Web to Markdown — Clean, LLM-Ready Markdown from Web Pages
Pricing
from $3.00 / 1,000 page converteds
Web to Markdown — Clean, LLM-Ready Markdown from Web Pages
Pricing
from $3.00 / 1,000 page converteds
You can access the Web to Markdown — Clean, LLM-Ready Markdown from Web Pages programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.2", "x-build-id": "tRWqB8MaHen9yzdaP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abdou_009~apify-web-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abdou_009-apify-web-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/abdou_009~apify-web-to-markdown/runs": { "post": { "operationId": "runs-sync-abdou_009-apify-web-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/abdou_009~apify-web-to-markdown/run-sync": { "post": { "operationId": "run-sync-abdou_009-apify-web-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": { "startUrls": { "title": "Start URLs", "minItems": 1, "type": "array", "description": "Pages to convert. In site mode the first URL is the crawl seed; in sitemap mode its domain is used to find sitemaps.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlMode": { "title": "Crawl mode", "enum": [ "single", "site", "sitemap" ], "type": "string", "description": "Single converts only the supplied URLs. Site follows same-domain links. Sitemap reads sitemap.xml (and nested sitemap indexes).", "default": "single" }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on pages fetched and converted. The Actor stops cleanly when the cap is reached.", "default": 10 }, "maxDepth": { "title": "Maximum link depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many link hops to follow from the start URL in site mode (0 = only the start URL).", "default": 2 }, "includeGlobs": { "title": "Include URL globs", "type": "array", "description": "Optional glob patterns; when set, only matching URLs are crawled. Example: **/docs/**", "items": { "type": "string" }, "default": [] }, "excludeGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Glob patterns for URLs to skip, for example **/tags/**, **/login/** or **/*.pdf.", "items": { "type": "string" }, "default": [] }, "renderingMode": { "title": "Rendering mode", "enum": [ "auto", "static", "browser" ], "type": "string", "description": "Auto uses fast static HTTP and falls back to Playwright only when the page looks JavaScript-driven. Static never opens a browser. Browser always renders with Playwright.", "default": "auto" }, "extractMainContentOnly": { "title": "Main content only", "type": "boolean", "description": "Extract the article/main content and remove navigation, sidebars, footers, cookie banners and ads. Turn off to keep the cleaned full body.", "default": true }, "includeLinks": { "title": "Keep links", "type": "boolean", "description": "Preserve hyperlinks as absolute Markdown links. Turn off to keep only the link text.", "default": true }, "includeImages": { "title": "Keep images", "type": "boolean", "description": "Preserve images as absolute Markdown image references. Off by default for lean, text-focused LLM context.", "default": false }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "markdown+metadata" ], "type": "string", "description": "Markdown only returns the body. Markdown + metadata adds YAML front matter (title, author, dates, canonical URL, word/token counts).", "default": "markdown+metadata" }, "chunking": { "title": "RAG chunking", "type": "object", "description": "Split Markdown into overlapping chunks for embeddings using the tiktoken cl100k_base tokenizer. maxTokens is a hard token cap; overlap must be smaller than maxTokens.", "default": { "enabled": false, "maxTokens": 800, "overlap": 100 } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Obey robots.txt disallow rules, crawl delays and sitemap declarations. Keep this on unless you have explicit permission to ignore them.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy configuration for geo-restricted or rate-limited sites. Disabled by default so local runs need no account.", "default": { "useApifyProxy": false } }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel requests. Browser rendering is capped lower internally to keep runs stable.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for a single page load in seconds.", "default": 30 }, "maxRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries per URL for transient network and HTTP errors, with exponential backoff.", "default": 3 }, "urls": { "title": "URLs (legacy)", "type": "string", "description": "DEPRECATED — kept for backward compatibility with v1 integrations. One URL per line. Use 'Start URLs' (startUrls) instead; if startUrls is empty, this field is mapped onto it." }, "maxChars": { "title": "Max characters per page (legacy)", "minimum": 100, "maximum": 200000, "type": "integer", "description": "DEPRECATED — kept for backward compatibility with v1 integrations. Truncates each page's Markdown to this many characters. In legacy mode (when you use 'urls') it defaults to 20000, as v1 did." } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Web to Markdown — Clean, LLM-Ready Markdown from Web Pages from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: