{"uid":"cap_zNdaFog-YNZ5Yk-EM5_tA","slug":"agentfeed-structured-data-extraction-e3eb9706","name":"AgentFeed Structured Data Extraction","description":"Structured extraction: JSON for a schema of up to 20 fields (string, number, boolean, date, string[]), with null for anything the document does not state, never an invented value. Use when you need to answer: What are these fields on this page or PDF, as JSON?","url":"https://x402.ochinimus.app/api/extract?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","schema"],"properties":{"url":{"type":"string","description":"the page or PDF: an absolute http or https URL"},"schema":{"type":"string","description":"JSON object of field name to type, e.g. {\"title\":\"string\",\"price\":\"number\",\"released\":\"date\"}; up to 20 fields and 2 KB"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"data":{"type":"object","properties":{"data":{"type":"object"},"kind":{"type":"string"},"model":{"type":"string"},"title":{"type":"string"},"cached":{"type":"boolean"},"pct_read":{"type":"number"},"final_url":{"type":"string"},"truncated":{"type":"boolean"},"chars_read":{"type":"number"},"fetched_at":{"type":"string"},"source_url":{"type":"string"},"chars_total":{"type":"number"},"null_fields":{"type":"array"},"verbatim_fields":{"type":"array"},"tokens_estimated":{"type":"number"}}},"paid":{"type":"boolean"},"tool":{"type":"string"}}}}}}},"responseSchema":{"type":"json","example":{"data":{"data":{"title":"Example Domain","contact_email":null},"kind":"html","model":"gemini-3.1-flash-lite","title":"Example Domain","cached":false,"pct_read":100,"final_url":"https://example.com/","truncated":false,"chars_read":156,"fetched_at":"2026-10-14T06:27:40.974Z","source_url":"https://example.com/","chars_total":156,"null_fields":["contact_email"],"verbatim_fields":[],"tokens_estimated":45},"paid":true,"tool":"get_extract"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.025","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":"$0.025/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.025","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.025","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_NaedZPqg6SjdrlgwA_H0_","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.025","costPer":"request","priority":0,"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a web page or PDF at a given URL and extracts user-defined structured fields as JSON using an AI model","exampleAgentPrompt":"Fetch the page at https://example.com/product/42 and extract the title, price, and release date for me — return them as structured data.","exampleUseCases":[{"title":"Product price monitoring from URL","prompt":"Go to https://store.example.com/items/sneaker-air-max and extract the product name, current price, and whether it's in stock — I want those three fields as structured data."},{"title":"Academic paper metadata extraction","prompt":"Pull the abstract, author names, and publication date from this PDF: https://arxiv.org/pdf/2401.12345 and give them back as structured JSON."},{"title":"Lead enrichment from company website","prompt":"Visit https://acmecorp.com/about and extract the company name, contact email, and founding year from the page."}],"resultDescription":"A JSON response containing a 'data' object with the extracted fields matching the user-defined schema, plus metadata: the AI model used, whether the result was cached, percentage of the page read, character counts, the final resolved URL, a list of fields that were null, and a timestamp of when the page was fetched.","failureModes":["URL is unreachable or returns non-200 status — extraction fails with an error","PDF or page exceeds character limit — response is truncated (truncated: true, pct_read < 100)","Schema fields cannot be found in the page content — returned as null_fields","Invalid URL format — request rejected","Schema definition exceeds 20 fields or 2 KB limit — request rejected","Payment not completed (x402 flow incomplete) — 402 response returned"],"whenToPreferThis":"Choose this endpoint when you need to extract specific named fields from any publicly accessible web page or PDF URL and receive them as typed, structured JSON — especially when you don't want to write custom scrapers or parse raw HTML. It is distinct from general web search (no search query needed, you already have the URL) and from summarization (you get discrete fields, not prose). Ideal for product data extraction, document parsing, and lead enrichment workflows where the schema is known upfront.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T06:41:42.635Z","isFirstParty":false,"canonicalSlug":"agentfeed-structured-data-extraction-e3eb9706"}