Gemini 4 Argon API: Model ID, Pricing and How to Connect

Short answer

Gemini 4 Argon is available on TeamoRouter as gemini-4-argon, with a 1,000,000-token context window. Google's introductory list price is $2 per million input tokens and $10 per million output tokens; on TeamoRouter it is about $0.58 / $2.90 as of the publish date. It uses the same key and base URL as every other model, in both the OpenAI-compatible and the Gemini-native format.

What Gemini 4 Argon is

Gemini 4 Argon is Google's flagship model and the first in the Gemini 4 family, announced on September 30, 2026. Google describes it as built for long, multi-step work: software engineering, legal and financial knowledge work, and cyber defense.

What matters for API use:

• Output limit of up to 1,000,000 tokens. The previous limit was 64,000.
• Pricing in two steps, introductory and regular (table below).

Pricing

Per 1 million tokens, in USD:

Google has not said how long the introductory period lasts. The live TeamoRouter number is always on the pricing page; it moves with the upstream price list, so the figures here are as of the publish date.

For comparison, list prices of other models on TeamoRouter:

Argon launches at the Sonnet 5.5 price and moves to the Opus 5.5 price afterwards.

Calling Gemini 4 Argon

OpenAI-compatible format:

curl https://api.teamorouter.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gemini-4-argon",
    "messages": [{"role": "user", "content": "Explain a context window in one sentence"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.teamorouter.com/v1", api_key="YOUR_KEY")
resp = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[{"role": "user", "content": "Find the bug in this function and propose a fix: ..."}],
)
print(resp.choices[0].message.content)

Gemini-native format:

curl https://api.teamorouter.com/v1beta/models/gemini-4-argon:generateContent \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "content-type: application/json" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Explain a context window in one sentence"}]}
    ]
  }'

Environment variables for Gemini SDKs and Gemini CLI:

export GOOGLE_GEMINI_BASE_URL="https://api.teamorouter.com"
export GEMINI_API_KEY="YOUR_KEY"
export GEMINI_API_KEY_AUTH_MECHANISM="bearer"

Step-by-step install: Gemini CLI with TeamoRouter. Full request reference: API integration.

Paying for usage

You top up a balance in the console and are charged only for tokens actually used — no subscription.

• Card — Visa, Mastercard and other major cards via Stripe.
• USDT — "Pay with crypto" in the top-up dialog.

FAQ

What is the model ID for Gemini 4 Argon? gemini-4-argon. It is the same in the OpenAI-compatible and the Gemini-native format.

Are Gemini 4 and Gemini 4 Argon the same thing? Argon is the name of the first model in the Gemini 4 family. In the API it is called gemini-4-argon.

Do I need to apply for access? No — a TeamoRouter API key is enough.

Will the price change? Google announced an introductory price of $2 and $10 per million tokens and a regular price of $4 and $20, without saying when the introductory period ends. TeamoRouter's price follows Google's price list.

Are there request limits? Yes — see the rate limits page.

Next steps

• Create an API key and send your first gemini-4-argon request.
• Claude vs Gemini vs Codex.
• Claude Sonnet 5.5: pricing and setup — a model at the same list price.