{ "openapi": "3.0.1", "info": { "title": "OCR Text Extractor - Image & Scanned PDF to Text", "description": "English OCR for PNG, JPEG, PDF. Pages are OCR'd as images; PDF text layers aren't copied. From $4/1,000 pages with text + start fee $0.005/GB RAM per run.", "version": "0.2", "x-build-id": "wL4SD7v6eAX7s0Yfo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/luxe_tasks~ocr-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-luxe_tasks-ocr-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/luxe_tasks~ocr-text-extractor/runs": { "post": { "operationId": "runs-sync-luxe_tasks-ocr-text-extractor", "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/luxe_tasks~ocr-text-extractor/run-sync": { "post": { "operationId": "run-sync-luxe_tasks-ocr-text-extractor", "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": { "files": { "title": "Files", "type": "array", "description": "PNG, JPEG or PDF files (max 20 MB, 50 pages each). Uploads: [{\"key\": \"scan-1.pdf\"}] for a record in this run's default key-value store. File URLs: [{\"fileUrl\": \"https://example.com/doc.pdf\"}] - only documents you own or are licensed to process, one file per URL, no crawling; needs the attestation below. At most 50 file URLs per registered domain and 200 per run (more are skipped, not charged). URLs with a user name or password (user:pass@host) are refused; presigned URLs are fine and their query strings are never logged. Leave empty to read a built-in sample page instead (shows the output; sample pages are never charged)." }, "language": { "title": "Language", "enum": [ "eng" ], "type": "string", "description": "OCR language model (Tesseract tessdata, English). English only in this version.", "default": "eng" }, "layout": { "title": "Page layout", "enum": [ "auto", "single-column", "sparse" ], "type": "string", "description": "auto = automatic page segmentation; single-column = one block of text; sparse = scattered text (forms, labels).", "default": "auto" }, "renderDpi": { "title": "PDF render resolution (dpi)", "minimum": 100, "maximum": 300, "type": "integer", "description": "PDF pages are rendered at this resolution before OCR (capped at 25 megapixels per page).", "default": 200 }, "pageTimeoutSecs": { "title": "Per-page OCR timeout (seconds)", "minimum": 10, "maximum": 120, "type": "integer", "description": "A page that takes longer is reported as ocr_timeout and not charged.", "default": 60 }, "maxPagesPerFile": { "title": "Max pages per PDF", "minimum": 1, "maximum": 50, "type": "integer", "description": "PDFs with more pages are refused (too_many_pages), not charged.", "default": 50 }, "includeTextInDataset": { "title": "Include text in the dataset", "type": "boolean", "description": "Also copy the text (first 100,000 characters) into each dataset record. The full text is always saved as a .txt file in the run's key-value store.", "default": true }, "documentRightsAttestation": { "title": "I own or am licensed to process every document at these URLs, and fetching them does not bypass any access control.", "type": "boolean", "description": "Required only when you give file URLs. Leave unticked for uploads.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Items processed in parallel (each site still gets at most 1 request per second).", "default": 3 } } }, "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 } } } } } } } } } }