Gemini 4 Argon API — Access via an AI API Gateway
Call Google’s Gemini 4 Argon through byesu — an AI API gateway with pay-as-you-go billing and no subscription. Call it through the OpenAI-compatible API; the same token also works for Claude, GPT and other models.
Model specs below are quoted from Google’s official documentation, checked on 2026-10-29.
What It Is
Gemini 4 Argon is the flagship reasoning model of Google’s Gemini 4 generation, released on 2026-10-13 (official page last updated October 2026). Google positions it for complex software engineering, deep mathematical and scientific problem solving, autonomous multi-step agents, and long decode up to 1M tokens. It takes text, image, video, audio and PDF input and returns text.
| Item | Value |
|---|---|
| Model ID on byesu | gemini-4-argon |
| Context window | 1,048,576 tokens (input and output combined) |
| Max output | 65,536 tokens (default synchronous); up to 1,048,576 with long decode |
| Input types | Text, image, video, audio, PDF |
| Thinking | Supported (see Google’s thinking guide) |
| Caching | Implicit caching; explicit caching not supported |
| Tools | Function calling, code execution, file search; computer use in preview |
| Official release | 2026-10-13 |
Models available on byesu
| Model ID | Notes |
|---|---|
gemini-4-argon | Stable (Google’s only published version) |
Other Gemini models on byesu
gemini-3.8-flash · gemini-3.8-flash-high · gemini-3.6-flash · gemini-3.6-flash-high · gemini-3-flash · gemini-3.1-pro-low
They work with the same default auto-group token; just change the model ID.
How Pricing Works
byesu bills per token with no monthly fee. The actual price of every model is shown live in the model list after you sign in, and the console records the charge for each request.
Official list price: Google announced an introductory price of $2 per million input tokens and $10 per million output tokens, with cached input tokens at 95% off (source: Google’s launch post; Google calls it introductory, so check the Gemini API pricing page for the current figure).
TIP
A token in the default auto group can call gemini-4-argon — no need to pick a group. A wrong group returns “no available channel”; see Choosing a Group.
How to Call It
The base URL depends on the API format:
- OpenAI-compatible (
/v1/chat/completions,/v1/responses) →https://byesu.com/v1 - Gemini native format →
https://byesu.com
Authenticate with Authorization: Bearer sk-YOUR_TOKEN.
from openai import OpenAI
client = OpenAI(api_key="sk-YOUR_TOKEN", base_url="https://byesu.com/v1")
resp = client.chat.completions.create(
model="gemini-4-argon",
messages=[{"role": "user", "content": "Explain what an API gateway is in one sentence"}],
)
print(resp.choices[0].message.content)For clients that speak the Gemini native format, set the address to https://byesu.com and use your token as the key.
FAQ
How do I get Gemini 4 Argon API access?
Sign up at byesu, create a token (the default auto group works), and call gemini-4-argon through the OpenAI-compatible endpoint https://byesu.com/v1. You can pay with USDT or Alipay.
How much does the Gemini 4 Argon API cost on byesu?
byesu bills per token with no subscription; the live price is shown in the model list after you sign in. For reference, Google’s official introductory price is $2 per million input tokens and $10 per million output tokens, with cached input at 95% off.
How long is the Gemini 4 Argon context window?
According to Google’s documentation, the context window is 1,048,576 tokens (input and output combined). Default synchronous max output is 65,536 tokens, or up to 1,048,576 tokens with long decode.
Can I call Gemini 4 Argon with the OpenAI SDK?
Yes. Set the SDK base_url to https://byesu.com/v1, use your byesu token as the api_key, and set model to gemini-4-argon.
Is Gemini 4 Carbon available on byesu?
Not yet. When Google announced Carbon on 2026-10-28 it opened access only to a subset of cyber defenders and trusted partners in phases; the developer API is not generally available. byesu lists it once Google makes it generally available — check the model list.