{ "openapi": "3.0.1", "info": { "title": "URL to Markdown — Clean LLM-Ready Markdown from Any Web Page", "description": "Convert web pages and PDF links to clean Markdown for ChatGPT, Claude, RAG and AI agents. Main-content extraction, metadata, token counts and optional chunks; Chrome only when a page needs JavaScript. From $0.001 per page.", "version": "1.0", "x-build-id": "ENj1uQoIKbJxQ82Rf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/reverend_sal~url-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-reverend_sal-url-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/reverend_sal~url-to-markdown/runs": { "post": { "operationId": "runs-sync-reverend_sal-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/reverend_sal~url-to-markdown/run-sync": { "post": { "operationId": "run-sync-reverend_sal-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": { "urls": { "title": "URLs", "type": "array", "description": "Web pages (or PDF links) to convert. Add a crawl depth below to also convert the pages they link to.", "default": [ { "url": "https://en.wikipedia.org/wiki/Markdown" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "renderMode": { "title": "Rendering", "enum": [ "auto", "http", "browser" ], "type": "string", "description": "Auto = fast HTTP fetch, and a real Chrome browser only for JavaScript-rendered pages (React/Vue/Next shells) or pages that block plain HTTP. HTTP only = never use a browser (cheapest). Browser = always render in Chrome.", "default": "auto" }, "mainContentOnly": { "title": "Main content only", "type": "boolean", "description": "Extract the article/main content (Mozilla Readability) and drop menus, headers, footers, cookie banners and sidebars. Turn off to convert the whole page.", "default": true }, "includeLinks": { "title": "Keep links", "type": "boolean", "description": "Keep hyperlinks as Markdown links with absolute URLs. Turn off for plain text with fewer tokens.", "default": true }, "includeImages": { "title": "Keep images", "type": "boolean", "description": "Keep images as ![alt](url) with absolute URLs.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Also split the Markdown into chunks of at most this many characters on paragraph boundaries, each with its nearest heading — ready for embeddings/RAG. 0 = no chunks. Chunking is free.", "default": 0 }, "crawlDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "0 = only the URLs above. 1 = also convert pages they link to, 2 = links of those, … Only same-site links are followed.", "default": 0 }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Upper limit on pages converted in this run (start URLs + crawled pages). Also caps cost.", "default": 50 }, "sameUrlPrefixOnly": { "title": "Stay under the start URL path", "type": "boolean", "description": "When crawling, only follow links under the start URL's folder (e.g. start at https://docs.site.com/guide/ → only /guide/… pages).", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "When crawling, skip pages disallowed by the site's robots.txt. Start URLs are always converted.", "default": true }, "maxPdfPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "PDF links are converted too (charged per PDF page). Stop after this many pages of each PDF.", "default": 50 }, "maxConcurrency": { "title": "Parallel pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pages processed at the same time.", "default": 5 }, "timeoutSecs": { "title": "Page timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Give up on a page after this long.", "default": 30 } } }, "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 } } } } } } } } } }