{ "openapi": "3.0.1", "info": { "title": "Image & Scanned PDF to Text OCR (41 languages)", "description": "Extract text from photos, screenshots, scans and scanned PDFs (JPG, PNG, WebP, TIFF, GIF, BMP, PDF) in 41 languages. A photo engine for signs, menus and receipts, plus a document engine for scans. Line positions and confidence. Pay per image or page.", "version": "1.0", "x-build-id": "7ce6zbXbYznbQWsoR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/prometheus-maker~image-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-prometheus-maker-image-to-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/prometheus-maker~image-to-text-ocr/runs": { "post": { "operationId": "runs-sync-prometheus-maker-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/prometheus-maker~image-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-prometheus-maker-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "imageUrls" ], "properties": { "imageUrls": { "title": "Image or PDF URLs", "type": "array", "description": "Direct links to images (JPG, PNG, WebP, TIFF, GIF, BMP) or scanned PDFs. Each PDF page is read and billed as one image. For PDFs that already contain selectable text, the PDF & Document to Markdown actor is faster and cheaper.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPdfPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Reads at most this many pages of each PDF, starting from page 1. Every page read is billed as one image.", "default": 50 }, "engine": { "title": "Engine", "enum": [ "auto", "photo", "document" ], "type": "string", "description": "The photo engine (PaddleOCR models) reads text in photos far better and handles English, Chinese, Japanese and most Latin-script languages. The document engine (Tesseract) is tuned for scanned pages and reads all 41 languages. Auto picks the photo engine for images when it supports your languages, otherwise the document engine.", "default": "auto" }, "languages": { "title": "Languages", "type": "array", "description": "Languages in the images (41 available). Choosing only the ones you need is faster and more accurate.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "rus", "ukr", "ces", "slk", "hun", "ron", "bul", "hrv", "srp", "slv", "ell", "tur", "swe", "dan", "nor", "fin", "est", "lav", "lit", "cat", "ara", "heb", "fas", "hin", "ben", "tha", "vie", "ind", "msa", "jpn", "kor", "chi_sim", "chi_tra" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Russian", "Ukrainian", "Czech", "Slovak", "Hungarian", "Romanian", "Bulgarian", "Croatian", "Serbian (Cyrillic)", "Slovenian", "Greek", "Turkish", "Swedish", "Danish", "Norwegian", "Finnish", "Estonian", "Latvian", "Lithuanian", "Catalan", "Arabic", "Hebrew", "Persian", "Hindi", "Bengali", "Thai", "Vietnamese", "Indonesian", "Malay", "Japanese", "Korean", "Chinese (Simplified)", "Chinese (Traditional)" ] }, "default": [ "eng" ] }, "layout": { "title": "Layout", "enum": [ "auto", "single-block", "single-line", "sparse" ], "type": "string", "description": "Auto works for most images. Use 'sparse' for screenshots/memes with scattered text, 'single line' for captions or plates. Applies to the document engine.", "default": "auto" }, "includeLines": { "title": "Include lines with positions and confidence", "type": "boolean", "description": "Each line's text, confidence (0–100) and bounding box as fractions of image width/height.", "default": true }, "minLineConfidence": { "title": "Drop lines below this confidence", "minimum": 0, "maximum": 100, "type": "integer", "description": "Lines OCR is unsure about (noise, borders, cut-off text) are dropped. 0 keeps everything.", "default": 30 }, "maxConcurrency": { "title": "Images in parallel", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many images to read at once. OCR is CPU-heavy and Apify gives roughly one CPU core per 4 GB of memory, so raise this only together with memory.", "default": 2 } } }, "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 } } } } } } } } } }