{"uid":"cap_StyBwBqibUYeUK3CybEyU","slug":"oblique-markets-json-extractor-7fea5e1b","name":"Oblique Markets JSON Extractor","description":"Use when an agent needs extract json. Returns Extract structured JSON from unstructured text against a caller-supplied JSON Schema — parse-validated with one automatic retry, 502 on failure instead of garbage. $0.01.","url":"https://api.oblique.markets/api/v1/paid/extract-json?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"text":{"type":"string","description":"Source text; truncated to 8,000 characters"},"schema":{"type":"object","description":"JSON Schema the extracted document must conform to"}}},"responseSchema":{"type":"json","example":{"data":{"total":1249.5,"vendor":"Acme GmbH","currency":"EUR","due_date":"2026-09-01","invoice_number":"INV-2041"},"model":"inclusionai/ling-3.0-flash"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":1,"rating":{"score":"0.00","successRate":"0.50","reviews":1,"stars":null,"state":"rated"},"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_FBoSR7-vXyJ9M0q7NQmlw","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 structured JSON from unstructured text by matching it against a caller-supplied JSON Schema, with automatic retry and parse validation.","exampleAgentPrompt":"Take this block of text — 'John Smith, born March 3 1985, lives at 42 Maple Street, New York, NY 10001, phone 555-234-5678' — and extract it into structured JSON with fields: name (string), birthDate (string), streetAddress (string), city (string), state (string), zip (string), phone (string).","exampleUseCases":[{"title":"Parse resume text into structured profile","prompt":"I have this raw resume text from a PDF and I need it structured as JSON with fields: fullName, email, phone, yearsOfExperience, skills (array of strings), and mostRecentJobTitle. Here's the text: 'Jane Doe | jane@example.com | 555-987-6543 | 8 years in software engineering. Skills: Python, Go, Kubernetes. Most recent role: Senior Engineer at Acme Corp.'"},{"title":"Extract invoice fields from email body","prompt":"Pull the invoice details out of this email body into JSON with fields: invoiceNumber, vendorName, totalAmount (number), currency, dueDate, and lineItems (array of objects with description and amount): 'Invoice #INV-2041 from Globex Supplies. Due: June 30 2025. Total: $1,250.00 USD. Items: Office chairs x2 $800, Desk lamp x5 $450.'"},{"title":"Structure product review sentiment data","prompt":"I'm getting product reviews as raw text and need them in JSON with fields: reviewerName, rating (integer 1-5), pros (array of strings), cons (array of strings), and summary (string). Here's one: 'By Alex T. — 4 stars. Love the battery life and the slim design. Wish the camera were better and the price a bit lower. Overall a solid mid-range phone.'"}],"resultDescription":"A schema-validated JSON object matching the caller-supplied JSON Schema, extracted from the input unstructured text. If the first LLM extraction attempt fails JSON schema validation, the service automatically retries once. If both attempts fail, the endpoint returns a 502 error rather than returning malformed or non-schema-compliant output.","failureModes":["502 returned if two consecutive extraction attempts both fail JSON Schema validation — no garbage output is ever returned","Ambiguous or contradictory input text may produce extraction results that are schema-valid but semantically incomplete","Very complex or deeply nested JSON Schemas may increase the likelihood of extraction failures","If the input text contains no information relevant to the schema fields, extracted values may be null or missing","Schema that is overly strict (e.g. tight regex patterns or enum constraints) may increase retry failure rates"],"whenToPreferThis":"Choose this endpoint when you need reliable, schema-validated JSON extracted from unstructured text and cannot tolerate receiving malformed or non-compliant output. The automatic retry-then-502 pattern makes it safer than rolling your own LLM extraction prompt where you'd have to handle parsing failures yourself. It is ideal for pipelines where downstream code expects strictly typed JSON and a hard failure is preferable to silently wrong data. Prefer it over general-purpose LLM calls when you already have a defined JSON Schema and want parse validation enforced server-side.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":2,"lastUsedAt":"2026-08-30T04:04:22.810Z","lastSuccessfullyRanAt":"2026-08-30T04:02:06.281Z","lastHealthCheckAt":"2026-10-21T12:43:43.214Z","isFirstParty":false,"canonicalSlug":"oblique-markets-json-extractor-7fea5e1b"}