Gemini 4 Argon on GCP Vertex AI

Gemini 4 · Google DeepMind

ServerlessProvisioned

Last refreshed 2026-10-17. Next refresh: weekly.

Why use Gemini 4 Argon on GCP Vertex AI?

GCP Vertex AI offers Gemini 4 Argon with pay-as-you-go pricing at $2.00/1M input tokens. Vertex AI is Google Cloud's managed AI platform, offering access to Gemini models and hundreds of partner models alongside tools for fine-tuning, grounding, vector search, and end-to-end MLOps pipelines.

Compare Gemini 4 Argon across 4 providers to find the best fit for your use case
Input / 1M
$2.00
Output / 1M
$10.00
Cache
read $0.10
Batch
-50% · in $1.00 / out $5.00

Setup recipe

Python + curl
Install
pip install google-cloud-aiplatform
Auth
export GOOGLE_CLOUD_PROJECT=...
Call
import os
import vertexai
from vertexai.generative_models import GenerativeModel
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
Model ID
gemini-4-argon

Request example

import os
import vertexai
from vertexai.generative_models import GenerativeModel

# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("gemini-4-argon")
response = model.generate_content("Hello")
print(response.text)

Gotchas

  • For Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".
  • The examples expect GOOGLE_CLOUD_PROJECT; rename it only if your application config maps the new variable.

Compare Gemini 4 Argon Across Providers

ProviderInput (per 1M)Output (per 1M)
Google AI Studio$2.00$10.00
GCP Vertex AI$2.00$10.00
OpenRouter$2.00$10.00
Vercel AI Gateway$2.00$10.00

Pricing

TypePrice (per 1M)
Input tokens$2.00
Output tokens$10.00
Pricing notes

Gemini Enterprise Agent Platform (Vertex AI) generative AI pricing page (retrieved 2026-10-17), Gemini 4 Argon. Standard global: input $2 / cached $0.1; output $10 through November 30, 2026; $4 / $0.2 / $20 starting December 1, 2026. Non-global $2.2 / $0.11 / $11 (then $4.4 / $0.22 / $22). Batch global $1 / $0.05 / $5 (then $2 / $0.1 / $10). Priority global $3.6 / $0.18 / $18 (then $7.2 / $0.36 / $36). Promotional rate is applied as 50% credits back on net spend. Provisioned Throughput supported (Vertex model page).

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch APIAudioVideo

About Gemini 4 Argon

Gemini 4 Argon is a Google DeepMind reasoning model, announced on September 30, 2026 for trusted cyber defenders and testers in Google's Fairwind Program and made generally available on October 13, 2026 through the Gemini API, Gemini Enterprise Agent Platform, Google Antigravity and the Gemini app. Google built it for long-horizon software engineering, legal and finance work, cybersecurity defense and science. It takes text, image, video, audio and PDF input and returns text. Input and output share a 1,048,576-token limit; one synchronous request returns up to 65,536 output tokens, and long decodes extend output up to 1,048,576 tokens.

Get Started

Model Specs

Released2026-09-30
Context1M

Related Models on GCP Vertex AI

Provider

GCP Vertex AI

Google Cloud Platform (GCP)

All models on GCP Vertex AI →