{
"openapi": "3.0.1",
"info": {
"title": "Webpage to Markdown – HTML to Markdown for LLM & RAG",
"description": "Turn web pages into clean Markdown for LLMs and RAG: main content only, no nav or footer, links resolved to full URLs, token count per page. Opens a browser only for JavaScript pages. $1 per 1,000 pages; failed pages are free.",
"version": "0.1",
"x-build-id": "E5av96N6I6mKVTcX1"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/tidyrun~webpage-to-markdown/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-tidyrun-webpage-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/tidyrun~webpage-to-markdown/runs": {
"post": {
"operationId": "runs-sync-tidyrun-webpage-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/tidyrun~webpage-to-markdown/run-sync": {
"post": {
"operationId": "run-sync-tidyrun-webpage-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": "Pages to convert. You can also upload a text file with one URL per line.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"datasetId": {
"title": "Take URLs from a dataset",
"type": "string",
"description": "Optional dataset, for example from a scraper run. Its page links are read together with the URLs above, and each row keeps the dataset record index. When connected as an integration after a scraper, use {{resource.defaultDatasetId}}."
},
"urlField": {
"title": "URL field in the dataset",
"type": "string",
"description": "Field that holds the page link: a URL, a list of URLs, or objects with url/href. Dot paths work: results.0.url, or results.url for every link in a list. Leave empty and only the row’s own address is used (a top-level url, link or loadedUrl), so a scraper’s outbound links are never read by accident."
},
"mainContentOnly": {
"title": "Main content only",
"type": "boolean",
"description": "Keep the article and drop the navigation, header, footer, sidebars and share buttons. Turn this off to convert the whole page.",
"default": true
},
"render": {
"title": "Run JavaScript",
"enum": [
"auto",
"always",
"never"
],
"type": "string",
"description": "Most pages ship their text in the HTML and need no browser, which is much faster and cheaper. Auto starts there and opens a browser only when the page turns out to be a JavaScript shell.",
"default": "auto"
},
"includeLinks": {
"title": "Keep links",
"type": "boolean",
"description": "Keep [text](url) links, with relative URLs resolved to full ones. Turn off for plain prose.",
"default": true
},
"includeImages": {
"title": "Keep images",
"type": "boolean",
"description": "Keep  images. Off by default because image lines waste tokens in an LLM prompt.",
"default": false
},
"maxCharacters": {
"title": "Max characters per page",
"minimum": 0,
"maximum": 2000000,
"type": "integer",
"description": "Cut each page's Markdown to this length to fit a context window. Leave empty for the whole page."
},
"dedupe": {
"title": "Skip duplicates",
"type": "boolean",
"description": "Read a repeated URL once instead of paying for it twice. The row lists every dataset record it came from.",
"default": true
},
"timeoutSecs": {
"title": "Timeout",
"minimum": 5,
"maximum": 300,
"type": "integer",
"description": "How long to wait for one page.",
"default": 45
}
}
},
"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
}
}
}
}
}
}
}
}
}
}