Pdf OCR API
Pricing
from $0.01 / 1,000 results
Go to Apify Store
Pdf OCR API
Extract and convert text from PDF documents using advanced optical character recognition technology with support for multiple AI models.
Pricing
from $0.01 / 1,000 results
Extract and convert text from PDF documents using advanced optical character recognition technology with support for multiple AI models.
You can access the Pdf OCR API programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, youβll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "u3UFURgPfTd1SX3lk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cspnair~pdf-ocr-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cspnair-pdf-ocr-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cspnair~pdf-ocr-api/runs": { "post": { "operationId": "runs-sync-cspnair-pdf-ocr-api", "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/cspnair~pdf-ocr-api/run-sync": { "post": { "operationId": "run-sync-cspnair-pdf-ocr-api", "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": [ "ocrModel", "pdfUrls" ], "properties": { "ocrModel": { "title": "OCR Model", "enum": [ "google-vision", "deepseek-ocr", "amazon-textract", "azure-vision", "openai", "huggingface", "gemini", "native" ], "type": "string", "description": "Select the OCR model to use for text extraction", "default": "native" }, "pdfUrls": { "title": "PDF Document URLs", "minItems": 1, "type": "array", "description": "Array of PDF document URLs to process", "items": { "type": "string" }, "default": [ "https://pdfobject.com/pdf/sample.pdf" ] }, "language": { "title": "Document Language", "enum": [ "eng", "spa", "fra", "deu", "ita", "por", "rus", "chi_sim", "jpn", "kor", "ara", "dan" ], "type": "string", "description": "Primary language of the documents", "default": "eng" }, "preserveFormatting": { "title": "Preserve Document Formatting", "type": "boolean", "description": "Maintain document layout and structure", "default": true }, "extractImages": { "title": "Extract Images", "type": "boolean", "description": "Extract and process images from PDF", "default": false }, "outputFormat": { "title": "Output Format", "enum": [ "json", "text", "markdown" ], "type": "string", "description": "Format for extracted text", "default": "json" }, "pageRange": { "title": "Page Range", "type": "string", "description": "Specific pages to process (e.g., '1-5' or '1,3,5' or 'all')", "default": "all" }, "googleVisionApiKey": { "title": "Google Vision API Key", "type": "string", "description": "Required if using Google Vision API" }, "deepseekApiKey": { "title": "DeepSeek API Key", "type": "string", "description": "Required if using DeepSeek OCR" }, "awsAccessKeyId": { "title": "AWS Access Key ID", "type": "string", "description": "Required if using Amazon Textract" }, "awsSecretAccessKey": { "title": "AWS Secret Access Key", "type": "string", "description": "Required if using Amazon Textract" }, "awsRegion": { "title": "AWS Region", "type": "string", "description": "AWS region for Textract (e.g., us-east-1)", "default": "us-east-1" }, "azureEndpoint": { "title": "Azure Vision Endpoint", "type": "string", "description": "Required if using Azure AI Vision" }, "azureApiKey": { "title": "Azure Vision API Key", "type": "string", "description": "Required if using Azure AI Vision" }, "openaiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Required if using OpenAI GPT-4 Vision" }, "huggingfaceApiKey": { "title": "Hugging Face API Key", "type": "string", "description": "Required if using Hugging Face models" }, "geminiApiKey": { "title": "Google Gemini API Key", "type": "string", "description": "Required if using Gemini API" } } }, "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 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Pdf OCR API from the options below:
If youβd like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: