API Reference

Extract any document into schema-validated data with a single API call. The Talonic API provides programmatic access to the full extraction pipeline — from document upload through schema validation to structured data delivery with per-cell provenance.

Quick start

Three modes. Pick the one that matches the call you’re already writing. See authentication for API key setup and schema formats for all three accepted inline schema formats.

Mode 1 — Extract (auto-detect)

Send a document, get every field the AI discovers. No schema needed.

curl -X POST https://api.talonic.com/v1/extract \
  -H "Authorization: Bearer $TALONIC_API_KEY" \
  -F "file=@invoice.pdf"

Use when you’re prototyping or don’t yet know what’s in the document. → Full reference

Mode 2 — Extract with inline schema

Send a document AND the shape you want. Get back exactly that shape, with field-level confidence and provenance.

curl -X POST https://api.talonic.com/v1/extract \
  -H "Authorization: Bearer $TALONIC_API_KEY" \
  -F "file=@invoice.pdf" \
  -F 'schema={"vendor_name":"string","total_amount":"number","due_date":"date"}'

Use when your code already knows the shape it needs. Three schema formats accepted: JSON Schema, simplified fields, flat key-type. → Schema formats

Mode 3 — Filter documents

Documents were ingested days or months ago. Now just ask.

curl -X POST https://api.talonic.com/v1/documents/filter \
  -H "Authorization: Bearer $TALONIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "conditions": [
      {"fieldId": "vendor_name", "operator": "eq", "value": "Meridian Energy AG"}
    ],
    "limit": 50
  }'

Zero re-extraction. Zero AI calls. → Full reference

Endpoints