{ "openapi": "3.0.1", "info": { "title": "PDF & Scan to Markdown with OCR", "description": "Convert PDFs, scanned documents, images and Word files to clean Markdown or plain text. Keeps headings, lists and tables, and runs OCR only on pages that have no text layer.", "version": "1.0", "x-build-id": "MLMuaNkXE2EDrtenG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ensorcelling_melilot~doc-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ensorcelling_melilot-doc-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ensorcelling_melilot~doc-to-markdown/runs": { "post": { "operationId": "runs-sync-ensorcelling_melilot-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ensorcelling_melilot~doc-to-markdown/run-sync": { "post": { "operationId": "run-sync-ensorcelling_melilot-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "documentUrls" ], "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Links to the documents to convert, one per line. PDF (text or scanned), images (PNG, JPG, TIFF, GIF, BMP, WebP), Word .docx and plain text files are supported.", "items": { "type": "string" } }, "ocrMode": { "title": "OCR for scanned pages", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto reads the text layer and runs OCR only on pages that have none (scans). Always forces OCR on every page, useful when a PDF's hidden text is wrong. Never skips OCR and only reads real text layers.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages of the scanned text. Several can be combined for mixed documents. Supported: eng, deu, fra, spa, ita, por, nld. Defaults to English.", "default": [ "eng" ], "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps headings, lists and tables. Plain text strips the formatting. Both returns two fields.", "default": "markdown" }, "pageRange": { "title": "Pages to convert", "type": "string", "description": "For PDFs, only convert these pages, for example 1-5,8,12-. Leave empty to convert every page. You are charged only for converted pages." }, "includePageDetails": { "title": "Include page-by-page output", "type": "boolean", "description": "Adds a pageDetails list to each result with the Markdown, the method used (text layer or OCR) and the character count for every page.", "default": false }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stops reading a document after this many pages. A safety limit for very large files.", "default": 500 }, "maxDocuments": { "title": "Max documents", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Converts at most this many of the URLs you give.", "default": 100 }, "maxFileSizeMB": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Documents larger than this are skipped and not charged for.", "default": 50 }, "concurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many documents are converted at the same time. OCR is CPU heavy, so a small number is best.", "default": 2 }, "requestHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional headers sent when downloading each document, for example a Referer or Cookie for sites that check them." } } }, "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 } } } } } } } } } }