{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR - Scanned PDF OCR, $2/1k Pages, Per Line", "description": "Image to text OCR and scanned PDF OCR in bulk for $2 per 1000 images or pages. One row per image or page: text, every line with confidence and bounding box. Digital PDFs use the text layer, scans use Tesseract. 8 languages, only-new mode.", "version": "0.1", "x-build-id": "QaMB66FPcROk7AG63" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/martin10291~image-pdf-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-martin10291-image-pdf-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/martin10291~image-pdf-ocr/runs": { "post": { "operationId": "runs-sync-martin10291-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/martin10291~image-pdf-ocr/run-sync": { "post": { "operationId": "run-sync-martin10291-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", "properties": { "urls": { "title": "Image and PDF URLs", "type": "array", "description": "Direct links to images (png, jpg, webp, tiff, bmp, gif) or PDF files, scanned or digital. One result row is produced per image and per PDF page. Links must be public and point straight to the file.", "default": [ "https://www.gutenberg.org/cache/epub/11/pg11.cover.medium.jpg", "https://www.gutenberg.org/cache/epub/84/pg84.cover.medium.jpg", "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf" ], "items": { "type": "string" } }, "languages": { "title": "OCR languages", "type": "array", "description": "Languages of the text in your images. Pick one, or several for mixed text (a little slower). Used only when a page has to be read by OCR.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "bul", "rus" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Bulgarian", "Russian" ] }, "default": [ "eng" ] }, "outputMode": { "title": "Detail level", "enum": [ "lines", "words" ], "type": "string", "description": "lines = every text line with its confidence and bounding box. words = every single word with confidence and bounding box (bigger output).", "default": "lines" }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "Read at most this many pages from each PDF (from the first page). You pay per page, so this caps the cost of big documents.", "default": 20 }, "forceOcr": { "title": "Always use OCR for PDFs", "type": "boolean", "description": "By default, PDF pages that already contain a text layer are read from it (fast, exact). Turn this on to run OCR on every page anyway, for example when the text layer is wrong.", "default": false }, "onlyNew": { "title": "Only new files since last run", "type": "boolean", "description": "Skip every image or PDF URL that was already processed in an earlier run with the same Monitor ID. Use it for recurring jobs on a folder or feed of files. Each file is paid for once.", "default": false }, "monitorId": { "title": "Monitor ID", "type": "string", "description": "Separate memory for each watch list (used with only-new mode). Use a different ID per feed or customer.", "default": "default" }, "datasetId": { "title": "Dataset (integration input)", "type": "string", "description": "Optional. Pick a dataset (or paste its ID) to read the input from, for example the result of Google Maps Scraper. When this actor runs as an integration, the dataset of the triggering run is used automatically (payload.resource.defaultDatasetId), so you can leave this empty. If set, the values found in the dataset replace the main input list." }, "datasetField": { "title": "Dataset field", "type": "string", "description": "Optional. The item field that holds the value, for example website, url or videoUrl (dot paths like author.url work). Empty = detected automatically." }, "datasetMaxItems": { "title": "Max values from the dataset", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Upper limit of unique values taken from the dataset, to keep the cost under control.", "default": 1000 } } }, "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 } } } } } } } } } }