{ "openapi": "3.0.1", "info": { "title": "Document & PDF to Markdown for LLMs: Word, Excel, OCR", "description": "Convert PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX), CSV and HTML files into clean, LLM-ready Markdown and JSON. Keeps headings, lists and tables, outputs per-page chunks for RAG and vector databases, and OCRs scanned PDFs and images. Failed files are free. $3 per 1,000 pages.", "version": "0.1", "x-build-id": "jnqUXOadzcgEFXFsn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/magenta_waterwheel~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-magenta_waterwheel-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/magenta_waterwheel~document-to-markdown/runs": { "post": { "operationId": "runs-sync-magenta_waterwheel-document-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/magenta_waterwheel~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-magenta_waterwheel-document-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": [ "startUrls" ], "properties": { "startUrls": { "title": "Document URLs", "type": "array", "description": "Direct links to documents: PDF, DOCX, PPTX, XLSX, CSV, HTML, TXT, Markdown, or images (PNG, JPEG, TIFF) for OCR. Google Drive, Google Docs and Dropbox share links are converted to download links automatically. You can paste many links at once or upload a text file.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "pageRange": { "title": "Page range", "type": "string", "description": "Pages to extract, for example \"1-5, 8, 20-\". Applies to PDF pages, PowerPoint slides and the sections of other formats. Leave empty for all pages.", "default": "" }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Stop after this many pages of each document. Protects you from paying for unexpectedly huge files.", "default": 1000 }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto runs OCR only on pages with no usable text layer (scanned pages, broken fonts). Always runs OCR on every page. Never skips OCR. OCR pages are billed at the OCR page price.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages in the scanned documents. Adding more languages makes OCR slower; pick only those you need.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "por", "ita", "nld" ], "enumTitles": [ "English", "German", "French", "Spanish", "Portuguese", "Italian", "Dutch" ] }, "default": [ "eng" ] }, "includeTables": { "title": "Extract tables", "type": "boolean", "description": "Convert tables in PDFs to Markdown tables. Word, PowerPoint, Excel and HTML tables are always kept.", "default": true }, "removeHeadersFooters": { "title": "Remove repeating headers and footers", "type": "boolean", "description": "Drop text that repeats at the top or bottom of most PDF pages, such as running titles and page numbers.", "default": true }, "includeSpeakerNotes": { "title": "Include speaker notes", "type": "boolean", "description": "Add PowerPoint speaker notes under each slide.", "default": true }, "includeLinks": { "title": "Keep links", "type": "boolean", "description": "Keep hyperlinks as Markdown links in Word and HTML documents. Turn off for plain text with fewer tokens.", "default": true }, "htmlMainContentOnly": { "title": "HTML: main content only", "type": "boolean", "description": "For HTML pages, keep only the main article or content area and drop menus, sidebars, language lists and footers. Turn off to convert the whole page.", "default": true }, "outputMode": { "title": "Output mode", "enum": [ "document", "page" ], "type": "string", "description": "One dataset item per document (full Markdown plus a per-page array), or one item per page, which suits vector databases and RAG pipelines.", "default": "document" }, "includePages": { "title": "Include per-page chunks", "type": "boolean", "description": "In document mode, add a pages array with the Markdown of each page. Turn off to get only the full Markdown.", "default": true }, "saveMarkdownFiles": { "title": "Save .md files", "type": "boolean", "description": "Also save each document as a .md file in the key-value store and add a download link (markdownFileUrl).", "default": false }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip files larger than this. Files above 50 MB may need more memory.", "default": 50 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many documents to download and process at the same time.", "default": 2 }, "downloadTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Give up on a download after this many seconds without progress.", "default": 60 } } }, "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 } } } } } } } } } }