{ "openapi": "3.0.1", "info": { "title": "Image OCR Text Extractor: extract text from images", "description": "Plain text with pixel bounding boxes and confidence per word, offline Tesseract, multilingual layouts, no AI key needed. Costs 2 USD per 1,000 processed images.", "version": "0.1", "x-build-id": "CgxbdZKYUpRsOX00G" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bepolabs~image-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bepolabs-image-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bepolabs~image-ocr/runs": { "post": { "operationId": "runs-sync-bepolabs-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bepolabs~image-ocr/run-sync": { "post": { "operationId": "run-sync-bepolabs-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "imageUrls": { "title": "Image URLs", "type": "array", "description": "Direct links to images (PNG, JPEG, WebP, BMP, PBM/PGM/PPM). A key-value store record URL of an uploaded file works too. Up to 500 per run.", "items": { "type": "string" } }, "storeKeys": { "title": "Uploaded files", "type": "array", "description": "Keys of images stored in this run's default key-value store (upload them with the API before the run starts).", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Languages in the images. Pick more than one for mixed text (each extra language slows reading a little). Default English.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "swe", "dan", "nor", "fin", "tur", "rus", "ukr", "ell", "ara", "heb", "hin", "jpn", "kor", "chi_sim", "chi_tra", "vie", "tha", "ind", "ron", "hun" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Swedish", "Danish", "Norwegian", "Finnish", "Turkish", "Russian", "Ukrainian", "Greek", "Arabic", "Hebrew", "Hindi", "Japanese", "Korean", "Chinese (simplified)", "Chinese (traditional)", "Vietnamese", "Thai", "Indonesian", "Romanian", "Hungarian" ] }, "default": [ "eng" ] }, "includeWords": { "title": "Include words with boxes", "type": "boolean", "description": "Every word with its pixel box (x, y, width, height), confidence and its block, paragraph and line. Off: smaller rows.", "default": true }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Plain text with the line breaks of the image. Off: Markdown only.", "default": true }, "minConfidence": { "title": "Min word confidence", "minimum": 0, "maximum": 100, "type": "integer", "description": "Words Tesseract is less sure of (0 to 100) are dropped from text, Markdown and words. 0 keeps all; 50 to 60 removes most noise on photos.", "default": 0 }, "maxSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 50, "type": "integer", "description": "Larger files are refused before they are downloaded.", "default": 20 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries per download on network errors, 429 and 5xx, with exponential backoff.", "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 } } } } } } } } } }