{
"openapi": "3.0.1",
"info": {
"title": "PDF to Markdown Converter: Word, Excel, PPT & OCR for LLMs",
"description": "Convert PDF, Word, Excel, PowerPoint, HTML and scans to clean Markdown or JSON for LLMs, RAG pipelines and AI agents. Keeps headings and tables, runs OCR only on scanned pages, returns a page map for citations. $0.002 per page, failed files free.",
"version": "1.0",
"x-build-id": "PCL0QmYmMYo6xotdS"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/tinplatelabs~document-to-markdown/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-tinplatelabs-document-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/tinplatelabs~document-to-markdown/runs": {
"post": {
"operationId": "runs-sync-tinplatelabs-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/tinplatelabs~document-to-markdown/run-sync": {
"post": {
"operationId": "run-sync-tinplatelabs-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",
"required": [
"sources"
],
"properties": {
"sources": {
"title": "Documents",
"type": "array",
"description": "Documents to convert to Markdown, one per line: PDF (digital or scanned), Word (DOCX), Excel (XLSX), PowerPoint (PPTX), HTML pages, CSV/TXT and images (read with OCR). Mix formats freely. Each is either a public http(s) URL of the file, or a record in an Apify key-value store: kvs://KEY (the store picked below, or this run's store) or kvs://STORE_ID_OR_NAME/KEY. Signed Apify record URLs (with ?signature=) work too. Other stores can be read only when picked in Key-value store. Only the exact URL is fetched; links inside documents are never followed. Supported: PDF, DOCX, XLSX, PPTX, HTML, CSV, TXT/Markdown, PNG, JPEG, TIFF, BMP, GIF, WebP. Max 50 MB per file, 1,000 sources per run.",
"items": {
"type": "string"
}
},
"keyValueStoreId": {
"title": "Key-value store",
"type": "string",
"description": "Your key-value store that holds the document files. Pick it (or paste its ID) and list its records as kvs://KEY. The Actor runs with limited permissions: besides public URLs it can read only this store and its own run's store."
},
"outputFormat": {
"title": "Output format",
"enum": [
"markdown",
"json"
],
"type": "string",
"description": "markdown: one Markdown string per document with <!-- page N --> markers, plus a page map of character offsets. json: per page, a list of typed blocks (heading, paragraph, list, table with rows as arrays, code), handy when an agent needs table cells as data.",
"default": "markdown"
},
"ocr": {
"title": "OCR",
"enum": [
"auto",
"always",
"never"
],
"type": "string",
"description": "auto (recommended): OCR only pages with no text layer (scans) and images. always: OCR every PDF page, even ones with text (slower, every page billed as an OCR page). never: no OCR; scanned pages come back empty with a warning, and image files fail.",
"default": "auto"
},
"ocrLanguages": {
"title": "OCR languages",
"type": "array",
"description": "Tesseract language codes used for OCR, most likely first. Installed: eng, deu, fra, spa, ita, por, nld, pol, ces, swe, dan, nor, fin, tur, ron, hun, rus, ukr, ell, ara, heb, hin, chi_sim, chi_tra, jpn, kor. More languages make OCR slower and slightly less accurate, so list only the ones in your documents.",
"default": [
"eng"
],
"items": {
"type": "string"
}
},
"chunkByPage": {
"title": "One dataset item per page",
"type": "boolean",
"description": "Push one dataset item per page (slide, sheet section, ...) instead of one per document. Each item repeats the document's metadata, so it's ready to embed for RAG.",
"default": false
},
"maxPages": {
"title": "Max pages per document",
"minimum": 1,
"maximum": 500,
"type": "integer",
"description": "Convert at most this many pages (or slides, or ~3,000-character sections) of each document. Pages beyond it are skipped, not billed, and the item is marked truncated. Use it to cap cost on unknown files.",
"default": 500
}
}
},
"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
}
}
}
}
}
}
}
}
}
}