{ "openapi": "3.0.1", "info": { "title": "PDF, Word & PowerPoint to Text/Markdown [$3/1K 💰]", "description": "💰 $3 per 1,000 documents, no start fee; failed and no-text files free. PDF, Word (DOCX) and PowerPoint (PPTX) to clean text and Markdown with headings, lists and tables kept, page rows and RAG chunks. Cheaper than memo23's PDF extractor ($5/1K + start fee). Changed-files monitor.", "version": "0.1", "x-build-id": "un61OU34sFi2MqVgS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cybermax~pdf-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cybermax-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cybermax~pdf-to-text/runs": { "post": { "operationId": "runs-sync-cybermax-pdf-to-text", "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/cybermax~pdf-to-text/run-sync": { "post": { "operationId": "run-sync-cybermax-pdf-to-text", "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": [ "urls" ], "properties": { "urls": { "title": "Document URLs", "type": "array", "description": "Direct links to PDF, Word (.docx) or PowerPoint (.pptx) files. Links to files in an Apify key-value store work too.", "items": { "type": "string" } }, "formats": { "title": "Output formats", "type": "array", "description": "Markdown keeps headings, bullet lists and tables; plain text is clean reading order.", "items": { "type": "string", "enum": [ "markdown", "text" ], "enumTitles": [ "Markdown (headings, lists, tables)", "Plain text" ] }, "default": [ "markdown", "text" ] }, "outputMode": { "title": "One row per", "enum": [ "document", "pages" ], "type": "string", "description": "Per-page rows carry a page number, handy for citations. You pay per document either way.", "default": "document" }, "pageRange": { "title": "Pages", "type": "string", "description": "Optional, e.g. 1-5, 8, 12-. Empty = all pages (up to Max pages)." }, "maxPages": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Pages read per document at most; you pay per document either way.", "default": 500 }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Optional. Adds a chunks array split at paragraph and sentence ends, ready for embeddings. 0 = off." }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated between neighbouring chunks.", "default": 150 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Larger files are skipped and reported, not charged.", "default": 100 }, "monitor": { "title": "Monitor mode: changed documents only", "type": "boolean", "description": "Returns only documents that are new or whose file changed since the last monitor run with the same URL list. Unchanged documents are not charged.", "default": false }, "monitorKey": { "title": "Watchlist name", "type": "string", "description": "Optional name for this watchlist's saved state." } } }, "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 } } } } } } } } } }