{ "openapi": "3.0.1", "info": { "title": "PDF & Image to Text OCR for AI Agents - No Login", "description": "Extract clean text or Markdown from PDF and image URLs. Uses the PDF text layer when present and Tesseract OCR for scanned pages, per page. 20 languages, page ranges, per-page rows. No login, no API key.", "version": "0.1", "x-build-id": "1yB2gjv40qjiwzHUB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cliqtomedia~pdf-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cliqtomedia-pdf-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cliqtomedia~pdf-text-ocr/runs": { "post": { "operationId": "runs-sync-cliqtomedia-pdf-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cliqtomedia~pdf-text-ocr/run-sync": { "post": { "operationId": "run-sync-cliqtomedia-pdf-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "PDF or image URLs", "maxItems": 100, "type": "array", "description": "Up to 100 public http(s) URLs of PDF files or images (PNG, JPG, TIFF, GIF, BMP, WEBP). The file type is detected from the file content, not the URL. No login, cookies or private networks; duplicates are processed once. Files are deleted when the run ends.", "items": { "type": "string" } }, "ocr": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto (default): use the PDF text layer and run OCR only on pages without usable text (scans). always: OCR every page, even if it has a text layer. never: text layer only, no OCR (images then fail with OCR_DISABLED). Text-layer pages are covered by one per-document charge; OCR is charged per page and per selected language.", "default": "auto" }, "languages": { "title": "OCR languages", "maxItems": 3, "type": "array", "description": "Languages of the document, used by OCR only. Up to 3. Each OCR page is charged once per selected language, and more languages make OCR slower, so pick only the languages the document uses. Default: English.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "swe", "dan", "nor", "fin", "tur", "rus", "ukr", "ara", "hin", "vie", "ind" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Swedish", "Danish", "Norwegian", "Finnish", "Turkish", "Russian", "Ukrainian", "Arabic", "Hindi", "Vietnamese", "Indonesian" ] }, "default": [ "eng" ] }, "pages": { "title": "Pages", "maxLength": 200, "type": "string", "description": "Optional page selection for every document, e.g. 1-3, 5, 10- (10 to the end). Empty: all pages, up to Max pages per document." }, "maxPages": { "title": "Max pages per document", "minimum": 1, "maximum": 300, "type": "integer", "description": "Upper limit of processed pages per document (after the page selection). Extra pages are skipped, not charged, and reported in warnings. 1–300, default 50.", "default": 50 }, "outputFormat": { "title": "Text format", "enum": [ "text", "markdown" ], "type": "string", "description": "text (default): clean plain text. markdown: paragraphs re-flowed, bullet and numbered lists, short ALL-CAPS lines as headings, page markers. Tables are not rebuilt.", "default": "text" }, "outputMode": { "title": "Rows", "enum": [ "document", "page" ], "type": "string", "description": "document (default): one row per document with full text and a pages[] list; text-layer pages are charged as one document event. page: one row per page, ready for chunking and RAG; text-layer pages are charged as one document event per started 50 page rows. A scan with OCR off gives one row, charged as one document event.", "default": "document" }, "preserveLayout": { "title": "Keep column layout (text layer)", "type": "boolean", "description": "Keep the physical layout of text-layer pages (columns, aligned spacing). Off by default, which gives reading-order text. Does not affect OCR pages.", "default": false }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger files are not downloaded and get error FILE_TOO_LARGE. 1–100, default 50.", "default": 50 } } }, "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 } } } } } } } } } }