Anyparser API Reference

Anyparser provides a REST API that allows you to integrate document parsing capabilities into your applications. The API supports multiple file types and parsing models, and it returns structured data in Markdown and JSON formats.

Endpoint

Select the endpoint nearest to you.

API Key

Get your free API key with unlimited developer usage. No credit card required. Get Free API Key

Upload File

Upload a file

or drag and drop

PDF, DOC up to 10MB

Model

Output Format

JSON

Markdown

HTML

Customize

Tables

Detect

Images

Embed

Result

No documents processed yet.

Base URL

The base URL for all API requests is:

https://api.anyparser.com/v1

Authentication

To authenticate API requests, you need to include your API key in the Authorization header. The format should be:

Authorization: Bearer <your-api-key>

You can obtain your API key from your account dashboard.

API Endpoints

1. POST /parse

This endpoint processes a document and returns the parsed content in the specified output format (Markdown or JSON).

Request

POST /v1/parse

Request Parameters

file (form-data): The document to be parsed. Supports PDFs, Word documents, Excel files, images (OCR), audio, and more.
model (optional, query): Choose the parsing model. Supported values:
- text: Basic text extraction (fast).
- ocr: OCR for images and scanned documents.
- vlm: Vision Language Model for complex or diverse data (slower but more accurate).

Example Request (cURL)

curl -X POST https://api.anyparser.com/v1/parse \
  -H "Authorization: Bearer your-api-key" \
  -F "file=@/path/to/document.pdf" \
  -F "model=text"

Example Response

{
  "markdown": "# Sample Document\n\nThis is the content of the document..."
}

2. POST /batch-parse

This endpoint allows you to parse multiple files in a single request.

Request

POST /v1/batch-parse

Request Parameters

files (form-data): An array of documents to be parsed. Supports the same formats as the /parse endpoint.
model (optional, query): Choose the parsing model (text, ocr, vlm).

Example Request (cURL)

curl -X POST https://api.anyparser.com/v1/batch-parse \
  -H "Authorization: Bearer your-api-key" \
  -F "files[]=@/path/to/document1.pdf" \
  -F "files[]=@/path/to/document2.pdf" \
  -F "model=text"

Example Response

[
  {
    "markdown": "# Document 1\n\nThis is the first document."
  },
  {
    "markdown": "# Document 2\n\nThis is the second document."
  }
]

3. GET /models

This endpoint returns the available parsing models and their descriptions.

Request

GET /v1/models

Example Response

{
  "models": [
    {
      "name": "text",
      "description": "Basic text extraction, ideal for documents without tables."
    },
    {
      "name": "ocr",
      "description": "OCR for extracting text from images and scanned documents."
    },
    {
      "name": "vlm",
      "description": "Vision Language Model (VLM) for diverse and complex data extraction."
    }
  ]
}

Error Handling

If the API encounters an error, it will return a structured error response. The response will include a status code, error message, and an optional error description.

Example Error Response

{
  "error": {
    "code": "invalid_file_type",
    "message": "The uploaded file type is not supported. Please upload a PDF, Word, or image file."
  }
}

Common Error Codes

Code	Description
`invalid_api_key`	The API key provided is invalid.
`invalid_file_type`	The uploaded file type is not supported.
`model_not_found`	The specified model is not available or is misspelled.
`too_large`	The uploaded file exceeds the size limit.

Rate Limits

Anyparser enforces rate limits to ensure fair usage. The current rate limit is:

Requests per minute: 60
Requests per day: 1,000

If you exceed the rate limit, you will receive a 429 Too Many Requests error.