---
title: "Google Gemini | Skills We Assign For | Azendo"
description: "Google Gemini for multimodal work — video and audio input, Vertex integration, plus the Azendo roles assigned for it."
url: "https://azendo.co/skills/google-gemini/"
---

[Skills](https://azendo.co/skills/) AI and machine learning 

# Google Gemini.

Gemini is Google's multimodal model family, handling text, images, audio and video, available through the Gemini API and Vertex AI with very large context windows.

## Where Google Gemini fits on a long engagement.

Native video and audio understanding is the differentiator that matters architecturally. Processing a recording without first transcribing it, or answering questions about a video directly, removes a preprocessing pipeline and the errors that pipeline introduces.

For organisations already on Google Cloud, Vertex AI integration is the practical argument: data residency, IAM and billing all sit inside the existing estate rather than requiring a separate vendor relationship, which for regulated clients is often the deciding factor rather than model quality.

## What an assigned team does with Google Gemini.

Multimodal work has cost characteristics people do not anticipate. Video and audio consume tokens at rates far above text, so a feature that is cheap in a demo can be expensive at production volume.

Modelling that before building is part of responsible scoping, and what that assessment covers is set out in [how the monthly fee is built](https://azendo.co/pricing/).

## What we use Google Gemini for.

* Video understood without transcription Direct processing, removing a preprocessing stage and its error rate.
* Staying inside an existing cloud estate Vertex integration where data residency and IAM matter more than model choice.
* Cost modelled for multimodal volume Token consumption projected honestly, because media is far more expensive than text.

## How Google Gemini capacity is assigned.

Multimodal capacity is assigned under [ai engineering services](https://azendo.co/services/ai-engineering/), with per-modality cost established before the architecture is fixed.

## Service lines it sits in

* [AI engineering](https://azendo.co/services/ai-engineering/)

Capacity is agreed as a committed monthly capacity across a discipline, not per skill.

## Related in ai and machine learning

* [PyTorch — skill we assign for](https://azendo.co/skills/pytorch/)
* [TensorFlow — skill we assign for](https://azendo.co/skills/tensorflow/)
* [scikit-learn — skill we assign for](https://azendo.co/skills/scikit-learn/)
* [Pandas — skill we assign for](https://azendo.co/skills/pandas/)
* [NumPy — skill we assign for](https://azendo.co/skills/numpy/)
* [embeddings — skill we assign for](https://azendo.co/skills/embeddings/)
* [function calling — skill we assign for](https://azendo.co/skills/function-calling/)
* [vLLM — skill we assign for](https://azendo.co/skills/vllm/)

## Tell us what your roadmap needs Google Gemini for.

A service delivery manager replies with the disciplines we would assign, the monthly capacity and what the first month looks like.

[All skills we assign for](https://azendo.co/skills/)