pdf","category":"market","description":"Extract a public PDF (by HTTPS URL or base64) into clean Markdown - headings and tables preserved via layout-aware parsing, plus title/author/page count/date metadata and a real token count. Text content itself is never generated or altered, only its structure is inferred. Try GET /pdf/sample. Part ","price_listed":0.002,"price_asked":0.002,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":974,"reported_calls_30d":0,"reported_payers_30d":0,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"url":"https://www.ohchr.org/sites/default/files/UDHR/Documents/UDHR_Translations/eng.pdf"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"pdf_base64":{"description":"Base64-encoded PDF file content. Provide this or url, not both.","type":"string"},"url":{"description":"Public HTTPS URL of a PDF file. Provide this or pdf_base64, not both.","type":"string"}},"required":[]},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"markdown":{"description":"Extracted Markdown - headings and tables preserved via layout-aware parsing.","type":"string"},"metadata":{"properties":{"author":{"description":"Document author from PDF metadata, when present."},"date":{"description":"Document creation date from PDF metadata, when present."},"pages":{"description":"Number of pages in the PDF.","type":"integer"},"title":{"description":"Document title from PDF metadata, when present."}},"type":"object"},"token_count":{"description":"Real BPE token count (cl100k_base) of the extracted markdown.","type":"integer"},"x402_receipt":{"description":"Billing and provenance receipt for this call.","type":"object"}},"required":["markdown","metadata","token_count"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-25","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.002,"price_match":true,"latency_ms":974,"error":null}],"description_full":"Extract a public PDF (by HTTPS URL or base64) into clean Markdown - headings and tables preserved via layout-aware parsing, plus title/author/page count/date metadata and a real token count. Text content itself is never generated or altered, only its structure is inferred. Try GET /pdf/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.","last_updated":"2026-09-25T17:42:10.809Z","schemes":["exact"]}