Gemini 4 Argon · Google

What does Gemini 4 Argon cost to run in a coding agent?

Gemini 4 Argon costs about $0.11 per average coding-agent request on our measured traffic, at list prices of $4 per million input and $20 per million output tokens. It scores 53 on the Artificial Analysis Intelligence Index, 5th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: Gemini API pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

Run current Claude, GPT, Gemini and open models in your agent from $19/month

See plans

What Gemini 4 Argon costs per coding-agent request

Cost at list price	Gemini 4 Argon
Prompt under 100K tokens50% of requests, 87% of input cached	$0.052
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.13
Prompt over 272K tokens11% of requests, 86% of input cached	$0.28
Average request	$0.11
100 requests	$10.55
Median session16 requests; a session ends after 10 idle minutes	$1.43
A month of regular usemedian of 20 users active on 5+ days	$152

Each logged request priced at the vendor’s list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

Gemini 4 Argon benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	53	5 of 48
Terminal-Bench 4.0agentic coding in a terminal	57.1%	4 of 39

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: Gemini 4 Argon (High), speed on Google. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

About Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model and the first of the Gemini 4 generation, released in October 2026 and on OpenRouter since October 13. Google pitches it for complex software engineering, deep math and science, and autonomous multi-step agents. It takes text, images, video, audio and PDFs in a 1M-token window, writes 65K tokens by default and up to 1M with long decode, and offers low, medium and high thinking. Artificial Analysis scores it 53 on its Intelligence Index (high effort) and 57.1% in its Terminal-Bench 4.0 run, close to Claude Opus 5.5's 58 and 59.6%. At the introductory price it costs about half as much per request as Opus 5.5 in our measurements ($0.053 vs $0.107); from December 1 the two cost the same.

Sources: Google model page · Artificial Analysis

Gemini 4 Argon FAQ

How much does Gemini 4 Argon cost per coding-agent request?

$0.11 on average at list price, $10.55 per 100 requests, and $1.43 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at Google's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does Gemini 4 Argon charge more for long prompts?

No. Gemini 4 Argon bills the same rate per token up to its 1M-token context window.

Is Gemini 4 Argon good for AI agents?

Hard coding and agent steps where you want a frontier model outside the Claude and GPT families. On our scoring, which is calibrated to public benchmarks, it rates 9.4/10 for agentic ability and 9.3/10 for output quality. 57.1% in Artificial Analysis's Terminal-Bench 4.0 run, close to Opus 5.5's 59.6%.

What is Gemini 4 Argon's context window?

Gemini 4 Argon has a 1.0M-token context window, large enough to hold sizeable codebases or document sets in a single run. Google is the maker.

Can I self-host Gemini 4 Argon?

No. Gemini 4 Argon is a proprietary, hosted-only model from Google. You access it through an API, such as OpenRouter, rather than running the weights yourself.

What are the downsides of Gemini 4 Argon?

The main trade-offs: Price doubles to $4/$20 per million on December 1, 2026; Not available on the Gemini API free tier or the Google AI Pro plan, per Google; Implicit caching only; explicit context caching is not supported. It's strongest for hard coding and agent steps where you want a frontier model outside the Claude and GPT families.