Gemini 4 Argon API: model ID, pricing and how to get access

The Gemini 4 Argon API is the part of Google's announcement everyone wants to try. Here is exactly where it stands today, what it will cost, and the code you can run right now so that switching to Argon takes one line on launch day.

Is the Gemini 4 Argon API available?

Google is releasing Argon in phases. In its announcement it says a model at this level needs a careful, staged release, so security partners get it first. Wider access is planned after paid API customers and AI Ultra, but Google hasn't put dates on any of it.

So if you call the Gemini API today, Argon won't be there. That's normal for this kind of launch, and you can still do all the setup work now.

What is the Gemini 4 Argon model ID?

Google has not published one. Argon is not listed on the Gemini API models page today, where the newest public models include gemini-3.8-flash. You will see blog posts and tweets guessing at names like gemini-4-argon. Don't hard-code a guess: a wrong model name simply fails.

The reliable way to know the moment it lands is to ask the API which models your key can use:

# pip install google-genai
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY
for m in client.models.list():
    if "argon" in m.name.lower():
        print("Argon is live for this key:", m.name)

Or with curl:

curl -s "https://generativelanguage.googleapis.com/v1beta/models" \
  -H "x-goog-api-key: $GEMINI_API_KEY" | grep -i argon

We will add the official model ID to this page as soon as Google publishes it.

Gemini 4 Argon API pricing

Google did publish the price, and it launches with an introductory discount:

Google hasn't said when the intro price ends. It also hasn't published rate limits, regional availability, or whether prices change for very long prompts. Try our Gemini 4 Argon cost calculator to see what your own jobs would cost.

What the Gemini 4 Argon API can do

Google has not yet published the input context window, knowledge cutoff, or the details of function calling and "thinking" settings for Argon. When the model card and API docs arrive, we'll fill these in. Until then, treat anything more specific you read elsewhere as a guess.

Get ready: code you can run today

The trick is simple: build on today's Gemini model, and keep the model name in one environment variable. On launch day you change GEMINI_MODEL and nothing else.

1. Get an API key. Sign in to Google AI Studio and create a Gemini API key. Keep it out of your code and out of git.
2. Set two environment variables. GEMINI_API_KEY for the key, and GEMINI_MODEL for the model name (today gemini-3.8-flash).
3. Install the official SDK. pip install google-genai for Python, or npm install @google/genai for JavaScript.
4. Swap the model on launch day. When Argon's ID appears in the models list, update GEMINI_MODEL and run your tests.

Python

import os
from google import genai
from google.genai import types

client = genai.Client()  # reads GEMINI_API_KEY
MODEL = os.environ.get("GEMINI_MODEL", "gemini-3.8-flash")

response = client.models.generate_content(
    model=MODEL,
    contents="Review this function and list every bug you find.",
    config=types.GenerateContentConfig(max_output_tokens=8000),  # cap the bill
)
print(response.text)

JavaScript / Node

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({}); // reads GEMINI_API_KEY
const MODEL = process.env.GEMINI_MODEL ?? "gemini-3.8-flash";

const response = await ai.models.generateContent({
  model: MODEL,
  contents: "Summarize this contract in plain English.",
  config: { maxOutputTokens: 8000 },
});
console.log(response.text);

curl (REST)

curl "https://generativelanguage.googleapis.com/v1beta/models/${GEMINI_MODEL:-gemini-3.8-flash}:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{"contents":[{"parts":[{"text":"Explain the CAP theorem in three sentences."}]}]}'

OpenAI-compatible endpoint

Already using the OpenAI SDK? The Gemini API has an OpenAI-compatible endpoint, so you only change the key, the base URL and the model name:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["GEMINI_API_KEY"],
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
)
reply = client.chat.completions.create(
    model=os.environ.get("GEMINI_MODEL", "gemini-3.8-flash"),
    messages=[{"role": "user", "content": "Write a haiku about argon."}],
)
print(reply.choices[0].message.content)

Google hasn't confirmed yet that Argon will be served through this endpoint on day one, so test it when access opens.

Using the 1M-token output well

The headline feature for developers is the output limit. A few habits make it useful instead of expensive:

• Stream long answers. Don't wait minutes for one giant response. Print it as it arrives:

for chunk in client.models.generate_content_stream(model=MODEL, contents=long_task):
    print(chunk.text or "", end="", flush=True)

• Ask for a plan first. Have Argon outline the full job, check the plan, then ask it to write everything in one pass.
• Cache what repeats. Cached input is 95% off at the intro price, which adds up fast when you send the same codebase or document over and over.
• Cap every call. Set max_output_tokens to what the job needs, and raise it only for the runs that truly need a huge answer.

Google AI Studio, Vertex AI and other platforms

Google's announcement names paid API customers and Google AI Ultra as the next groups to get Argon. It does not yet confirm dates for Vertex AI (Google Cloud), the Gemini app for other plans, or third-party routers and coding tools. Expect Google AI Studio and the Gemini API first, since that's where the pricing applies, but check the official docs before you plan around any one platform.

Want to use Gemini from inside Claude Code or Claude Desktop? Our Gemini 4 Argon and Claude guide shows a small MCP server that works today and switches to Argon with the same one-line change.

Gemini 4 Argon API questions

Sources: Google's announcement, 9to5Google, Gemini API models, OpenAI compatibility.