{ "openapi": "3.0.1", "info": { "title": "Invoice & PDF to JSON Parser (OCR) – DOCX to Markdown", "description": "Convert PDF, DOCX and scanned documents to clean Markdown, tables and structured JSON. Extracts invoice & receipt fields (vendor, dates, totals, tax, line items, IBAN, VAT ID) with no AI key required. Fast, batch, pay per document.", "version": "1.0", "x-build-id": "clly8BeN8OgigzpzA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~document-invoice-to-json/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-document-invoice-to-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gazidev~document-invoice-to-json/runs": { "post": { "operationId": "runs-sync-gazidev-document-invoice-to-json", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gazidev~document-invoice-to-json/run-sync": { "post": { "operationId": "run-sync-gazidev-document-invoice-to-json", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Public URLs of PDF, DOCX, image (PNG/JPG/TIFF/WEBP) or TXT files. Google Drive, Dropbox and GitHub share links are converted to direct downloads automatically. One result row is produced per document.", "items": { "type": "string" } }, "uploadedFiles": { "title": "Or upload files", "type": "array", "description": "Upload documents directly instead of providing URLs." }, "documentType": { "title": "Document type", "enum": [ "auto", "invoice", "generic" ], "type": "string", "description": "'auto' detects invoices/receipts and extracts invoice fields only for them. 'invoice' always runs invoice extraction. 'generic' only returns Markdown, text and tables.", "default": "auto" }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Clean Markdown with headings, paragraphs, lists and tables - ideal for LLMs, RAG and AI agents.", "default": true }, "includeTables": { "title": "Include tables as JSON", "type": "boolean", "description": "Every detected table as {header, rows} arrays (page number and bounding box included).", "default": true }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Full plain text of the document.", "default": false }, "includePages": { "title": "Include per-page output", "type": "boolean", "description": "Adds a 'pages' array with text, Markdown and tables for each page (useful for citations / page-level RAG).", "default": false }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "force", "off" ], "type": "string", "description": "'auto' runs OCR only on pages without a text layer (scans, photos) and on image files. 'force' OCRs every page. 'off' never runs OCR (fastest, cheapest). OCR pages are billed with the extra 'ocr-page' event.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract language codes joined with '+'. Available: eng, deu, fra, spa, ita, por, nld, tur. Example: 'eng+deu'.", "default": "eng" }, "tableStrategy": { "title": "Table detection", "enum": [ "lines", "text", "none" ], "type": "string", "description": "'lines' detects ruled/bordered tables (accurate, recommended). 'text' additionally tries whitespace-aligned tables when no ruled table is found on a page (can produce noisy tables). 'none' disables table detection.", "default": "lines" }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Pages beyond this limit are skipped (and not billed).", "default": 300 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are rejected (and not billed).", "default": 50 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many documents are downloaded/processed in parallel.", "default": 4 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs (applied to all documents)." }, "llmProvider": { "title": "LLM refinement (optional, bring your own key)", "enum": [ "none", "anthropic", "openai" ], "type": "string", "description": "Invoice fields are extracted with built-in rules and need no API key. Optionally let an LLM refine them using YOUR key - billed by your LLM provider, not by this Actor. 'openai' works with any OpenAI-compatible endpoint (OpenAI, OpenRouter, Groq, Together...).", "default": "none" }, "llmApiKey": { "title": "LLM API key", "type": "string", "description": "Your Anthropic or OpenAI(-compatible) API key. Stored encrypted." }, "llmModel": { "title": "LLM model", "type": "string", "description": "Model ID. Defaults: 'claude-opus-5' (Anthropic), 'gpt-4o-mini' (OpenAI). Use a smaller model such as 'claude-haiku-4-5' for lower LLM cost." }, "llmBaseUrl": { "title": "OpenAI-compatible base URL", "type": "string", "description": "Only for provider 'openai'. Default https://api.openai.com/v1 (e.g. https://openrouter.ai/api/v1)." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }