{ "openapi": "3.0.1", "info": { "title": "Any URL to Markdown — Web Pages, PDF, Word, Excel & OCR", "description": "Turn any URL into clean, LLM-ready Markdown: web pages, PDFs, Word, Excel, PowerPoint, EPUB, CSV and JSON, plus OCR for images and scanned PDFs. One url in, Markdown plus a token estimate out. Built for AI agents, MCP, RAG, Clay and n8n. From $1 per 1,000 pages.", "version": "0.1", "x-build-id": "bqqRgvsWbzAhY93FI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~any-url-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-any-url-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~any-url-to-markdown/runs": { "post": { "operationId": "runs-sync-actor-forge-any-url-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/actor-forge~any-url-to-markdown/run-sync": { "post": { "operationId": "run-sync-actor-forge-any-url-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", "properties": { "url": { "title": "URL", "type": "string", "description": "One link to convert: a web page, PDF, Word (.docx), Excel (.xlsx), PowerPoint (.pptx), OpenDocument, EPUB, CSV, JSON or image. The file type is detected automatically." }, "urls": { "title": "More URLs", "type": "array", "description": "Optional: more links to convert in the same run (up to 1,000 in total, duplicates removed).", "items": { "type": "string" } }, "includeText": { "title": "Also return plain text", "type": "boolean", "description": "Add a text field with the Markdown syntax removed.", "default": false }, "onlyMainContent": { "title": "Web pages: main content only", "type": "boolean", "description": "Keep only the article or main content of web pages (navigation, footers and cookie banners removed). Turn off to convert the whole page body.", "default": true }, "ocr": { "title": "OCR images and scanned PDFs", "type": "boolean", "description": "Read text from images (PNG, JPEG, TIFF, WebP, GIF, BMP) and from PDF pages that have no text layer, with Tesseract OCR. Turn off to never pay for OCR: images and scanned pages are then reported as errors (free).", "default": true }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages in your scanned documents (up to 3). For 29 languages and word boxes use the OCR to Text actor.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch" ] }, "default": [ "eng" ] }, "maxOcrPages": { "title": "Max OCR pages per PDF", "minimum": 1, "maximum": 200, "type": "integer", "description": "Upper limit of scanned pages read by OCR in one PDF ($0.003 each). Pages beyond it are left out and the row is marked truncated.", "default": 20 }, "maxPdfPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Read at most this many pages of each PDF.", "default": 500 }, "maxRowsPerSheet": { "title": "Max rows per spreadsheet sheet", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Excel, OpenDocument and CSV tables are cut after this many rows (marked truncated).", "default": 1000 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs that the site's robots.txt disallows. It is checked before every request: web pages, direct file links and every redirect target. A robots.txt that answers with a server error counts as disallow-all (RFC 9309).", "default": 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 } } } } } } } } } }