| Bounding boxes (word/line level) | Yes (word/line level, Surya OCR) | n/a (translation) |
| Sandwich PDF / searchable archive PDF | Yes — searchable archive PDF | no — no DMS archive PDF |
| Click-to-evidence / visual validation (HITL) | Yes — click-to-evidence / HITL | no |
| Structured IDP fields (ready types) | ~30 ready types incl. DATEV/ZUGFeRD | n/a — text translation focus |
| DMS/archive included (WORM, audit, legal hold) | Yes — WORM, audit trail, legal hold | no |
| E-signatures on the same document | Yes — on the same document object | no |
| Native MCP server (tool count) | Yes — 165+ DMS tools (MCP) | no — specialty API |
| EU inference on owned hardware | Yes — owned EU GPU hardware | DeepL infrastructure (EU vendor) |
| Specialty API feature scope | Document + Data AI in one API | Text + documents; min. 50,000 characters/file for certain document types |
| One token / credit system | one Bearer for all tools | own Developer/Growth plan |
| Price / 1,000 pages (extraction only) | Basic €30 / Premium €40 / Ultra €100 per 1,000 pages (3/4/10¢) | Developer / Growth (API Free/Pro no longer sold, as of 08/2026) |