{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown", "description": "PDF to Markdown converter API for RAG and LLMs: clean Markdown, plain text or JSON chunks with page numbers. Tables, multi-column layouts, OCR for scanned pages. $0.002 per PDF + $0.00025 per page; failures are free.", "version": "1.0", "x-build-id": "IcWx3MQupnuZfh73T" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jcwilk~pdf-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jcwilk-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/jcwilk~pdf-to-markdown/runs": { "post": { "operationId": "runs-sync-jcwilk-pdf-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/jcwilk~pdf-to-markdown/run-sync": { "post": { "operationId": "run-sync-jcwilk-pdf-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": "PDF URLs", "type": "array", "description": "Direct links to PDF files. Redirects are followed.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "file": { "title": "Upload a PDF", "type": "string", "description": "Upload a PDF from your computer (stored in the run's key-value store)." }, "base64Files": { "title": "Base64 PDFs (API use)", "type": "array", "description": "For API/agent callers: list of {\"name\": \"a.pdf\", \"data\": \"\"} objects or base64 strings." }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "json" ], "type": "string", "description": "markdown = Markdown with headings, lists and tables. text = plain text. json = Markdown plus RAG chunks and per-page Markdown with page metadata.", "default": "markdown" }, "chunking": { "title": "Split into RAG chunks", "type": "boolean", "description": "Add heading-aware chunks (with page range and heading path) ready for embedding. Always on for JSON output.", "default": false }, "chunkSize": { "title": "Chunk size (approx. tokens)", "minimum": 50, "maximum": 8000, "type": "integer", "description": "Target chunk size in tokens (1 token ≈ 4 characters).", "default": 512 }, "chunkOverlap": { "title": "Chunk overlap (approx. tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Trailing paragraphs repeated at the start of the next chunk, up to this many tokens.", "default": 64 }, "ocr": { "title": "OCR for scanned pages", "enum": [ "auto", "off", "force" ], "type": "string", "description": "auto = OCR only pages with no text layer (recommended). off = never OCR (fastest, cheapest). force = OCR every page.", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "type": "string", "description": "Tesseract language code(s), e.g. eng, deu, fra, spa, ita, por, nld, or combined: eng+deu.", "default": "eng" }, "pageRange": { "title": "Page range", "type": "string", "description": "Pages to convert, e.g. 1-5,8,10-. Empty = all pages. You are only charged for converted pages." }, "tables": { "title": "Tables", "enum": [ "markdown", "text", "skip" ], "type": "string", "description": "markdown = convert detected tables to Markdown tables. text = tab-separated rows. skip = don't detect tables (faster).", "default": "markdown" }, "imageCaptions": { "title": "Image placeholders with captions", "type": "boolean", "description": "Insert ![caption](page-N-image-M) placeholders where images appear, using the nearby 'Figure ...' caption text. Off by default.", "default": false }, "removeHeadersFooters": { "title": "Remove repeated headers/footers", "type": "boolean", "description": "Drop running headers, footers and page numbers repeated on most pages.", "default": true }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "type": "integer", "description": "Safety cap on pages converted per PDF.", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Max file size (MB).", "default": 100 }, "maxConcurrency": { "title": "Max parallel documents", "minimum": 1, "maximum": 16, "type": "integer", "description": "Max parallel documents.", "default": 2 } } }, "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 } } } } } } } } } }