Gemini 4 Argon

Chat Completions

gemini-4-argon

Google|Created Oct 17, 2026|1.0M context

Chat Completions

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Pricing-50%

Pay-as-you-go rates for this model. More details in the billing guide.

Input Tokens (1M)

$0.50

Cached Input Tokens (1M)

$0.02

Output Tokens (1M)

$2.50

Capabilities

Input Modalities

TextImageAudioFile

Supported Parameters

Available parameters for API requests

Max Completion TokensReasoning EffortResponse FormatStopTemperatureTool ChoiceToolsTop PWeb Search OptionsImage ConfigFrequency PenaltyLogit BiasParallel Tool CallsPresence PenaltyPrediction

Usage Analytics

Token usage of this model on our platform

Not enough activity data to display a chart

Throughput

Not enough throughput data

Time-To-First-Token (TTFT)

Not enough TTFT data

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[
        {"role": "user", "content": "What's 2+2?"}
    ],
    temperature=0.2,
)
print(resp.choices[0].message.content)

Gemini 4 Argon

Input Tokens (1M)

Cached Input Tokens (1M)

Output Tokens (1M)

Input Modalities

Gemini 4 Argon

Input Tokens (1M)

Cached Input Tokens (1M)

Output Tokens (1M)

Input Modalities

Output Modalities