Reducto · Schema
Reducto Extract
Schema for the Reducto Extract API request and response. POST /extract returns structured JSON data shaped by a caller-supplied JSON Schema, with optional citations and deep-extract behavior.
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://api-evangelist.com/schemas/reducto/reducto-extract-schema.json",
"title": "Reducto Extract",
"description": "Schema for the Reducto Extract API request and response. POST /extract returns structured JSON data shaped by a caller-supplied JSON Schema, with optional citations and deep-extract behavior.",
"type": "object",
"definitions": {
"ExtractRequest": {
"type": "object",
"description": "Request body for POST /extract — synchronous or asynchronous structured-data extraction.",
"required": ["document_url", "schema"],
"properties": {
"document_url": {
"type": "string",
"description": "Source document URL, reducto://upload, or jobid:// reference to reuse a prior parse.",
"format": "uri"
},
"schema": {
"type": "object",
"description": "JSON Schema describing the shape of the data to extract. Supports nested objects and arrays."
},
"system_prompt": {
"type": "string",
"description": "Optional natural-language instruction guiding extraction decisions."
},
"options": {
"type": "object",
"properties": {
"generate_citations": { "type": "boolean" },
"use_chunking": { "type": "boolean" },
"deep_extract": {
"type": "object",
"description": "Enables deep extract mode for harder pages. Adds per-field cost.",
"properties": {
"enabled": { "type": "boolean" },
"mode": { "type": "string", "enum": ["balanced", "thorough"] }
}
},
"array_extract": {
"type": "object",
"properties": { "enabled": { "type": "boolean" } }
}
}
},
"priority": { "type": "boolean" }
}
},
"ExtractResponse": {
"type": "object",
"description": "Synchronous /extract response.",
"required": ["job_id", "result"],
"properties": {
"job_id": { "type": "string" },
"result": {
"type": "array",
"description": "Array of extraction results, one per matched document section.",
"items": { "type": "object" }
},
"citations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"field": { "type": "string" },
"page": { "type": "integer" },
"bbox": {
"type": "object",
"properties": {
"top": { "type": "number" },
"left": { "type": "number" },
"height": { "type": "number" },
"width": { "type": "number" }
}
}
}
}
},
"usage": {
"type": "object",
"properties": {
"num_pages": { "type": "integer" },
"credits": { "type": "number" }
}
}
}
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/reducto-extract"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.