Kuhunyushwe ngomshini
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
Mayelana
Imikhiqizo
Models
Developers
Careers
Playground

Ulimi nesifunda

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

Izilimi ezingu-136

Kunconyiwe

1

i-Eastern Asia

7

i-South-Eastern Asia

11

i-Southern Asia

18

i-Central Asia

5

IMpumalanga Ephakathi neKhawkhasu

10

i-Western Europe ne-i-Southern Europe

16

i-United Kingdom ne-i-Ireland

4

i-Northern Europe

10

IYurophu Emaphakathi neBalkan

14

i-Eastern Europe

5

i-Eastern Africa

8

i-Western Africa ne-i-Middle Africa

9

i-Southern Africa

8

i-Americas

5

i-Oceania

5