Google
Operational· checked every few minutes

Gemini 4 Argon API

The Gemini 4 Argon API, Google's frontier model for long, complex work, 60% below Google's list price

Price per 1M tokens60%off
Input
$0.80$2.00
Output
$4.00$10.00
Cached input
$0.04
Get your API keyTry it in the playground
Model IDgemini-4-argon
chat.py
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[{"role": "user", "content": "Explain quicksort in two sentences."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK. Chat API docs

Context window
1M tokens
Max output
64K tokens
Reasoning
low · medium · high
Input
Text, Image, Video, Audio
Released
Oct 13, 2026
Status
Operational

Pricing

Gemini 4 Argon API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.

RateZurelayGoogle list
Input
per 1M tokens
$0.80$2.00
Output
per 1M tokens
$4.00$10.00
Cached input
per 1M tokens
$0.04—

One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.

Every Gemini model and price
Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M
Output tokens per month10M
Zurelay
$80.00
Google list price
$200.00
You save every month$120.00

$1,440 a year

Overview

What is Gemini 4 Argon?

Gemini 4 Argon is Google's frontier model for software engineering, professional knowledge work and defensive cybersecurity, announced on September 30, 2026 and opened to developers on October 13, 2026. The Zurelay Gemini 4 Argon API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 60% below Google's list price.

Google announced Gemini 4 Argon on September 30, 2026 and opened it to developers and businesses on October 13, 2026, as gemini-4-argon in the Gemini API. It reads text, images, video, audio and PDFs and writes text, in a context window of 1,048,576 tokens shared by input and output, with up to 65,536 output tokens per response. On Zurelay the model ID is gemini-4-argon and it costs $0.80 per 1M input tokens and $4.00 per 1M output tokens.

Google built Argon for long, multi-step work: real-world software engineering, legal and financial research, document-heavy enterprise tasks, finding and fixing security vulnerabilities, and creative writing. It reports 77.9% on DeepSWE v1.1, a new state of the art, 51.3% on Zapier's AutomationBench, first place, 91.7% on LVBench for long-video understanding, and a top score of 68% on CWE-Bench v1 for remediating vulnerabilities. Google also says it leads the Vals Index and Harvey's Legal Agent Benchmark.

Thinking is built in, with low, medium and high levels; Zurelay uses medium unless you set reasoning_effort. High thinks the longest and is meant for the hardest problems. The model supports function calling and structured outputs, and Google caches repeated prompt prefixes automatically, so cached input bills at $0.04 per 1M tokens. Thinking tokens bill as output.

Google's launch price of $2.00 input and $10.00 output per 1M tokens runs through November 30, 2026, and doubles to $4 and $20 from December 1. When Google's price doubles, Zurelay's moves with it and stays 60% below Google's. Google says Argon refuses harmful cyber and CBRN requests and calls it its most resilient model yet against indirect prompt injection.

Strengths

Where Gemini 4 Argon shines. And what teams build with it.

01

Software engineering

77.9% on DeepSWE v1.1, a new state of the art, for debugging, migrations and changes across large codebases.

02

Agentic workflows

51.3% on Zapier's AutomationBench, first place, for long tasks that call tools over many steps.

03

Long video and documents

91.7% on LVBench, a state-of-the-art score for understanding long videos, plus charts and series of documents.

04

Defensive security

A top score of 68% on CWE-Bench v1 for remediating vulnerabilities, and 0.7% attack success on Gray Swan's indirect prompt injection test.

Use cases

  • Coding agents

    Debugging, algorithm design, code migrations and performance work in agents that run tools over many steps.

  • Legal and financial research

    Deep research, analysis and drafting over long contracts, filings and reports in one request.

  • Security review

    Finding, checking and patching vulnerabilities in your own code, with a model built to refuse harmful cyber requests.

  • Long-context analysis

    Read codebases, recordings, long videos or stacks of documents in up to 1,048,576 tokens and reason across them.

Get started

Call Gemini 4 Argon in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.

  1. 1

    Create a key

    Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.

    Get your API key
  2. 2

    Point your SDK at Zurelay

    Change the base URL. Everything else in your code stays the same.

    https://api.zurelay.com/v1
  3. 3

    Use gemini-4-argon

    Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.

    gemini-4-argon

Works with the tools you already use

Compare

Similar models. All on the same key.

60%off

Gemini 3.1 Pro

$0.80 / $4.80 per 1M tokens

Pick Gemini 3.1 Pro, Google's Pro model in preview, for complex reasoning at a lower price per token.

Gemini 3.1 Pro API
58%off

Gemini 3.8 Flash

$0.32 / $1.59 per 1M tokens

Pick Gemini 3.8 Flash for fast, low-cost coding and agent work with the same 1M-token context and input types.

Gemini 3.8 Flash API
65%off

Claude Opus 5.5

$1.40 / $7.00 per 1M tokens

Pick Claude Opus 5.5 to compare Anthropic's Opus model on long-running agentic coding and knowledge work.

Claude Opus 5.5 API

FAQ

Gemini 4 Argon API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the Gemini 4 Argon API cost?

On Zurelay, gemini-4-argon costs $0.80 per 1M input tokens and $4.00 per 1M output tokens, with cached input at $0.04. Google's launch price is $2.00 input and $10.00 output per 1M through November 30, 2026, so you save 60%. Thinking tokens bill as output.

Will the Gemini 4 Argon price go up?

Google's price doubles to $4 input and $20 output per 1M tokens on December 1, 2026. Zurelay's price moves with Google's that day and stays 60% below it. You pay from prepaid credit, with no subscription.

What is Gemini 4 Argon best at?

Long, complex work: software engineering, agentic workflows, legal and financial research and defensive security. Google reports 77.9% on DeepSWE v1.1, 51.3% on AutomationBench, 91.7% on LVBench and 68% on CWE-Bench v1.

How do I call the Gemini 4 Argon API with the OpenAI SDK?

Install the official openai package, set base_url to https://api.zurelay.com/v1 and use your Zurelay API key. Then send a Chat Completions request with model set to "gemini-4-argon". Images, PDFs, audio and video go in the message as data or links.

What is the Gemini 4 Argon context window?

Gemini 4 Argon has a 1,048,576-token context window shared by input and output, and writes up to 65,536 output tokens per response. It accepts text, image, video, audio and PDF input and writes text.

How do Gemini 4 Argon thinking levels work?

The model thinks before it answers, at low, medium or high. On Zurelay you pick the level with reasoning_effort, and medium is used when you don't. Low answers fastest; high thinks the longest and can take minutes on the hardest problems, so stream long requests.

Should I use Gemini 4 Argon or Gemini 3.1 Pro?

Gemini 4 Argon is Google's newest frontier model and its pick for long, multi-step work. Gemini 3.1 Pro is the earlier Pro model, still in preview, at a lower price per token. Both take the same input types with a 1M-token context, and both work with the same Zurelay key, so test them side by side on your own prompts.

Is there a Gemini Barium API?

No. Barium is a name reported for Google's internal test versions of Gemini 4, not a model Google sells. The Gemini 4 model in Google's API is Gemini 4 Argon, gemini-4-argon, and that is the one Zurelay serves.

Is it the same model as Google's Gemini 4 Argon?

Yes, it is Google's Gemini 4 Argon. Responses are sampled, so wording varies between runs, and Zurelay does not promise byte-identical output. Zurelay is independent and is not affiliated with or endorsed by Google.

More models on Zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer