{
"openapi": "3.0.1",
"info": {
"title": "PDF to Markdown – DOCX, PPTX, XLSX & HTML for LLM & RAG",
"description": "Convert PDF to Markdown, plus Word (DOCX), PowerPoint (PPTX), Excel (XLSX/CSV) and HTML documents, into clean LLM-ready Markdown or plain text. Keeps headings, lists and tables, adds metadata and RAG chunking (per page or by tokens with overlap). Pay only per page.",
"version": "1.0",
"x-build-id": "Zwuc3EwyQrjgqKKCU"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/openharvest~document-to-markdown/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-openharvest-document-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/openharvest~document-to-markdown/runs": {
"post": {
"operationId": "runs-sync-openharvest-document-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/openharvest~document-to-markdown/run-sync": {
"post": {
"operationId": "run-sync-openharvest-document-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"fileUrls": {
"title": "Document URLs",
"type": "array",
"description": "Direct links to documents: PDF, DOCX, PPTX, XLSX/XLS/ODS, CSV, HTML web pages, TXT or MD. The type is detected from the file content, so URLs without an extension work too. Example: https://arxiv.org/pdf/1706.03762.",
"items": {
"type": "string"
}
},
"files": {
"title": "Uploaded files",
"type": "array",
"description": "Optional. Upload documents from your computer (they are stored in an Apify key-value store) - or enter keys of records in this run's default key-value store."
},
"outputFormat": {
"title": "Output format",
"enum": [
"markdown",
"text",
"both"
],
"type": "string",
"description": "markdown keeps headings, lists, tables and links (best for LLMs). text is plain text without Markdown syntax. both returns both fields.",
"default": "markdown"
},
"chunking": {
"title": "Chunking (for RAG)",
"enum": [
"none",
"page",
"tokens"
],
"type": "string",
"description": "none: one dataset item per document. page: one item per PDF page / slide / sheet (DOCX and HTML are split at H1/H2 headings). tokens: chunks of about Chunk size tokens with overlap, ready for embeddings. Chunking does not change the price.",
"default": "none"
},
"chunkSize": {
"title": "Chunk size (tokens)",
"minimum": 50,
"maximum": 32000,
"type": "integer",
"description": "Target chunk size in tokens (estimated as 4 characters per token) when Chunking = tokens. Chunks break on paragraph boundaries where possible.",
"default": 1000
},
"chunkOverlap": {
"title": "Chunk overlap (tokens)",
"minimum": 0,
"maximum": 16000,
"type": "integer",
"description": "How many tokens from the end of one chunk are repeated at the start of the next (Chunking = tokens). Max half of the chunk size.",
"default": 100
},
"pageRange": {
"title": "Page range",
"type": "string",
"description": "Optional. Convert only these pages (PDF), slides (PPTX) or sheets (XLSX), e.g. 1-5, 1,3,7-9 or 10-. Empty = all. Ignored for DOCX and HTML."
},
"maxPages": {
"title": "Max pages per document",
"minimum": 0,
"type": "integer",
"description": "Upper limit of pages / slides / sheets converted per document (DOCX and HTML: estimated pages). You pay per page, so this also caps your cost. 0 = no limit.",
"default": 200
},
"includeTables": {
"title": "Tables as Markdown tables",
"type": "boolean",
"description": "Render tables from DOCX, PPTX, XLSX and HTML as GitHub-flavoured Markdown tables. If off, table rows are output as tab-separated lines.",
"default": true
},
"includeSpeakerNotes": {
"title": "Include PowerPoint speaker notes",
"type": "boolean",
"description": "Append the speaker notes of each slide (PPTX) as a quote block.",
"default": true
},
"extractMainContent": {
"title": "HTML: main content only",
"type": "boolean",
"description": "For web pages, keep only the main article (Mozilla Readability) and drop navigation, menus, footers and ads. Turn off to convert the whole page.",
"default": true
},
"maxRowsPerSheet": {
"title": "Max rows per sheet",
"minimum": 1,
"type": "integer",
"description": "Spreadsheets: convert at most this many non-empty rows per sheet (protects you from giant tables).",
"default": 5000
},
"maxFileSizeMb": {
"title": "Max file size (MB)",
"minimum": 1,
"maximum": 500,
"type": "integer",
"description": "Skip files larger than this (reported as a free error item).",
"default": 100
}
}
},
"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
}
}
}
}
}
}
}
}
}
}