Gemini 4 Argon has been open to the public since October 13, 2026. Here are the ways in (the Gemini app, Google AI Studio and the API, and Vertex AI for businesses), what each one costs, and how to prompt a model built for long, heavy jobs.
Available now, but not free. You need a Google AI Pro or Ultra subscription for the Gemini app, or a paid Gemini API account for AI Studio and the API. The model ID is gemini-4-argon.
Who can use Gemini 4 Argon
Google released Argon in stages. Here is where it stands today:
| Who | How | Since |
|---|---|---|
| Cyber defenders (Fairwind Program) | Including a version without cyber guardrails | Sept 30, 2026 |
| Developers | Gemini API paid tier, Google AI Studio, Android Studio | Oct 13, 2026 |
| Businesses | Vertex AI, Gemini for business, Google Antigravity | Oct 13, 2026 |
| Google AI Pro and Ultra subscribers | Gemini app and AI Mode in Search | Oct 13, 2026 |
| Free Gemini users | Not announced | No date |
For the full timeline, see our Gemini 4 Argon release date page. Google has since announced a stronger model, Gemini 4 Carbon, but it is limited to cyber defenders for now.
Route 1: the Gemini app with Google AI Pro or Ultra
- Have Google AI Pro or Ultra. Google made Argon available to both plans on October 13. It hasn't announced Argon for free users.
- Open the Gemini app. Sign in on the web or on your phone with the account that holds the subscription.
- Pick the model. Choose Argon from the model menu if it isn't already the default for your plan.
- Start with a big task. Argon is built for long, multi-step work. A one-line question won't show you much of what it can do.
Route 2: Google AI Studio and the Gemini API
- Get an API key. Sign in to Google AI Studio. It creates a project and an API key for new users automatically, and you can copy yours from the API keys page.
- Turn on billing. Argon is not on the free tier, so your project needs billing set up.
- Use the model ID. Set the model to
gemini-4-argon. It costs $2 per 1M input tokens and $10 per 1M output until November 30, 2026, then $4 and $20. - Test on your own tasks. Our Gemini 4 Argon API page has Python, JavaScript and curl examples.
What about Vertex AI?
Yes. Argon has been generally available on Vertex AI, which Google now calls Gemini Enterprise Agent Platform, since October 13, 2026. It is also in BigQuery's generative AI functions. Businesses can use it through Gemini for business and Google Antigravity too.
Set it up in five minutes
- Get a Gemini API key from Google AI Studio, with billing turned on.
- Keep the model ID in config, not scattered through your code, so you can compare models, and later switch to Gemini 4 Carbon, with a one-line change.
- Write a small test set. Ten to twenty real tasks with answers you know are good. You can compare Argon with your current model in an afternoon instead of trusting headline scores (Google's own numbers are on our benchmarks page).
- Budget. $2 per 1M input tokens and $10 per 1M output until November 30, then $4 and $20, with cached input 95% off. See pricing.
Here's the minimal Python setup with Google's Gen AI SDK. Install it with pip install -U google-genai and set GEMINI_API_KEY in your environment:
import os
from google import genai
MODEL = os.environ.get("GEMINI_MODEL", "gemini-4-argon")
client = genai.Client() # reads GEMINI_API_KEY
interaction = client.interactions.create(
model=MODEL,
input="Summarize this changelog for customers: ...",
)
print(interaction.output_text)
Already using the OpenAI SDK? Gemini has an OpenAI-compatible endpoint, so you only change the key, the base URL and the model. Google notes this compatibility layer is still in beta.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["GEMINI_API_KEY"],
base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
)
response = client.chat.completions.create(
model=os.environ.get("GEMINI_MODEL", "gemini-4-argon"),
messages=[{"role": "user", "content": "Explain to me how AI works"}],
)
print(response.choices[0].message.content)
Want Argon inside your coding assistant? Our guide to connecting Gemini to Claude sets it up as a tool Claude can call.
Creative work is a different tool
Argon writes text. For images, video and music, Lumeta AI has the models ready now, in one account.
How to prompt Gemini 4 Argon
Google built Argon for long-horizon coding and enterprise knowledge work. Its 1M-token window is shared by input and output: answers stop at 65,536 tokens by default, and with long decoding turned on it can write up to the full million. That changes how you should ask.
Ask for the whole thing
With that much output room, you no longer need to break work into small pieces. Ask for every changed file in full, the complete report or the entire test suite in one go.
Give it the full context
Include everything relevant: the spec, the code, the data and an example of output you like. Reusing the same large context also gets cheaper, since cached input is 95% off and Google applies it automatically.
Ask for a plan first
For big jobs, have Argon write a numbered plan, check it yourself, then say go. Fixing a plan is much cheaper than fixing a million tokens of output.
Define "done"
Spell out acceptance criteria, format and what to skip, then ask Argon to check its work against that list at the end.
Cap the output when you don't need it all
At the intro price, a maximum-length answer costs about $10 in output tokens alone, and $20 from December 1. Set a maximum output length for everyday calls.
Here's a plan-first prompt you can adapt:
Goal: Move our billing module from raw REST calls to the new SDK.
Context: [paste the module, the SDK docs and our style guide]
Step 1: Write a numbered plan. List every file you will change and why.
Then stop and wait for my go-ahead.
Step 2 (after I say go): Output every changed file in full, one after
another, each headed by its path.
Done means: existing tests still pass, no public function signatures
change, and you end with a list of anything you were unsure about.
Images, video and music: use the right model
Argon doesn't make images, audio or video, so for creative work you need a different model. Lumeta AI has these tools today (and our video guide shows how to plan a clip with a language model and make it with a video model):
Make something today
Images, video, lip sync and music, all in one Lumeta AI account.
Frequently asked questions
How do I get access to Gemini 4 Argon?
Subscribe to Google AI Pro or Ultra to use it in the Gemini app, or set up a paid Gemini API account to use it in Google AI Studio and the API. Businesses can use it on Vertex AI.
Is Gemini 4 Argon free?
No. It isn't on the Gemini API free tier, and in the Gemini app it needs a Google AI Pro or Ultra plan. In the API it costs $2 per 1M input tokens and $10 per 1M output until November 30, 2026, then $4 and $20.
What is the Gemini 4 Argon model ID?
gemini-4-argon, a stable model on the Gemini API since October 13, 2026.
Can I use Gemini 4 Argon in the Gemini app?
Yes, with a Google AI Pro or Ultra subscription. It is also in AI Mode in Search on those plans.
Is Gemini 4 Argon available on Vertex AI?
Yes. It has been generally available on Vertex AI, now called Gemini Enterprise Agent Platform, since October 13, 2026.
Does Gemini 4 Argon have an OpenAI-compatible API?
The Gemini API offers an OpenAI-compatible endpoint at https://generativelanguage.googleapis.com/v1beta/openai/, still labeled beta. Point it at gemini-4-argon and test your use case before relying on it.
Sources: Google's Argon availability post, Google's Argon announcement, Gemini API models, Gemini API pricing, Gemini API OpenAI compatibility, Gemini Interactions API.