{"uid":"cap_Q8RxGR2OAAb0AxgyOxbTK","slug":"parseapi-info-document-parser-33481de9","name":"parseapi.info Document Parser","description":"Parse a document (PDF, DOCX, PPTX, CSV/XLSX, HTML, EML, MSG, LOG) into token-compressed structure","url":"https://parseapi.info/parse/document?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"properties":{}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_NiO9KlOe9Q6Pcqiyy5bVx","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Parses documents (PDF, DOCX, PPTX, CSV/XLSX, HTML, EML, MSG, LOG) into token-compressed structured representations","exampleAgentPrompt":"Can you parse this PDF for me and give me back a structured, token-compressed version of its content so I can feed it into my pipeline?","exampleUseCases":[{"title":"AI pipeline document ingestion","prompt":"Take this 50-page PDF whitepaper and parse it into a compressed structured format so I can feed it efficiently into my LLM without blowing the context window."},{"title":"Email attachment content extraction","prompt":"I have a bunch of .EML email files — can you parse each one into structured content so I can pull out the key information and store it?"},{"title":"Spreadsheet data structuring","prompt":"Parse this XLSX financial report into a structured format I can actually work with programmatically — I need the tables and values extracted cleanly."}],"resultDescription":"Returns a token-compressed structured representation of the input document, including parsed text, sections, metadata, and document structure in a format optimized for downstream AI or programmatic processing.","failureModes":["Unsupported file type returns an error indicating the document format is not accepted","Corrupted or malformed files may fail to parse and return a parsing error","Oversized documents may time out or return partial results","Incorrectly specified bodyType (json/form-data/text) may cause request rejection","Network or payment (x402) failures result in no response or 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you need to convert office documents, PDFs, emails, spreadsheets, or log files into AI-ready structured content. Especially useful when token efficiency matters and you need structured output rather than raw text dumps. Prefer over OCR endpoints for text-native formats like DOCX or PPTX.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-16T06:32:58.095Z","isFirstParty":false,"canonicalSlug":"parseapi-info-document-parser-33481de9"}