Quickstart
Create a key, set it in your environment, and make your first call.
1. Create an API key
Open the API keys page, create a key, and tick the tools it may call. A key reaches only the tools you grant it. The secret is shown once — copy it before you close the dialog.
2. Set it in your environment
macOS / Linux
export KRIYAM_API_KEY="kri_live_..."
Windows (PowerShell)
setx KRIYAM_API_KEY "kri_live_..."
Every sample in this reference reads the key from that variable.
3. Make your first call
curl -X POST "https://studioapi.kriyam.ai/models/docwise/v2" \
-H "X-API-Key: $KRIYAM_API_KEY" \
-F "files=@invoice.pdf" \
-F "capability=extract" \
-F "processing_mode=fast" \
--form-string 'extraction_schema={"type": "object", "properties": {"invoice_number": {"type": "string", "description": "The invoice number printed by the seller"}, "invoice_date": {"type": "string", "description": "Date of issue, as YYYY-MM-DD"}, "seller_gstin": {"type": "string", "description": "GSTIN of the seller, not the buyer"}, "total_amount": {"type": "number", "description": "Grand total payable including tax"}, "line_items": {"type": "array", "description": "One entry per billed line", "items": {"type": "object", "properties": {"description": {"type": "string", "description": "What was billed"}, "amount": {"type": "number", "description": "Line total before tax"}}}}}}'A synchronous tool answers with the finished run — see the run envelope. DocForensics and Docwise finish later and report to your webhook.
Next steps
Turn a stack of documents into parsed text, document types and structured fields.
Score how far a document can be trusted, with the evidence behind the score.
Spot AI-generated and manipulated images, and deepfaked faces, before you trust them.
Hide the Aadhaar and VID numbers on a card before you store or share it.
Confirm two photos show the same person, with a similarity score.
Find which of several photos match one reference face, in a single call.
Tell a live person from a printed photo or a screen held up to the camera.
