Gemini 4 Argon API Guide: Model ID, OpenAI SDK, Plan Quota

As of the 2026-10-14 catalog, Router One lists Gemini 4 Argon as google/gemini-4-argon. The gateway also accepts Google's own id, gemini-4-argon, for the same catalog entry. Send "model": "google/gemini-4-argon" to https://api.router.one/v1/chat/completions with a Router One key — or point any OpenAI-compatible SDK or client at https://api.router.one/v1 — and the request is routed, metered and logged like every other model. As of the 2026-10-14 plan response, Gemini 4 Argon is in the Premium models tier of the Pro, Max and Ultra plans: on a plan its calls draw that tier's allowance, and calls beyond it are billed to the wallet; without a plan, every call bills per token to the wallet at the rates on the Gemini 4 Argon model page.

This guide covers what the catalog lists for the id, where it sits next to GPT-6.1 Sol, GPT-6 Astra and Gemini 3.8 Flash on Router One, how billing and plans apply, the first request with curl and the OpenAI SDKs, which clients can call it, and access from mainland China. Catalog and plan observations are dated; the live catalog is the source of truth for a new request.

Gemini 4 Argon at a glance

Google announced Gemini 4 Argon on September 30, 2026, and describes it this way (Google's announcement, checked 2026-10-14): "Gemini 4 Argon delivers frontier performance in complex workflows across real-world software engineering, enterprise knowledge work like legal and finance, and cybersecurity defense." Per Google's Gemini API release notes (October 13, 2026; checked 2026-10-14), Gemini 4 Argon (Google's model id gemini-4-argon) is generally available on the Gemini API. Those are Google's statements; Router One is responsible for the catalog entry and for how the gateway routes and bills it.

Gemini 4 Argon, GPT-6.1 Sol, GPT-6 Astra or Gemini 3.8 Flash?

This section compares what Router One controls (the plan allowance a call draws, the endpoints, the posted rates), not output quality: run your own prompts through each candidate before you move a workload. As of the 2026-10-14 plan response:

What that means for the choice:

• One Premium allowance. As of the 2026-10-14 plan response, Gemini 4 Argon, GPT-6.1 Sol, GPT-6 Sol and Claude Opus 5 sit in the same Premium models tier, and a tier's allowance is one pool shared by every model the tier lists, so on a plan, moving a workload among them keeps it on the same allowance. GPT-6 Astra draws the Flagship models allowance, which only Max and Ultra carry, and Gemini 3.8 Flash draws the Standard models allowance.
• Which clients can send it. Router One serves Gemini 4 Argon on /v1/chat/completions only, so it needs a Chat Completions client; Claude Opus 5 is also served on /v1/messages, the endpoint Claude Code calls. The GPT-6.1 Sol API guide and the GPT-6 Astra API guide cover the endpoints Router One serves those two on and the request rules OpenAI documents for them.
• Switching from Gemini 3.8 Flash. The key, base URL and endpoint stay the same, so on the wire the switch is the model string. On a plan the calls move from the Standard models allowance to the Premium models allowance; without a plan, calls bill at the posted rates of the model you switch to. Test the parameters your code sends before you move a workload.
• Posted rates. Router One posts its own per-token rates on each model page. Compare the cost of a whole task (Dashboard → Logs lists each call's cost) rather than per-token rates alone.

How billing works

Gemini 4 Argon bills per token at the input and output rates posted on its model page. Router One posts its own rates for each model, and this guide prints no per-token figures because they go stale. Without a plan, every call bills the wallet. On a Pro, Max or Ultra plan, calls draw the Premium models allowance (as of the 2026-10-14 plan response), and calls beyond it bill the wallet at the posted rates. The pricing page shows the plans and each plan's allowance.

Dashboard → Logs lists the calls with their model, input and output tokens, cost, latency and status (per-request observability), so you can total what a task cost from the calls it made rather than estimate it from rates.

Do subscription plans cover Gemini 4 Argon?

Yes, as of the 2026-10-14 plan response: Gemini 4 Argon is in the Premium models tier of Router One's Pro, Max and Ultra plans, together with GPT-6.1 Sol, GPT-6 Sol, Claude Opus 5 and the other models that tier lists. On a plan its calls draw that tier's allowance, which every model in the tier shares, and calls beyond it are billed to the wallet at the posted rates. GPT-6 Astra sits in the Flagship models tier that only Max and Ultra carry. Plan model lists change; the pricing page lists each plan's allowance and the live model lists.

Send the first request

1. Create a key. Dashboard → API Keys → Create Key. Keys look like sk-.... For a trial, give the key a maxSpend cap: it cannot spend past that amount, and your other keys keep working (per-key cost tracking).
2. Keep a plan or a wallet balance. On Pro, Max or Ultra, Gemini 4 Argon calls draw the Premium models allowance first (2026-10-14 plan response); without a plan, and beyond the allowance, they bill the wallet — top up in Dashboard → Deposit.
3. Set the base URL to https://api.router.one/v1 in any OpenAI-compatible SDK or client.
4. Call the model. The examples use the catalog id google/gemini-4-argon and set max_tokens explicitly.

Chat Completions with curl, streaming:

curl https://api.router.one/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-4-argon",
    "max_tokens": 32768,
    "stream": true,
    "messages": [
      {"role": "system", "content": "You review SQL migrations. Answer in three short bullet points."},
      {"role": "user", "content": "What does this migration change, and what is one risk? ALTER TABLE orders ADD COLUMN archived_at TIMESTAMP;"}
    ]
  }'

The same request without streaming, from the OpenAI Python SDK (pip install -U openai) — only base_url and the key change:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.router.one/v1",
    api_key="sk-your-api-key",
)

response = client.chat.completions.create(
    model="google/gemini-4-argon",
    max_tokens=32768,
    messages=[
        {"role": "system", "content": "You review SQL migrations. Answer in three short bullet points."},
        {"role": "user", "content": "What does this migration change, and what is one risk? ALTER TABLE orders ADD COLUMN archived_at TIMESTAMP;"},
    ],
)
print(response.choices[0].message.content)
print(response.choices[0].finish_reason, response.usage)

The reply has the Chat Completions shape: the text is in choices[0].message.content, finish_reason says why generation stopped, and usage carries the input and output token counts.

Streaming from Node with the OpenAI SDK (npm install openai):

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.router.one/v1",
  apiKey: "sk-your-api-key",
});

const stream = await client.chat.completions.create({
  model: "google/gemini-4-argon",
  max_tokens: 32768,
  stream: true,
  messages: [
    {
      role: "user",
      content:
        "What does this migration change, and what is one risk? ALTER TABLE orders ADD COLUMN archived_at TIMESTAMP;",
    },
  ],
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

An image, sent inline as a base64 data URL (Python, same client as above):

import base64

with open("chart.png", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="google/gemini-4-argon",
    max_tokens=32768,
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Summarize what this chart shows in two sentences."},
            {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_b64}"}},
        ],
    }],
)
print(response.choices[0].message.content)

Rules that hold for every request:

• Set max_tokens on every request. Leave room above the longest answer you expect; the samples above set 32768. On Router One's Chat Completions, max_completion_tokens is accepted as the same cap (if both are sent, max_completion_tokens wins).
• Stream long answers. stream: true returns output as it is generated (streaming guide).
• Keep a healthy wallet balance for wallet-billed calls. Before a request runs, the gateway reserves an estimate against your balance; when the balance cannot cover it, the gateway lowers max_tokens to fit, which can cut a long answer short. If it cannot cover even the request's initial reservation, the gateway returns HTTP 402 before the model runs.
• Send images inline. Pass images as base64 data URLs in image_url content parts, as in the example above; Router One serves no Files API.
• Test what your code depends on. Before you move a workload, run the parameters and request shapes your code sends (tool definitions, image inputs, output caps) on your own prompts first.

5. Read the trace. Dashboard → Logs shows each call with model, input and output tokens, cost, latency and status (per-request observability). Retryable upstream failures are absorbed by automatic fallback across the candidate routes for the same model; a Gemini 4 Argon request is never answered by a different model.

A request the gateway refuses before any model is called has no row in Dashboard → Logs; its status code and error message say why. A 401 means the key was not accepted, a 402 that the wallet balance or the key's maxSpend cannot cover the request's initial reservation, and a 404 that the path or the model id does not exist, so copy the id exactly as the catalog lists it. The error codes page covers the rest.

Which clients can call it

Any client that speaks Chat Completions and takes a custom base URL can call Gemini 4 Argon: the official OpenAI SDKs (OpenAI SDK setup) and the chat apps and frameworks in the integrations directory that send /v1/chat/completions requests. Give the client the base URL https://api.router.one/v1 and a Router One key, and enter google/gemini-4-argon as the model; the OpenAI-compatible API page explains the endpoint in general.

Claude Code cannot call Gemini 4 Argon. Claude Code sends Anthropic Messages requests to /v1/messages, which Router One serves for Claude-family and DeepSeek ids only. For any other chat id the catalog lists, the gateway returns HTTP 400 before any model is called; for this one the message reads model 'google/gemini-4-argon' must be called via /v1/chat/completions. Keep Claude Code on Claude ids (Claude Code in China) and call Gemini 4 Argon from a Chat Completions client. The API compatibility facts state the endpoint rule for each model family.

From mainland China

Requests reach api.router.one from mainland China without a VPN, on the same key and base URL. Top up with a card or Alipay through one hosted checkout, or with USDT/USDC on six chains (Tron, BSC, Ethereum, Polygon, Base, Arbitrum). No US credit card required. For the other Gemini models Router One lists, see the Gemini API in China page and the Gemini API in China guide.

FAQ

What is the model id for Gemini 4 Argon on Router One? The catalog id is google/gemini-4-argon, as of the 2026-10-14 catalog; use it in code and client settings. The gateway also accepts Google's own id, gemini-4-argon, for the same catalog entry on /v1/chat/completions. On a Pro, Max or Ultra plan, calls draw the Premium models allowance (as of the 2026-10-14 plan response); without a plan, they bill per token to the wallet.

Which endpoint serves Gemini 4 Argon, and can I use the OpenAI SDK? POST /v1/chat/completions, Router One's OpenAI-compatible endpoint. Point the OpenAI SDK or any OpenAI-compatible client at https://api.router.one/v1 with a Router One key and set the model to google/gemini-4-argon. Router One does not serve it on /v1/messages.

Can I use Gemini 4 Argon in Claude Code? No. Claude Code sends Anthropic Messages requests to /v1/messages, which Router One serves for Claude-family and DeepSeek ids only, so a Gemini 4 Argon request there returns HTTP 400 before any model is called, with the message "model 'google/gemini-4-argon' must be called via /v1/chat/completions". Call Gemini 4 Argon from a Chat Completions client and keep Claude Code on Claude ids.

Is Gemini 4 Argon included in Router One subscription plans? Yes, as of the 2026-10-14 plan response: it is in the Premium models tier of the Pro, Max and Ultra plans, so on a plan its calls draw that tier's allowance, and calls beyond it are billed to the wallet at the posted rates. The pricing page lists each plan's allowance.

How is Gemini 4 Argon billed without a plan? Per token, from the wallet, at the input and output rates posted on the Gemini 4 Argon model page; this guide prints no figures because they go stale. Dashboard → Logs lists the calls with their tokens and cost.

Does Gemini 4 Argon take images, and does it support streaming and tool calling? The 2026-10-14 catalog entry lists text and image input, text output and the chat, streaming, tool-calling and vision flags. Send images inline as base64 data URLs in image_url content parts (Router One serves no Files API), and test the request shapes your code depends on, tool definitions included, on your own prompts before you move a workload.

Can I call Gemini 4 Argon from mainland China? Yes: api.router.one is reachable from mainland China without a VPN, on the same key and base URL. Top up with a card or Alipay through one hosted checkout, or with USDT/USDC on six chains; no US credit card is required.

Do I need Google's SDK or the Gemini API's native request format? No. Router One serves Gemini 4 Argon on its OpenAI-compatible Chat Completions endpoint, so you call it with the OpenAI SDK or any OpenAI-compatible client and a Router One key. Existing Chat Completions code moves over by changing the base URL, the key and the model string; then test the parameters it sends on your own prompts.

Next steps

• Open the Gemini 4 Argon model page for the live rates and the endpoint.
• Check each plan's allowance and the models each tier lists on the pricing page.
• Calling other Gemini models from mainland China? See the Gemini API in China page and the Gemini API in China guide.
• New to OpenAI-compatible endpoints? The OpenAI-compatible API page covers base URLs, keys and SDKs.
• Weighing a GPT model on the same Premium models allowance? Read the GPT-6.1 Sol API guide.
• See this month's other catalog changes in the October 2026 new-model guide.