# Google: Gemini models

Gemini is Google's family of models — fast Flash and strong Pro, a huge context window and work with images. What they are good at, access from Russia and how to connect them in SKILLOK.

## Who they are

**Google** develops the **Gemini** models at Google DeepMind. Gemini was trained from the start to work not only with text but also with images, audio and video.

## Models

* **Flash** and **Flash-Lite** — fast and very cheap, good for high-volume tasks.
* **Pro** — a strong model for complex analysis, code and reasoning.
* The open **Gemma** models — they can run on your own server.

The exact list and versions change often — current models are visible in the list when you connect a key in SKILLOK, and in the [model catalog](https://skillok.org/docs/en/ai-models/models).

## What they are good at

* A very large context window — you can pass a whole book or a big repository.
* Strong work with images and documents.
* Flash is one of the best price-to-quality ratios.

## Access from Russia

The Gemini API is not available in Russia directly.

## Models in the catalog

Prices, context window and comparison with similar models:

* [Gemini 4 Argon](https://skillok.org/docs/en/ai-models/models/gemini-4-argon) — $2 / $10 per million tokens
* [Gemini 3.8 Flash](https://skillok.org/docs/en/ai-models/models/gemini-3-8-flash) — $0.825 / $4.125 per million tokens
* [Nano Banana 2.1](https://skillok.org/docs/en/ai-models/models/gemini-nano-banana-2-1) — $1.5 / $7.5 per million tokens

## How to connect in SKILLOK

Gemini models work in SKILLOK **through OpenRouter**: connect an OpenRouter key and pick a `google/…` model.

In detail — [Connecting in SKILLOK](https://skillok.org/docs/en/ai-models/connecting-in-skillok).

## Prices

Prices per million input and output tokens are on the [official page](https://ai.google.dev/pricing). Through OpenRouter the prices are the same or close; how much you spent is shown in **Settings → AI**.

---

https://skillok.org/docs/en/ai-models/providers/google