Document Processing API — PDF, OCR & Validated JSON
Pricing
from $20.00 / 1,000 document results
Extract schema-validated JSON from PDFs, scans, images, DOCX, XLSX, emails, and text. Includes OCR, field evidence, custom rules, and workflow routing—no model API key required.
You can access the Document Processing API — PDF, OCR & Validated JSON programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.2", "x-build-id": "UP9dWGeDgVEoREWSH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scalogik~document-processing-api-pdf-ocr-validated-json/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scalogik-document-processing-api-pdf-ocr-validated-json", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scalogik~document-processing-api-pdf-ocr-validated-json/runs": { "post": { "operationId": "runs-sync-scalogik-document-processing-api-pdf-ocr-validated-json", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scalogik~document-processing-api-pdf-ocr-validated-json/run-sync": { "post": { "operationId": "run-sync-scalogik-document-processing-api-pdf-ocr-validated-json", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "outputSchema" ], "properties": { "document": { "title": "Upload a document", "type": "string", "description": "Upload one PDF, DOCX, XLSX, PNG, JPEG, WebP, EML, CSV, JSON, Markdown, HTML, or UTF-8 text document. API callers can provide an HTTPS URL." }, "documentUrls": { "title": "Additional document URLs", "type": "array", "description": "Optional HTTPS URLs for batch processing. Each file may be up to 20 MiB; total documents cannot exceed maxDocuments.", "default": [], "items": { "type": "string" } }, "inlineDocuments": { "title": "Inline text documents", "type": "array", "description": "Optional text records for direct API calls. Each object needs filename and text; mimeType is optional.", "default": [] }, "outputSchema": { "title": "Output JSON Schema", "type": "object", "description": "Draft 2020-12 JSON Schema for the extracted data object. Use nullable fields when a document may legitimately omit a value." }, "extractionInstructions": { "title": "Extraction instructions", "maxLength": 4000, "type": "string", "description": "Optional business context or field interpretation guidance. Instructions inside uploaded documents are ignored.", "default": "" }, "validationRules": { "title": "Validation rules", "maxItems": 5, "type": "array", "description": "Optional deterministic checks. Operators: required or exists, equals, notEquals, contains, regex, gt, gte, lt, lte, in, and matchesPreset. Regex rules use full-string matching and a short safety timeout.", "default": [] }, "routePolicy": { "title": "Workflow routing policy", "enum": [ "standard", "conservative", "strict", "review_all" ], "type": "string", "description": "Standard accepts clean results and sends warnings or incomplete evidence to review. Conservative reviews coverage below 90%. Strict rejects warnings. Review all sends every successful extraction to manual review.", "default": "standard" }, "pdfMode": { "title": "PDF processing mode", "enum": [ "auto", "digital", "scanned" ], "type": "string", "description": "Auto uses selectable text when available and visual extraction for scanned PDFs. Digital requires a text layer. Scanned forces page-image processing.", "default": "auto" }, "includeEvidence": { "title": "Include field evidence", "type": "boolean", "description": "Return source quotes, locations, confidence, and local quote-verification status for extracted fields.", "default": true }, "includeRawText": { "title": "Include raw extracted text", "type": "boolean", "description": "Off by default for privacy. When enabled, output is truncated to 20,000 characters.", "default": false }, "failFast": { "title": "Stop after the first error", "type": "boolean", "description": "When false, batch runs return a transparent result record for every valid input document.", "default": false }, "maxDocuments": { "title": "Maximum documents", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of documents processed in this run.", "default": 20 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Document Processing API — PDF, OCR & Validated JSON from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: