{ "openapi": "3.0.1", "info": { "title": "Image & PDF OCR — Image to Text and Scanned PDF to Text", "description": "Extract text from images and scanned PDFs with Tesseract OCR running inside the Actor: your files are never sent to a third-party OCR service. 16 languages, text per page with confidence scores, optional word boxes. $2 per 1,000 pages; blank pages and failed files are free.", "version": "0.1", "x-build-id": "wUKAVNY2awXGFubq4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/keyman98~image-pdf-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-keyman98-image-pdf-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/keyman98~image-pdf-ocr/runs": { "post": { "operationId": "runs-sync-keyman98-image-pdf-ocr", "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/keyman98~image-pdf-ocr/run-sync": { "post": { "operationId": "run-sync-keyman98-image-pdf-ocr", "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": [ "urls" ], "properties": { "urls": { "title": "Image/PDF URLs", "type": "array", "description": "Public URLs of the files to OCR. Supported: PNG, JPEG, TIFF (including multi-page), WebP, BMP, GIF, and PDF. The file type is detected from its content, not its URL extension.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Language(s) Tesseract should read the text as. Pick more than one for a page mixing languages (e.g. English + Italian) - Tesseract will try both.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "rus", "ukr", "tur", "ara", "hin", "chi_sim", "jpn", "kor" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Russian", "Ukrainian", "Turkish", "Arabic", "Hindi", "Chinese (Simplified)", "Japanese", "Korean" ] }, "default": [ "eng" ] }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 500, "type": "integer", "description": "Stop after this many pages/frames per PDF or multi-page image (keeps cost and run time predictable on huge files).", "default": 20 }, "dpi": { "title": "PDF render DPI", "minimum": 100, "maximum": 400, "type": "integer", "description": "Resolution used to rasterize each PDF page before OCR. Higher is sharper (better for small print) but slower and more memory. Ignored for image inputs, which are OCRed at their native resolution.", "default": 300 }, "includeWordBoxes": { "title": "Include word boxes", "type": "boolean", "description": "Also return each recognized word with its bounding box and confidence, not just the full page text.", "default": false }, "pageSegmentationMode": { "title": "Page segmentation mode", "enum": [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13" ], "type": "string", "description": "Tesseract's page segmentation mode (--psm), as a number 0-13. The default works for most single-page documents; switch it for a single line, a single word, or sparse/irregular layouts.", "default": "3" }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip (as an error row, not charged) any file larger than this.", "default": 50 } } }, "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 } } } } } } } } } }