Name: Google: Gemini 4 Argon
Creator: google
Published: 2026-10-13T16:04:37.000Z

Overview

Model specifications

Context: 1,048,576 tokens
Maximum output: 943,718 tokens
Architecture: text+image+file+audio+video->text
Tokenizer: Gemini
Knowledge cutoff: Not provided
Moderated: No

OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input: $2
Output: $10
Cache read: $0.1
Cache write: $0.1875
Image input: $2
Audio input: $2
Input Audio Cache: $0.1
Web search: $14

API

Model configuration

Reasoning

Reasoning required: Yes
Default parameters: medium
Capabilities: high, medium, low

API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-4-argon","messages":[{"role":"user","content":"Hello!"}]}'

Capabilities

Input → Output

Input

audiofileimagetextvideo

Output

text

Reasoning

No · high · medium · low

API

Supported API parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Available providers

6 providers

Checked: October 19, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Google AI Studio

Not provided

Context: 1.0M
Maximum output: 944K
Input: $1
Output: $5
Cache read: $0.05
Cache write: $0.0938

Google

Not provided

Context: 1.0M
Maximum output: 944K
Input: $2
Output: $10
Cache read: $0.1
Cache write: $0.1875

Google AI Studio

Not provided

Context: 1.0M
Maximum output: 944K
Input: $2
Output: $10
Cache read: $0.1
Cache write: $0.1875

Google

Not provided

Context: 1.0M
Maximum output: 66K
Input: $2.2
Output: $11
Cache read: $0.11
Cache write: $0.1875

Google

Not provided

Context: 1.0M
Maximum output: 944K
Input: $3.6
Output: $18
Cache read: $0.18
Cache write: $0.3375

Google AI Studio

Not provided

Context: 1.0M
Maximum output: 944K
Input: $3.6
Output: $18
Cache read: $0.18
Cache write: $0.3375

Google: Gemini 4 Argon (batch)

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...

Context

1.0M

Input

audio · file · image · text · video

Output

text

Input: $1Output: $5per 1M tokens

View model details →

Google: Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

Context

66K

Input

image · text

Output

image · text

Input: $1.5 per 1M tokensOutput: $7.5 per 1M tokens

View model details →

Google: Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio...

Context

98K

Input

audio

Output

transcription

Input: $2 per 1M tokensOutput: $12 per 1M tokens

View model details →

Google: Gemini 4 Argon

Model specifications

Complete pricing

Model configuration

Reasoning

Quick start

Input → Output

Supported API parameters

6 providers

Google AI Studio

Google

Google AI Studio

Google

Google

Google AI Studio

4 models