{ "openapi": "3.0.1", "info": { "title": "OCR Image to Text: Extract Text from Images & PDFs", "description": "OCR for image URLs (PNG, JPEG, WebP, TIFF, GIF) and scanned PDFs, with built-in Tesseract. 8 languages incl. English, German, Japanese, Chinese. Text, confidence and line boxes. Empty input = free demo. $0.004 per image.", "version": "0.1", "x-build-id": "SNbraqDUhstX22Rd1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ucchiii~ocr-image-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ucchiii-ocr-image-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ucchiii~ocr-image-text/runs": { "post": { "operationId": "runs-sync-ucchiii-ocr-image-text", "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/ucchiii~ocr-image-text/run-sync": { "post": { "operationId": "run-sync-ucchiii-ocr-image-text", "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 or PDF URLs", "type": "array", "description": "Public image URLs (http:// or https://; PNG, JPEG, WebP, TIFF, GIF first frame) and optionally scanned PDF URLs, for example 'https://example.com/scan.png'. Each file is downloaded once (size cap below, 30 s, up to 5 redirects). Up to 500 URLs per run. Leave empty to run a free demo on two built-in sample images (not charged).", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Languages expected in the images (up to 4 are combined, for example English + German). Pick only the languages you need: fewer languages are faster and more accurate. Default: English.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "por", "ita", "jpn", "chi_sim" ], "enumTitles": [ "English", "German", "French", "Spanish", "Portuguese", "Italian", "Japanese", "Chinese (Simplified)" ] }, "default": [ "eng" ] }, "outputLayout": { "title": "Output layout", "enum": [ "text", "lines" ], "type": "string", "description": "'text' (default): the recognized text with line breaks and blank lines between paragraphs. 'lines': the same text plus a 'lines' array with the text, bounding box (left, top, width, height in pixels of the original image) and confidence of each line. Charging is the same in both modes.", "default": "text" }, "maxImageSizeMB": { "title": "Max file size (MB)", "minimum": 0.1, "maximum": 25, "type": "number", "description": "Files larger than this are skipped with error 'file_too_large' (allowed 0.1 to 25, default 10). Images above 40 megapixels are also skipped.", "default": 10 }, "maxPdfPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 50, "type": "integer", "description": "Scanned PDFs are rasterized at 200 dpi and each page is read as one image. Only the first N pages of each PDF are processed (allowed 1 to 50, default 5). Each page read counts as one image for pricing.", "default": 5 }, "grayscale": { "title": "Convert to grayscale", "type": "boolean", "description": "Convert to grayscale and stretch the contrast before reading. Helps with most photos and scans; turn off for very clean screenshots if results look worse.", "default": true }, "upscaleSmall": { "title": "Upscale small images", "type": "boolean", "description": "Enlarge images whose longer side is under 1200 px (up to 3x) before reading. Small text is recognized much better after upscaling. Huge images are always scaled down to 5000 px.", "default": true } } }, "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 } } } } } } } } } }