{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown and Text: Tables, Pages, Metadata for RAG", "description": "PDF parser and text extractor: turn PDF URLs into clean Markdown, plain text, per-page text and detected tables. Fast, no browser, no proxy. Flags scanned pages that need OCR instead of charging for empty text. Built for RAG and document pipelines. USD 2 per 1,000 PDFs (up to 100 pages each).", "version": "1.0", "x-build-id": "06fqQLJkraVxfbaMF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jtpalms~pdf-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jtpalms-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jtpalms~pdf-to-markdown/runs": { "post": { "operationId": "runs-sync-jtpalms-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jtpalms~pdf-to-markdown/run-sync": { "post": { "operationId": "run-sync-jtpalms-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "PDF URLs", "type": "array", "description": "Links to PDF files, one per line. Each must be a public http or https address of a PDF. Duplicates are read once. The default list is three small public PDFs from US government sites.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "markdown: headings, paragraphs, lists (and tables when switched on). text: plain text with the same reading order. both: both fields.", "default": "markdown" }, "outputPages": { "title": "Text per page", "type": "boolean", "description": "Add pages[] with the text of every page read (and its Markdown, unless the format is plain text). Useful when you chunk by page.", "default": false }, "outputTables": { "title": "Detect tables", "type": "boolean", "description": "Find tables (rows of text that line up in 3 or more columns) and add them to tables[] as row arrays with a confidence, and to the Markdown as pipe tables. A heuristic: simple ruled and unruled tables work well, complex layouts may not.", "default": false }, "removeHeadersFooters": { "title": "Remove repeated headers, footers and page numbers", "type": "boolean", "description": "Drop lines at the top or bottom of the page that repeat on more than 60% of the pages, and bare page numbers. Needs at least 3 pages to spot repeats.", "default": true }, "pageRange": { "title": "Page range", "type": "string", "description": "Pages to read, for example 1-5,9 or 10- (page 10 to the end). Empty means all pages, up to the page limit. The same range is applied to every PDF." }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Pages read per PDF (1 to 2,000). When a PDF has more, the row says truncated: true. The first 100 pages are covered by the PDF price; each page beyond 100 is one extra page.", "default": 300 }, "maxFileMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "PDFs larger than this are skipped with an error row and are free. 1 to 200 MB.", "default": 50 }, "password": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs that you are entitled to open. Used only to open files, never stored or output. Without it, a PDF that asks for a password returns an error row." }, "includeAuthor": { "title": "Include the Author metadata", "type": "boolean", "description": "Adds author (the PDF's Author field, which can be a person's name). Off by default.", "default": false }, "maxConcurrency": { "title": "PDFs in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many PDFs are downloaded and read at the same time (1 to 10). Requests to one site are still spaced at least one second apart.", "default": 4 }, "timeoutSecs": { "title": "Timeout per file (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Time allowed to download one file, and again to read it. A PDF still being read at the limit returns the pages read so far with truncated: true.", "default": 60 } } }, "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 } } } } } } } } } }