{
"openapi": "3.0.1",
"info": {
"title": "OCR Japanese, Chinese, Korean & English — Images & Scanned PDFs",
"description": "Extract text from images and scanned PDFs in Japanese, Chinese (Simplified/Traditional), Korean and English. No stray spaces between CJK characters, vertical Japanese support, embedded PDF text used when available. Pay per page.",
"version": "1.0",
"x-build-id": "eFWEYAmIr01ijjzk8"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/masahishop~ocr-cjk/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-masahishop-ocr-cjk",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/masahishop~ocr-cjk/runs": {
"post": {
"operationId": "runs-sync-masahishop-ocr-cjk",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/masahishop~ocr-cjk/run-sync": {
"post": {
"operationId": "run-sync-masahishop-ocr-cjk",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"fileUrls"
],
"properties": {
"fileUrls": {
"title": "Image or PDF URLs",
"type": "array",
"description": "Direct links to images (JPEG, PNG, WebP, TIFF, GIF, BMP, AVIF) or PDF files. Only the URLs you list are downloaded.",
"items": {
"type": "string"
}
},
"languages": {
"title": "Languages",
"type": "array",
"description": "Languages in the documents. Choose only what you need — fewer languages are faster and more accurate.",
"items": {
"type": "string",
"enum": [
"jpn",
"chi_sim",
"chi_tra",
"kor",
"eng"
],
"enumTitles": [
"Japanese",
"Chinese (Simplified)",
"Chinese (Traditional)",
"Korean",
"English"
]
},
"default": [
"jpn",
"eng"
]
},
"verticalText": {
"title": "Vertical text (縦書き)",
"type": "boolean",
"description": "Turn on for vertically written Japanese (novels, newspapers, signs). Columns are read right-to-left.",
"default": false
},
"pdfTextLayer": {
"title": "PDF pages that already contain text",
"enum": [
"auto",
"ocr"
],
"type": "string",
"description": "auto: use the embedded text when a page has it (fast, cheap, exact) and OCR only scanned pages. ocr: OCR every page.",
"default": "auto"
},
"pageRange": {
"title": "Page range",
"type": "string",
"description": "PDF pages to process, e.g. 1-5, 8. Empty = all pages."
},
"dpi": {
"title": "PDF render resolution",
"minimum": 150,
"maximum": 400,
"type": "integer",
"description": "Resolution used to render scanned PDF pages. 300 is best for small CJK characters; 200 is faster.",
"default": 300
},
"password": {
"title": "PDF password",
"type": "string",
"description": "Password for encrypted PDFs."
},
"includeLines": {
"title": "Include lines with bounding boxes",
"type": "boolean",
"description": "Also return each text line with its confidence and position (x0, y0, x1, y1).",
"default": false
},
"maxPagesPerFile": {
"title": "Max pages per PDF",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Safety limit on pages processed per PDF.",
"default": 100
},
"maxFileSizeMb": {
"title": "Max file size",
"minimum": 1,
"maximum": 300,
"type": "integer",
"description": "Larger files are skipped (and not charged).",
"default": 50
},
"downloadTimeoutSecs": {
"title": "Download timeout",
"minimum": 5,
"maximum": 600,
"type": "integer",
"description": "Timeout for downloading one file.",
"default": 60
},
"maxConcurrency": {
"title": "Parallel files",
"minimum": 1,
"maximum": 8,
"type": "integer",
"description": "Files processed at the same time. Each needs about 1 GB of 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
}
}
}
}
}
}
}
}
}
}