{ "openapi": "3.0.1", "info": { "title": "OCR API — Image & Scanned PDF to Text, 100+ Languages", "description": "OCR API: text, confidence, paragraphs and word boxes from images and scanned PDFs for $2 per 1,000 images. Tesseract OCR by URL, optional hOCR/TSV, many languages. Unofficial OCR API.", "version": "0.1", "x-build-id": "zYvviwSk7Mv103haU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/highbrow_fame~ocr-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-highbrow_fame-ocr-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/highbrow_fame~ocr-api/runs": { "post": { "operationId": "runs-sync-highbrow_fame-ocr-api", "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/highbrow_fame~ocr-api/run-sync": { "post": { "operationId": "run-sync-highbrow_fame-ocr-api", "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 URLs", "type": "array", "description": "Public links to images of text (PNG, JPEG, WebP, BMP; GIF and TIFF are passed to tesseract) or scanned PDFs (first pages rendered and read), one per line. Up to 20 MB per file.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Tesseract language codes, e.g. eng, deu, fra, spa, por, ita, nld, pol, rus, tur, jpn, kor, chi_sim, chi_tra, ara, hin — one per line; several are combined (eng + deu). English ships with the Actor; other languages are downloaded once per run (a few MB each).", "default": [ "eng" ], "items": { "type": "string" } }, "outputFormat": { "title": "Extra output", "enum": [ "text", "hocr", "tsv" ], "type": "string", "description": "The plain text is always delivered. hOCR adds the full layout as HTML (hocr field); TSV adds tesseract's tab-separated table of every word with its box and confidence (tsv field).", "default": "text" }, "includeBlocks": { "title": "Blocks", "type": "boolean", "description": "Deliver blocks[]: each paragraph tesseract found, with its text, confidence and bounding box.", "default": true }, "includeWords": { "title": "Words", "type": "boolean", "description": "Deliver words[]: every word with its confidence and bounding box. Makes records much larger.", "default": false }, "minConfidence": { "title": "Report words below confidence", "minimum": 0, "maximum": 100, "type": "integer", "description": "Count the words whose confidence (0-100) is below this value in wordsBelowMinConfidence. The text itself is never cut. 0 = off.", "default": 0 }, "psm": { "title": "Page segmentation mode", "minimum": 0, "maximum": 13, "type": "integer", "description": "Tesseract PSM: 3 = fully automatic (default), 4 = single column of variable sizes, 6 = one uniform block of text, 7 = a single line, 8 = a single word, 11 = sparse text, 13 = raw line. Try 6 for screenshots and 11 for scattered labels.", "default": 3 }, "maxPdfPages": { "title": "Max PDF pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "For PDF links: how many pages from the start to render and read (one record per page).", "default": 5 }, "maxConcurrency": { "title": "Parallel images", "minimum": 1, "maximum": 4, "type": "integer", "description": "How many images to read at the same time: one tesseract worker per slot. OCR is CPU-bound, so more slots help only with more CPU (raise the run's memory).", "default": 2 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Images are downloaded directly first. The proxy is used only to retry a download that failed on the network.", "default": { "useApifyProxy": 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 } } } } } } } } } }