IBM's document-understanding API.
IBM's Docling project is the reference route for parsing PDFs, scanned documents, and structured-document extraction. Useful as a pre-processor for RAG and document-workflow pipelines where reliable structure extraction matters more than free-form language generation.
Every model we route through Docling. Compare residency, ZDR, training posture, and price at a glance — full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| EU | Enterprise | No | — | — | — | |
| EU | Enterprise | No | — | — | — |
Docling hosts on 1 route. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.
