{ "openapi": "3.0.1", "info": { "title": "Image OCR & Scanned PDF to Text — 19 Languages, Line Boxes", "description": "Read the text in images (PNG, JPEG, WebP, BMP) and scanned PDFs with OCR. One row per image or page with the text, confidence and optional line boxes. Pages that already have a text layer are taken as is. 19 languages incl. Japanese, Chinese, Korean, Arabic. $3 per 1,000 pages.", "version": "0.1", "x-build-id": "AqsnGE9BSlf8xcQsy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/northbell~image-ocr-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-northbell-image-ocr-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/northbell~image-ocr-text-extractor/runs": { "post": { "operationId": "runs-sync-northbell-image-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/northbell~image-ocr-text-extractor/run-sync": { "post": { "operationId": "run-sync-northbell-image-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", "required": [ "urls" ], "properties": { "urls": { "title": "Image or PDF links", "type": "array", "description": "Direct links to images (PNG, JPEG, WebP, BMP) or PDFs, one per line. Scanned PDFs are read page by page.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "The language(s) of the text, up to 3. Pick only what is there: each extra language makes reading slower and a little less accurate.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "por", "ita", "nld", "pol", "tur", "rus", "jpn", "chi_sim", "chi_tra", "kor", "ara", "hin", "vie", "ind", "tha" ], "enumTitles": [ "English", "German", "French", "Spanish", "Portuguese", "Italian", "Dutch", "Polish", "Turkish", "Russian", "Japanese", "Chinese (simplified)", "Chinese (traditional)", "Korean", "Arabic", "Hindi", "Vietnamese", "Indonesian", "Thai" ] }, "default": [ "eng" ] }, "includeLines": { "title": "Include lines with position", "type": "boolean", "description": "Add every line of text with its confidence and its box (x, y, width, height in pixels). Useful for receipts, forms and tables.", "default": false }, "forceOcr": { "title": "OCR every PDF page", "type": "boolean", "description": "By default a PDF page that already has a text layer is taken as is (exact and fast). Turn this on to read the picture of every page instead, for PDFs whose text layer is wrong.", "default": false }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Pages read from each PDF, from the first page.", "default": 50 }, "maxFileMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped with a free error row.", "default": 30 } } }, "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 } } } } } } } } } }