COVA MODELS

Put document and image information to work.
Meet Cova.

A Vision OCR model that extracts text alongside document structure, tables, and image information.
Use the extracted results for analysis and automation with CIP.

Cova: a dedicated model for reading documents

Beyond recognizing characters, Cova extracts document structure, positions,
tables, and image information together.
Connect the results directly to CIP for analysis and automation.

  • Structure contracts, reports, and invoices
  • Extract information while preserving tables and layout
  • Pass HTML or Markdown to downstream models

Cova

Supported features
Selective source-image review · Context efficiency
Recommended uses
Document search, automated data entry, and preprocessing for multi-document analysis

What Cova reads and structures

Preserve document layout while extracting the information needed for the next analysis step.

Find the latest Cova specifications in the developer docs

This page explains model capabilities and selection. Exact model IDs, input and output limits,
supported features, and version changes are maintained in the developer docs.

Model IDs Input and output specs API examples Changelog
Cova developer docs

Automate your document workflows with Cova

CLEVI

Language and region

Machine-translated languages are translated by clevi/cip-5.5-im and marked as such. This applies to languages with a published site bundle.

136 languages

Recommended

1

East Asia

7

Southeast Asia

11

South Asia

18

Central Asia

5

Middle East and the Caucasus

10

Western and Southern Europe

16

Britain and Ireland

4

Northern Europe and the Baltics

10

Central Europe and the Balkans

14

Eastern Europe

5

East Africa and the Horn

8

West and Central Africa

9

Southern Africa

8

The Americas

5

The Pacific

5
Cova — CLEVI