> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vortexiq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Vision-Capable Models, Google Gemini KPI card, Vortex IQ Nerve Centre

> Count of models whose description or displayName matches a multimodal keyword (vision, image, audio, multimodal) from /v1beta/models. Heuristic: Gemini exposes no explicit vision flag, so it is derived from the description text field.

**[Nerve Centre KPIs](/nerve-centre/kpi-cards/gemini) · [Sentiment Settings](/nerve-centre/kpi-cards/gemini/sentiment)**

## At a glance

* **Category:** Capabilities
* **Type:** Supporting Metrics
* **Chart:** kpi
* **Format:** number
* **Time window:** RT

## Calculation

Count of models whose description or displayName matches a multimodal keyword (vision, image, audio, multimodal) from /v1beta/models. Heuristic: Gemini exposes no explicit vision flag, so it is derived from the description text field.

## Known limitations

*Known limitations, FAQs, or reconciliation notes specific to this card. Replace this block when authored.*