Use code for 1,000 extra pages on your first month of Starter.+1,000 pages on Starter
See Starter →See →High-accuracy text extraction that handles degraded scans, complex multi-column layouts, and 100+ languages. Built for production pipelines that can't tolerate garbage output.
01# Install the SDK from GitHub (it is not on PyPI):02# git clone https://github.com/hyprbots/hyperapi-sdk03# cd hyperapi-sdk04# pip install -e .05from hyperapi import HyperAPIClient0607client = HyperAPIClient(api_key="YOUR_API_KEY")0809result = client.parse("document.pdf")10print(result["result"]["ocr"])1112client.close()Parse handles the edge cases that break standard OCR — degraded scans, handwriting, complex layouts, and mixed languages.
Parse documents in 100+ languages including mixed-language documents. No pre-configuration required.
Handles multi-column layouts, headers, footers, sidebars, and mixed text-image documents without losing reading order.
Fast returns the text and line boxes quickly. Advanced adds layout analysis for dense tables and forms, on Plus, Pro and Custom.
Works on low-resolution scans, skewed documents, and poor-quality images where standard OCR fails.
Install the SDK, grab your API key, and you're parsing documents.
01# Install the SDK from GitHub (it is not on PyPI):02# git clone https://github.com/hyprbots/hyperapi-sdk03# cd hyperapi-sdk04# pip install -e .05from hyperapi import HyperAPIClient0607client = HyperAPIClient(api_key="YOUR_API_KEY")0809result = client.parse("document.pdf")10print(result["result"]["ocr"])1112client.close()Install
The Python SDK is installed from GitHub.
git clone https://github.com/hyprbots/hyperapi-sdk cd hyperapi-sdk pip install -e .
The Node.js sample uses fetch (Node 18+), so it needs nothing installed.
Response Shape
POST /v1/parse, from the API reference.
{
"status": "success",
"request_id": "req_01j9x...",
"task": "parse",
"model_used": "HyperLM",
"result": {
"ocr": "…",
"pages": [{ "page_number": 1, "text": "…", … }],
"blocks": [{ "id": "…", "order": …, … }],
"groups": [{ "id": "…", "kind": "…", … }]
},
"duration_ms": …,
"metadata": {
"pages": …,
"source": "…",
"filename": "…",
"file_size": …,
"content_type": "…",
"groups_profile": "…"
}
}Searchable and scanned PDFs
Including embedded images and tables
Raster images and scanned pages
Excel workbooks with text content