Back to Models
google logoGoogle
gemini-4-argon
Chat only

Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

10/13/2026
1,048,576 tokens
#1 Text (russian)
Input: $2.20/M
Output: $11.00/M

Specifications

Modalities

Input
audio
file
image
text
video
Output
text

Supported Parameters

include_reasoning
max_tokens
reasoning
reasoning_effort
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p

Max Output Tokens

65,536

Reasoning Configuration

Default
Thinking on (effort: medium)
Selectable effort levels
high
medium
low
Turning thinking off
Not possible (always thinks)

How to control thinking, and what it costs

Data policy

Prompt retention
Unknown — we could not confirm
Training
Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Available in the web chat only

Gemini 4 Argon can be used in FastMetal's web chat, billed per token from your prepaid balance like any other model. It is not available through the API or MCP: a request naming it is refused by the gateway (HTTP 403).

Open in chat

How Gemini 4 Argon actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

To count the number of 'r's in the word "strawberry", let's break the word down letter by letter and examine each one: 1. **s** - Not an 'r'. 2. **t** - Not an 'r'. 3. **r** - **This is the 1st 'r'.** 4. **a** - Not an 'r'. 5. **w** - Not an 'r'. 6. **b** - Not an 'r'. 7. **e** - Not an 'r'. 8. **r** - **This is the 2nd 'r'.** 9. **r** - **This is the 3rd 'r'.** 10. **y** - Not an 'r'. **Conclusion:** By going through each of the 10 letters in the word "st**r**awbe**rr**y", we can see that there are a total of **3** 'r's (one near the beginning and two grouped together near the end).
3.4s response232 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

### What is causing this error? This error happens because the `users` prop being passed into the `UserList` component is `undefined` at the time the component tries to render. Since `undefined` is not an array, it does not have a `.map()` method, causing JavaScript to throw a `TypeError`. In React, this most commonly happens for one of two reasons: 1. **Asynchronous Data Fetching:** You are fetching `users` from an API in a parent component. On the initial render, before the API responds, the `users` state is still `undefined`. 2. **Missing Prop:** You rendered `<UserList />` in a parent component and simply forgot to pass the `users={...}` prop to it. --- ### How to fix it There are a…
6.6s response661 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Here is a comprehensive review of your function. While the original code works, it has several anti-patterns (like bare `except` clauses and local imports) and misses out on built-in `requests` features that can make the code much cleaner and faster. Here is the refactored code, followed by a detailed breakdown of the improvements, and finally an "industry-standard" version for production environments. ### 1. The Refactored Code (Direct Improvement) ```python import logging import time from typing import Any, Dict, List import requests # Configure basic logging logging.basicConfig(level=logging.WARNING) logger = logging.getLogger(__name__) def get_data( url: str, retries: int = 3,…
13.5s response1489 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Gemini 4 Argon API cost?
On FastMetal, Gemini 4 Argon is billed per token: $2.20 per 1M input tokens and $11.00 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
What is the context window of Gemini 4 Argon?
1,048,576 tokens, shared between the prompt and the response.
How does Gemini 4 Argon rank?
#1 on the public arena's Overall board (ELO 1,525). Ranks move as the leaderboard is updated.
What do I need to try Gemini 4 Argon?
Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try Gemini 4 Argon right now

Gemini 4 Argon is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Leaderboard

Text
russianELO: 1,529
#1
CodingELO: 1,562
#1
MathELO: 1,528
#1
Creative WritingELO: 1,519
#1
Instruction FollowingELO: 1,529
#1
Hard PromptsELO: 1,551
#1
Multi-TurnELO: 1,553
#1
OverallELO: 1,525
#1
ChineseELO: 1,588
#1
EnglishELO: 1,534
#1
spanishELO: 1,490
#9
Code
OverallELO: 1,678
#9

Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-08; category names mapped and ratings rounded by FastMetal.