{ "openapi": "3.0.1", "info": { "title": "OCR to Markdown: Scanned PDFs & Images to Text for AI", "description": "OCR scanned PDFs and images (PNG, JPG, TIFF) into clean Markdown or text for LLMs and RAG. 26 languages, auto-rotation, noise and table-line cleanup, smart mode that only OCRs pages that need it. Failed files are not charged.", "version": "0.0", "x-build-id": "9NKQwW7W8ACRP9WQD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bigochelo~ocr-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bigochelo-ocr-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bigochelo~ocr-to-markdown/runs": { "post": { "operationId": "runs-sync-bigochelo-ocr-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bigochelo~ocr-to-markdown/run-sync": { "post": { "operationId": "run-sync-bigochelo-ocr-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "File URLs (PDF or images)", "type": "array", "description": "Public links to scanned PDFs or images (PNG, JPG, TIFF, WEBP, GIF, BMP), one per line. Example: [\"https://example.com/scan.pdf\"]. Google Drive, Dropbox and GitHub share links are converted automatically.", "items": { "type": "string" } }, "languages": { "title": "Document languages", "type": "array", "description": "Languages in the documents (combine them for mixed documents). Accepts codes or names, e.g. [\"eng\", \"spa\"] or [\"en\", \"es\"]. Available: eng, spa, por, fra, deu, ita, nld, dan, swe, nor, fin, pol, ces, ron, hun, tur, rus, ukr, ell, ara, hin, chi_sim, jpn, kor, vie, ind.", "default": [ "eng" ], "items": { "type": "string" } }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always" ], "type": "string", "description": "\"auto\" (default): pages that already contain digital text are read directly (cheaper, exact) and only scanned pages are OCR'd. \"always\": OCR every page.", "default": "auto" }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "\"markdown\" (default, keeps headings and lists; best for LLMs), \"text\" (plain text) or \"both\".", "default": "markdown" }, "includePages": { "title": "Include per-page results", "type": "boolean", "description": "If true, adds a 'pages' array with each page's text, method (ocr or text-layer) and OCR confidence.", "default": false }, "chunking": { "title": "Split into RAG chunks", "type": "boolean", "description": "If true, adds a 'chunks' array: heading-aware pieces ready for embeddings / vector databases.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Maximum characters per chunk (about 4 characters per token).", "default": 1500 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated between consecutive chunks.", "default": 150 }, "aiSafety": { "title": "AI safety scan (prompt injection)", "type": "boolean", "description": "Removes text a human cannot see (white-on-white, tiny or off-page text in digital PDF pages) and reports hidden instructions aimed at AI, invisible characters and data-exfiltration links in an 'aiSafety' object. OCR only reads what is visible on scanned pages. Free and on by default.", "default": true }, "wrapAsUntrusted": { "title": "Wrap output as untrusted data", "type": "boolean", "description": "If true, the Markdown is wrapped in tags telling the LLM to treat it as data, not instructions.", "default": false }, "autoRotate": { "title": "Fix rotated pages", "type": "boolean", "description": "Detects pages scanned sideways or upside down and straightens them before OCR.", "default": true }, "dpi": { "title": "Scan resolution for PDFs (DPI)", "minimum": 150, "maximum": 400, "type": "integer", "description": "Resolution used to render scanned PDF pages. 300 is best for most documents; use 400 for very small print.", "default": 300 }, "maxPages": { "title": "Max pages per file", "minimum": 0, "type": "integer", "description": "Only process the first N pages of each file. 0 = all pages.", "default": 300 }, "password": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs (applied to all files in this run)." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 100 } } }, "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 } } } } } } } } } }