Skip to content
OfferSign up and get $10 of credit for any model in Chat and the API. Top up from $1, with no processing fees. See free models →·Some free models are at the daily cap — refills 05:30 IST; requests auto-route to a live backup. Status →
One AI API Key
Get API key

Google · Gemini · Flagship

Gemini 4 Argon

Discount −73%New

Google's flagship reasoning model for software engineering, maths, science and multi-step agents.

Model id

gemini-4-argon
Get an API keyTry in Chat

Price per 1M tokens

Input
Regular rate $2.00now $0.525
Output
Regular rate $10.00now $2.625
Cached input
$0.1081% below input

73% below the market rate.

Added here 18 Oct 2026 — read the changelog for what changed and why.

Output is 5× the input rate. $1 covers about 544 prompts of 1,000 input + 500 output tokens. 1 credit = $1 of usage. All rates

Start using Gemini 4 Argon

Set ONEAIAPIKEY_API_KEY to a key from your console, then run any example. Streaming is on so long answers are not cut off by idle-connection timeouts.

curl https://api.oneaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEAIAPIKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-4-argon",
    "stream": true,
    "messages": [{"role": "user", "content": "Show step by step whether the series of 1/(n log n) converges."}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oneaiapikey.com/v1",
    api_key=os.environ["ONEAIAPIKEY_API_KEY"],
)

stream = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[{"role": "user", "content": "Show step by step whether the series of 1/(n log n) converges."}],
    stream=True,  # recommended for long outputs
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.oneaiapikey.com/v1",
  apiKey: process.env.ONEAIAPIKEY_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "gemini-4-argon",
  messages: [{ role: "user", content: "Show step by step whether the series of 1/(n log n) converges." }],
  stream: true,
});

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

More: quickstart · API reference · try it in Chat first

Benchmarks reported by the vendor

Scores for Gemini 4 Argon as its maker published them, with the setting they state. We have not re-run them. Versions and settings differ between vendors, so compare only identical benchmark names; compare models side by side.

Tokens per day, by model

Last 7 days, UTC days

Hover, tap or drag across any day, or focus the chart and use the arrow keys, to see how every model did that day.

Real tokens served through this gateway, updated every 5 minutes. Ranked by usage, not quality.

Full ranking insights

Nearest alternative

Gemini 4 Argon or Step 5 Preview?

Gemini 4 Argon is the only Gemini model here. Step 5 Preview from StepFun is the closest-priced flagship-tier model from another vendor. Each comparison lists the published rates and limits, then what favours each side.

Gemini 4 ArgonvsStep 5 Preview

Per 1M tokensGemini 4 ArgonStep 5 Preview
Input$0.52525% less$0.70
Output$2.6339% more$1.89
Cached input$0.10the same$0.10
Context1Mthe same1M
Max output64kthe same64k

Pick Gemini 4 Argon when

  • cost per request decides it: Gemini 4 Argon charges input 25% less than Step 5 Preview.
  • the work is maths and science, which this catalogue lists for Gemini 4 Argon and not for Step 5 Preview.

Pick Step 5 Preview instead when

  • the job runs well enough on the lower rates: output at 28% less.
  • your workload looks like research, a label the catalogue gives Step 5 Preview only.

Use cases

What Gemini 4 Argon is listed for, and what it costs

The catalogue lists Gemini 4 Argon for software engineering, maths and science and agents. Each row prices one typical request at the published rates, with the arithmetic shown. The market-rate figure shows the same request at the lowest public price elsewhere. Token counts are examples; your prompts will differ.

Model your own traffic

  1. Software engineering

    Implementing a function or endpoint: 8,000 tokens of context in, 2,000 tokens of code out.

    “Write a TypeScript endpoint that returns paginated orders for the signed-in user.”

    Same request on Step 5 Preview $0.00938.

    $0.00945

    per task, about 1,058 per $10

    $0.036 at the market rate

    0.008 × $0.525 + 0.002 × $2.63

  2. Maths and science

    A calculation or proof with every step shown: 1,000 tokens in, 6,000 tokens out.

    “Show step by step whether the series of 1/(n log n) converges.”

    Same request on Step 5 Preview $0.01204.

    $0.016276

    per problem, about 614 per $10

    $0.062 at the market rate

    0.001 × $0.525 + 0.006 × $2.63

  3. Agents

    One step of a tool-using agent: 20,000 tokens of instructions, tool results and history, 15,000 of them cached, and 1,000 tokens of tool calls and notes out.

    “Check the order status for each customer in this list and draft a reply to the late ones.”

    Same request on Step 5 Preview $0.00689.

    $0.00675

    per agent step, about 1,481 per $10

    $0.0215 at the market rate

    0.005 × $0.525 + 0.015 × $0.10 + 0.001 × $2.63

Overview

When Gemini 4 Argon fits

Gemini 4 Argon is a flagship model from Google, available here under the exact model id “gemini-4-argon”. It is currently the only Gemini model we serve. Google has not published a release date we can cite; it has been available here since 18 Oct 2026.

Google documents tools, vision, reasoning, structured output and prompt caching for it, and it reads images as well as text.

It costs $0.525 per million input tokens and $2.63 per million output tokens, so output is 5× the input rate. That is 73% below the market rate of $2 input and $10 output per million tokens, the lowest public price we found at other API gateways. On the use cases below, output makes up 56% of the bill for software engineering, 97% for maths and science and 39% for agents, so capping max tokens and asking for diffs saves more than trimming the prompt. With a 3:1 input-to-output mix it ranks 14th lowest-cost of the 27 models on this site.

Cached input bills at $0.10 per million tokens, 81% below the standard input rate. In the agents example, 15k of the 20k input tokens come from cache, which brings one agent step from $0.013126 down to $0.00675.

It is served through the OpenAI-compatible format at https://api.oneaiapikey.com/v1, so any SDK or tool that lets you set a custom base URL, for example Codex CLI, Cursor and Cline, can use it. It is not offered on the Anthropic Messages endpoint; pick an Anthropic-format model for Claude Code.

Similar models

Same tier, other vendors

Same key, same balance. Switching is a change to the model field.

Compare side by sideAll models

Use Gemini 4 Argon with any balance.

Gemini 4 Argon is a paid model: any balance above $0 pays for it, the $10.00 sign-up credit included. When it runs out, add $1 or more to your wallet. Every request is billed at the rates above, with a receipt in your usage log.

Create an accountSee pricing

Gemini 4 Argon is developed by Google. Model names and trademarks belong to their owners. One AI API Key is an independent API gateway and is not affiliated with, endorsed by or sponsored by Google.