# Gemini 4 Argon: API price, context window and how to connect

Gemini 4 Argon by Google: $2 per million input tokens, $10 per million output tokens, a 1.05M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.

## In short

Google's flagship reasoning model for complex software engineering, deep math, scientific problems and autonomous multi-step agents. It accepts text, images, audio, video and files.

## Specifications

| | |
|---|---|
| Provider | [Google](https://skillok.org/docs/en/ai-models/providers/google) |
| Released | 2026-10-13 |
| Context window | 1.05M tokens |
| Accepts | audio, files, images, text, video |
| Answers with | text |
| Reasoning mode | yes |
| Tool calling | yes |
| Open weights | no |
| Identifier | `google/gemini-4-argon` |

## Price

| Per 1M tokens | In dollars |
|---|---|
| Input (question, context) | $2 |
| Output (answer) | $10 |

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about **$0.18**. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.

## What it is good for

* Hard math and science
* Agents with long chains of steps
* Analyzing video, audio and documents

## Similar models

Catalog models with the same kind of output, closest in the price of a typical request.

| Model | Input | Output | Window | Price |
|---|---|---|---|---|
| [GPT-6.1 Sol](https://skillok.org/docs/en/ai-models/models/gpt-6-1-sol) | $2 | $10 | 1.05M | about the same |
| [GPT-6.1 Sol Pro](https://skillok.org/docs/en/ai-models/models/gpt-6-1-sol-pro) | $2 | $10 | 1.05M | about the same |
| [Claude Sonnet 5.5](https://skillok.org/docs/en/ai-models/models/claude-sonnet-5-5) | $2 | $10 | 1M | about the same |
| [GLM 5.3 Prime](https://skillok.org/docs/en/ai-models/models/glm-5-3-prime) | $2.8 | $8.8 | 1M | about the same |
| [Kimi K3](https://skillok.org/docs/en/ai-models/models/kimi-k3) | $0.239 | $11.936 | 1.05M | about the same |

## Other Google models

* [Gemini 3.8 Flash](https://skillok.org/docs/en/ai-models/models/gemini-3-8-flash)
* [Nano Banana 2.1](https://skillok.org/docs/en/ai-models/models/gemini-nano-banana-2-1)

## How to connect in SKILLOK

Gemini 4 Argon works through OpenRouter: add an OpenRouter key in **Settings → AI** and pick the `google/gemini-4-argon` model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — [Connecting a model in SKILLOK](https://skillok.org/docs/en/ai-models/connecting-in-skillok).

## Where the data comes from

Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.

---

https://skillok.org/docs/en/ai-models/models/gemini-4-argon