{
"openapi": "3.0.1",
"info": {
"title": "Crawl4AI Web to Markdown — URL to Clean Markdown for LLM & RAG",
"description": "Convert any URL, sitemap, or whole website into clean Markdown for LLMs, RAG pipelines, and AI agents. Powered by the open-source Crawl4AI engine. Pay per page ($1/1,000), failed pages never charged. MCP-ready — call it from Claude or Cursor.",
"version": "0.1",
"x-build-id": "cnJO0n1KE2WZiRU2e"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/bikram07~web-to-markdown-crawl4ai/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-bikram07-web-to-markdown-crawl4ai",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/bikram07~web-to-markdown-crawl4ai/runs": {
"post": {
"operationId": "runs-sync-bikram07-web-to-markdown-crawl4ai",
"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/bikram07~web-to-markdown-crawl4ai/run-sync": {
"post": {
"operationId": "run-sync-bikram07-web-to-markdown-crawl4ai",
"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": "Start URLs",
"type": "array",
"description": "URLs to convert to Markdown. In single mode each URL is converted as-is. In sitemap mode each URL is treated as (or resolved to) a sitemap.xml. In crawl mode each URL is the starting point of a same-domain crawl.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"crawlMode": {
"title": "Crawl mode",
"enum": [
"single",
"sitemap",
"crawl"
],
"type": "string",
"description": "single — convert only the listed URLs. sitemap — load each site's sitemap.xml and convert the pages it lists (up to Max pages). crawl — follow same-domain links from each start URL (breadth-first, up to Max pages).",
"default": "single"
},
"maxPages": {
"title": "Max pages",
"minimum": 1,
"maximum": 1000,
"type": "integer",
"description": "Maximum number of pages to convert across the whole run. Hard limit: 1000. You are only charged for pages that convert successfully.",
"default": 10
},
"includeLinks": {
"title": "Keep hyperlinks in Markdown",
"type": "boolean",
"description": "When enabled, hyperlinks are preserved in the Markdown output. Disable for cleaner text aimed at embeddings/RAG chunking.",
"default": false
},
"outputFormat": {
"title": "Output format",
"enum": [
"markdown",
"markdown+html",
"markdown+json"
],
"type": "string",
"description": "markdown — Markdown only (smallest items). markdown+html — also include the cleaned HTML. markdown+json — also include page metadata and extracted link lists.",
"default": "markdown"
},
"removeBoilerplate": {
"title": "Remove boilerplate",
"type": "boolean",
"description": "Use Crawl4AI's pruning content filter to strip navigation, footers, cookie banners and other boilerplate, producing 'fit markdown' optimized for LLM context windows.",
"default": true
},
"respectRobotsTxt": {
"title": "Respect robots.txt",
"type": "boolean",
"description": "Skip pages disallowed by the site's robots.txt. Skipped pages are not charged.",
"default": true
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Optionally route browser traffic through Apify Proxy or custom proxies. Not required for most public sites."
}
}
},
"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
}
}
},
"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
}
}
}
}
}
}
}
}
}
}