{"uid":"cap_eIML4Eyo9YZinYM7p40gh","slug":"apiacre-com-document-text-metadata-extractor-d90cbf38","name":"apiacre.com Document Text & Metadata Extractor","description":"Extract clean text and metadata from supplied PDF, DOCX, HTML, Markdown, CSV, JSON, YAML, or plain-text documents.","url":"https://apiacre.com/v1/document/extract","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"filename":{"type":"string","title":"Filename","maxLength":240},"content_base64":{"type":"string","title":"Content Base64","maxLength":7100000}}},"responseSchema":{"type":"json","example":{"data":{"text":"Hello world","words":2,"metadata":{"bytes":11,"sha256":"64ec88ca00b268e5ba1a35678a1b5316d212f4f366b2477232534a8aeca37f3c","filename":"report.txt"},"characters":11},"meta":{"cached":false,"sources":[],"warnings":[],"duration_ms":42,"next_actions":[{"path":"/v1/document/redact","price":"$0.01","title":"PII and personal-data redaction","method":"POST","reason":"Remove common personal-data patterns from the extracted text before reuse.","service":"document.redact","use_output":"Use result.data.text as the redacted document and inspect the returned counts.","sample_path":"/samples/document.redact","handoff_path":"/catalog/document.redact","checkout_path":"/try/document.redact","input_template":{"text":"$result.data.text"},"maximum_atomic_usdc":"10000","authorization_required":true,"executes_automatically":false,"handoff_payment_required":false}]},"service":"document.extract","version":"1","request_id":"018f1f54-7f38-7ba2-8dc3-5f90272d9f1a"}},"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":"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_RxAd1j-KMC7UQDDfCvx8k","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 text content and metadata from common document file formats via a single POST call.","exampleAgentPrompt":"Can you pull all the text and metadata out of this PDF contract I just uploaded so I can search through it?","exampleUseCases":[{"title":"Legal contract text extraction","prompt":"I have a PDF of a vendor contract — can you extract all the text and any metadata like author and page count so I can review its contents?"},{"title":"Research paper ingestion pipeline","prompt":"Take this uploaded DOCX academic paper and extract all the text and metadata from it so I can index it in my knowledge base."},{"title":"Invoice data preprocessing","prompt":"I need to pull the raw text out of this scanned invoice PDF before I run it through my data parser — can you extract the text and any document metadata for me?"}],"resultDescription":"Returns the full extracted plain text from the document along with metadata fields such as title, author, creation date, page count, and detected file format.","failureModes":["Unsupported file format returns an error indicating the format is not handled","Corrupted or password-protected files may fail to parse and return an extraction error","Very large documents may time out or return partial results","Missing or malformed input body returns a 400 validation error","Empty documents return empty text with only metadata fields populated"],"whenToPreferThis":"Choose this endpoint when you need to extract raw text and metadata from common document formats (PDF, DOCX, PPTX, etc.) as a preprocessing step before search, indexing, analysis, or storage. It is a good fit for agent pipelines that receive user-uploaded files and need programmatic access to document contents without building a parsing library. Prefer it over general-purpose OCR services when dealing with natively digital documents rather than scanned images.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T12:45:54.935Z","isFirstParty":false}