{"uid":"cap_AT0ys2VpPFOm6_yWABpyD","slug":"agentdata-document-extraction-api-ac6c0050","name":"AgentData Document Extraction API","description":"Structured data from any document for AI agents, $0.25 per call: send a PDF, DOCX, XLSX, HTML, image or plain text plus a JSON Schema, get back one JSON object filled from the document — invoices, contracts, forms, CVs, receipts. Fields the document does not state come back null. One call, url or base64 (max 10 MB). Unreadable input means a 400 and you pay nothing. USDC on Base, no account.","url":"https://agentdata-api.sander-van-aard.workers.dev/doc/extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object"},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"headers":{"type":"object","additionalProperties":{"type":"string"}},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"queryParams":{"type":"object","additionalProperties":{"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":"0.25","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":"$0.25/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_avNCW-KZ9vlSejHxXqyIr","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.25","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts structured JSON data from documents (PDF, DOCX, XLSX, HTML, images, plain text) according to a user-supplied JSON Schema, returning one filled JSON object per call.","exampleAgentPrompt":"Can you extract the invoice number, vendor name, line items, and total amount from this PDF invoice I just uploaded? Use a schema with those four fields and give me back a JSON object.","exampleUseCases":[{"title":"Invoice data extraction for accounting","prompt":"I have a PDF invoice from a supplier — can you pull out the invoice number, issue date, vendor name, and total amount due and give me that as structured JSON?"},{"title":"CV parsing for recruitment pipeline","prompt":"Parse this candidate's CV (it's a DOCX) and extract their name, email, years of experience, list of skills, and most recent job title into a JSON object so I can add them to our applicant database."},{"title":"Receipt field extraction for expense reports","prompt":"I've got a photo of a restaurant receipt — can you extract the merchant name, date, itemized amounts, and grand total from it as structured JSON for my expense report?"}],"resultDescription":"A single JSON object whose keys match the supplied JSON Schema, with values filled from the document content. Any field the document does not explicitly state is returned as null. The response is always one JSON object per call.","failureModes":["400 error returned for unreadable or corrupt input documents (no charge applied)","Fields absent from the document come back as null rather than errored","Document exceeds 10 MB size limit resulting in rejection","Unsupported file types or malformed base64 encoding cause extraction failure","Schema mismatch may result in all-null output if schema does not align with document content"],"whenToPreferThis":"Choose this endpoint when you need to extract specific, named fields from a heterogeneous document (PDF, DOCX, XLSX, HTML, image, or plain text) into a guaranteed-schema JSON object in a single call. It is especially useful for invoice processing, contract analysis, CV parsing, and form digitization where you control the output schema. Prefer it over general-purpose LLM document Q&A when you need deterministic, schema-conformant JSON output rather than free-text answers, and when you want per-call pricing with no account setup.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T12:34:07.163Z","isFirstParty":false,"canonicalSlug":"agentdata-document-extraction-api-ac6c0050"}