{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown OCR Converter: Scanned PDFs & Images to Text", "description": "PDF to Markdown OCR converter and API for LLMs, RAG and AI agents. Convert scanned PDF to text and images (PNG, JPG, WEBP, TIFF) to Markdown. Open source Tesseract OCR runs inside the Actor, so your documents go to no LLM or outside API. Markdown tables, one entry per page. $0.006 per page.", "version": "0.1", "x-build-id": "mNOmI02y25y2FV6t5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brasspage~pdf-ocr-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brasspage-pdf-ocr-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/brasspage~pdf-ocr-to-markdown/runs": { "post": { "operationId": "runs-sync-brasspage-pdf-ocr-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/brasspage~pdf-ocr-to-markdown/run-sync": { "post": { "operationId": "run-sync-brasspage-pdf-ocr-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Direct links to PDF, PNG, JPEG, WEBP or TIFF files, up to 100 MB each. Scanned and digital PDFs both work. Apify key-value store record URLs also work. For a private store, use the record's signed URL (with ?signature=).", "items": { "type": "string" } }, "documentFile": { "title": "Upload a file", "type": "string", "description": "Upload one PDF or image (PNG, JPEG, WEBP or TIFF) from your computer. You can use it together with Document URLs." }, "pages": { "title": "Pages", "pattern": "^[0-9,\\- ]*$", "type": "string", "description": "Optional. Pages to convert in each document, for example 1-3, 5, 10- (10- means page 10 to the end). Leave empty for all pages. An image is page 1." }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text" ], "type": "string", "description": "Markdown keeps headings, lists and tables. Plain text has no Markdown formatting.", "default": "markdown" }, "markdownTables": { "title": "Tables as Markdown tables", "type": "boolean", "description": "On: tables become Markdown pipe tables (also in plain text output). Off: one table row per line, cells separated by tabs.", "default": true }, "language": { "title": "Language", "enum": [ "eng", "spa", "fra", "deu", "por", "rus", "ara", "hin", "chi_sim", "jpn" ], "type": "string", "description": "The language of scanned pages. English also reads most Latin-alphabet text, but accents come out better with the right language. Pages with a text layer are read as they are, in any language.", "default": "eng" }, "secondReader": { "title": "Second reader for handwriting", "type": "boolean", "description": "On: an English page that Tesseract reads badly, like handwriting, is also read by RapidOCR, a free reader that runs inside the Actor. Its text is used when it finds more, and the page says so in `reader`. Needs 1 GB of memory or more. Off: Tesseract only.", "default": true }, "maxPagesPerRun": { "title": "Max pages per run", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Safety limit. The run stops after this many pages in total, and the last dataset row says so. On the Apify free plan, runs are a free trial of up to 20 pages per run and 50 pages per month; upgrade to a paid Apify plan to convert more.", "default": 1000 } } }, "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 } } } } } } } } } }