Parse, extract, classify, split and redact financial documents through one API.
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.extract("invoice.pdf", category="financial")10print(result["result"]["entities"])1112client.close()Validation-aware extraction. Not just text extraction: we understand document semantics and enforce cross-field consistency.
Extract text from PDFs and images with OCR. Returns page-level text, word boxes, layout blocks and tables. Advanced mode adds markdown.
Categorize document type automatically. Returns the document type, a confidence label and whether the result needs review.
Segment a multi-document PDF into individual logical documents. Returns page ranges for each detected document.
Extract structured data with Basic Financial or Other formats. Other accepts a JSON output template through the schema field. For mixed or unknown document types, the SDK's Advanced extractor (extract_advanced()) detects the type automatically.
Mask or de-identify PII in a document. Returns redacted page images, an updated text block, and a summary of masked entities.
Free
Starter
Plus
Pro
Custom
Why HyperAPI
Not just OCR. We enforce document-level constraints like line-item totals and cross-field consistency.
A Python SDK, a REST API you can call from Node.js with fetch, and an MCP server for agents.
SOC 2 Type II compliant. SSO/SAML support, audit logs, and data encryption at rest and in transit.
Optional human review for mission-critical workflows, on Custom plans.
Real-time dashboards for usage tracking, cost monitoring, and performance metrics.
Run any operation asynchronously and poll the job, or send a batch and get a webhook when it finishes.