Help Center

How can we help you?

Search our knowledge base or browse categories to find answers to your questions

Browse by Category

Getting Started

Learn the basics and set up your account

Billing & Plans

Manage your subscription and payments

Security & Privacy

Keep your data safe and compliant

Troubleshooting

Common issues and solutions

Account Management

Manage your account settings

Frequently Asked Questions

Quick answers to common questions

How do I get started with TechDexAI?

Sign up for a free account, get your API key from the dashboard, and start making API requests. Check our Quick Start Guide for detailed instructions.

What document types are supported?

We support bank statements, receipts, invoices, and other financial documents. Supported formats include Documents (PDF, DOCX, DOC, TXT), Images (PNG, JPG, JPEG, JFIF, GIF, BMP, TIFF), and Spreadsheets (XLSX, XLS, CSV). Our AI can extract data from various formats and layouts.

How accurate is the data extraction?

Our AI achieves 95%+ accuracy on standard documents. For custom or complex documents, accuracy may vary. You can review and verify all extracted data.

Is my financial data secure?

Yes! We use bank-level encryption (AES-256) for data at rest and TLS 1.3 for data in transit. We're SOC 2 Type II certified and GDPR compliant. Results are persisted and retained indefinitely - you can retrieve them anytime using the request_id.

Can I cancel my subscription anytime?

Yes, you can cancel your subscription at any time. You'll continue to have access until the end of your billing period.

What are the rate limits?

Rate limits vary by plan: Free (5 requests/minute), Pro (50 requests/minute), Business (100 requests/minute), Enterprise (custom). Check the Pricing page for details.

Why do document processing times fluctuate?

Processing times vary based on document length/complexity (e.g. multi-page bank statements vs. single receipts) and real-time user concurrency on the platform. During high-traffic periods with many simultaneous users, jobs are queued and processed sequentially. Using async mode (wait=false) with polling or webhooks provides the most resilient and predictable experience.

What is the ongoing model fine-tuning timeline and dataset roadmap?

We are currently conducting an active 30–45 day model fine-tuning cycle. We are expanding our training dataset corpora with diverse, legally verified commercial financial documents, enforcing strict PII redaction and GDPR/SOC-2 compliance, and elevating OCR and tabular parsing accuracy with zero API downtime.

Still need help?

Can't find what you're looking for? Our support team is here to help you succeed.