{ "openapi": "3.0.1", "info": { "title": "PDF to Text & Markdown Converter with OCR (DOCX, Images)", "description": "Use this when you need text or LLM-ready Markdown from a PDF, DOCX or image URL, incl. scanned pages (OCR, 27 languages). $0.003/document + $0.0003/text page (first 30) or $0.005/OCR page. Input: {\"url\":\"https://arxiv.org/pdf/1706.03762\"}. Output: markdown, text, pageCount, ocrPages, metadata.", "version": "1.0", "x-build-id": "PdwDQFTYkfEQoaiX6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/poised_beardlichen~pdf-to-text-markdown-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-poised_beardlichen-pdf-to-text-markdown-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/poised_beardlichen~pdf-to-text-markdown-ocr/runs": { "post": { "operationId": "runs-sync-poised_beardlichen-pdf-to-text-markdown-ocr", "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/poised_beardlichen~pdf-to-text-markdown-ocr/run-sync": { "post": { "operationId": "run-sync-poised_beardlichen-pdf-to-text-markdown-ocr", "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": { "url": { "title": "Single document URL (optional)", "type": "string", "description": "Shortcut for one document URL, e.g. \"https://arxiv.org/pdf/1706.03762\". Combined with the list below; provide at least one of the two." }, "urls": { "title": "Document URLs", "minItems": 1, "maxItems": 10000, "type": "array", "description": "Direct links to PDF, DOCX or image files (PNG, JPEG, TIFF, WebP, BMP, GIF). Public Google Drive and Dropbox share links are converted automatically. Add as many as you like - they are processed in parallel. Use \"url\" instead for a single item.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "both", "markdown", "text" ], "type": "string", "description": "Markdown keeps headings, lists and paragraphs (ideal for LLMs, RAG and vector databases). Plain text keeps the original line breaks.", "default": "both" }, "outputMode": { "title": "One result per", "enum": [ "document", "page" ], "type": "string", "description": "Return one dataset item per document, or one item per page with its page number.", "default": "document" }, "ocrMode": { "title": "OCR (scanned pages)", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto detects scanned or image-only pages (and pages with broken/garbled fonts) and runs OCR only on those. Images are always OCRed.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Language(s) of scanned text. Pick 1-3 for best accuracy and speed; English is used if empty.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "swe", "dan", "nor", "fin", "ces", "tur", "rus", "ukr", "ell", "ara", "heb", "hin", "vie", "ind", "tha", "chi_sim", "chi_tra", "jpn", "kor" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Swedish", "Danish", "Norwegian", "Finnish", "Czech", "Turkish", "Russian", "Ukrainian", "Greek", "Arabic", "Hebrew", "Hindi", "Vietnamese", "Indonesian", "Thai", "Chinese (Simplified)", "Chinese (Traditional)", "Japanese", "Korean" ] }, "default": [ "eng" ] }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Render resolution for OCR. 200 is the best balance; use 300 for tiny print, 150 for large, clean scans.", "default": 200 }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Stop after this many pages of each document (0 = all pages). Useful to cap cost on huge files.", "default": 0 }, "startPage": { "title": "Start page", "minimum": 1, "maximum": 100000, "type": "integer", "description": "First page to extract (PDF only).", "default": 1 }, "includePages": { "title": "Include per-page text", "type": "boolean", "description": "In document mode, also add a 'pages' array with the text/markdown of every page.", "default": false }, "pageMarkers": { "title": "Page markers in Markdown", "type": "boolean", "description": "Insert comments into the Markdown so you can cite page numbers.", "default": false }, "removeHeadersFooters": { "title": "Remove repeating headers & footers", "type": "boolean", "description": "Drop running heads, footers and page numbers that repeat on most pages.", "default": true }, "saveFiles": { "title": "Also save .md / .txt files", "type": "boolean", "description": "Store each document's Markdown and text as files in the key-value store and return download links. Very large documents are always saved as files.", "default": false }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped (not charged).", "default": 100 }, "maxConcurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many documents to download and convert at the same time.", "default": 4 } } }, "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 } } } } } } } } } }