{"slug":"doc-extract-api-thestarboy9696-4ef-workers-dev-extract-custo-707f86","title":"SchemaLock — extract structured JSON data from any PDF/image or raw text/HTML, c","host":"doc-extract-api.thestarboy9696-4ef.workers.dev","method":"POST","resource":"https://doc-extract-api.thestarboy9696-4ef.workers.dev/extract/custom","category":"image","description":"SchemaLock — extract structured JSON data from any PDF/image or raw text/HTML, converting it into a JSON Schema you supply, not limited to invoice/receipt/contract/resume. Unlike the fixed invoice/receipt/contract/resume endpoints, this accepts any JSON Schema — you define the fields. Takes a PDF/im","price_listed":0.02,"price_asked":null,"state":"effects","state_label":"Not tested: has real-world effects","checks_7d":0,"answered_7d":0,"latency_ms_median":null,"reported_calls_30d":3,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"content":"<string: raw text or HTML, e.g. an already-scraped web page, max 100000 chars — send this OR 'file', not both>","file":"<binary: PDF, PNG, or JPEG/WEBP, max 15MB — send this OR 'content', not both>","instructions":"<optional string: extra guidance for the model, max 1000 chars>","schema":"<string: JSON Schema, type \"object\", e.g. {\"type\":\"object\",\"properties\":{\"order_id\":{\"type\":\"string\"},\"ship_date\":{\"type\":\"string\"},\"total_weight_kg\":{\"type\":\"number\"}}}>"},"bodyType":"form-data","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{}},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[],"description_full":"SchemaLock — extract structured JSON data from any PDF/image or raw text/HTML, converting it into a JSON Schema you supply, not limited to invoice/receipt/contract/resume. Unlike the fixed invoice/receipt/contract/resume endpoints, this accepts any JSON Schema — you define the fields. Takes a PDF/image file OR raw text/HTML you already have (e.g. a scraped page). Schema-conformance, not fact-checking. A rejected schema is a 400 and costs nothing.","last_updated":"2026-09-08T19:25:19.108Z","schemes":["exact"]}