Home → Guides → Gemini 4 Argon API pricing: the introductory rate, the December 1 change, and what calls cost

Gemini 4 Argon API pricing: the introductory rate, the December 1 change, and what calls cost

The introductory price lasts until November 30. After that every token costs twice as much — unless most of your input comes from cache, where the discount is big enough to outweigh the price change.

Official price per million tokens

	Input	Cached input	Output
Until November 30, 2026	$2.00	$0.10	$10.00
From December 1, 2026	$4.00	$0.20	$20.00

Cached input is billed at 5% of the input rate in both periods.

On this platform:

Model	Input / 1M	Output / 1M	Share of list price
gemini-4-argon	$0.250	$1.25	12.5%

The rate here is set as a share of the list price, so expect it to move when the list price changes on December 1. The figures in this table are filled in from live billing data.

What a call costs

A typical coding-agent turn: 100,000 input tokens and 2,000 output tokens, at list price.

• Nothing cached, introductory price: $0.20 + $0.02 = $0.22
• Nothing cached, from December 1: $0.40 + $0.04 = $0.44
• 80,000 of the input cached, from December 1 (fresh input + cached input + output): $0.08 + $0.016 + $0.04 = $0.136

With a well-cached prompt, the post-December price is still below the introductory price without cache. Keep the stable part of the prompt — system prompt, tool definitions, files — at the start, and put whatever changes each turn at the end.

Calling gemini-4-argon here

The endpoint is OpenAI-compatible. Base URL https://apiclan.us/v1, model name gemini-4-argon:

curl https://apiclan.us/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-4-argon","stream":true,"messages":[{"role":"user","content":"hi"}]}'

With the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI(base_url="https://apiclan.us/v1", api_key="sk-your-key", timeout=120)
r = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[{"role": "user", "content": "hi"}],
)
print(r.choices[0].message.content)

Create the API key under the Gemini group in the console. A key that belongs to another group does not see this model.

Response time

In our own test calls on October 16, the first request after an idle period took 39 seconds to return a five-token answer; the next one took 4.8 seconds. Set a client timeout of at least 120 seconds and stream long responses.

Top-ups are in USDT, at 1 USDT for 2 credits of balance, with no monthly fee.

Start using it

No subscription, no monthly minimum, no sales call. Top up with USDT and spend what you use — 1 USDT gives you 2 credits of API balance.

Read the 30-second quickstart

Language: English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Deutsch · Français · Español · Türkçe · Português · Italiano · Bahasa Indonesia · Tiếng Việt · Bahasa Melayu · Polski · Čeština · فارسی · Русский

Prices on this page are filled in automatically from live billing data. Third-party terms are quoted from that party's own documentation.