티스토리 수익 글 보기

티스토리 수익 글 보기

Gemini platform | Google Cloud

Try Gemini 4 Argon, built to help solve your business’s hardest problems

Gemini icon

Gemini platform

Innovate, build, and deploy enterprise-ready agents and apps

Gemini platform enables technical teams to build agents that can transform enterprise applications and workflows into powerful agentic systems.

Features

Build, scale, govern, and optimize enterprise grade AI agents

Gemini platform is our open and comprehensive platform that empowers businesses to rapidly build, scale, govern and optimize enterprise-grade agents grounded in your enterprise data. It provides the full-stack foundation and extensive developer choice you need to transform your applications and workflows into powerful agentic systems at global scale.

Scale agents from Gemini platform to your organization
Use Gemini to securely register, manage, and govern your custom-built agents.
Learn about Gemini

Agent-powered development and workflows

Now available through Gemini platform, Google Antigravity provides a centralized app to steer, customize, and orchestrate agents. You can deploy multiple agents to simultaneously execute entire workflows like product launches—automating the code generation for your website, on-brand asset creation, and customer email production. Download Antigravity and log in to the desktop application or Antigravity CLI using your standard Google Cloud credentials.

200+ Google and third-party AI models and tools

Choose from Google’s latest multimodal models like Gemini 4 Argon, third-party models like Anthropic's Claude Model Family, and open models like Gemma in Model Garden. You can also customize models to your use case with a variety of tuning options.

Our Model Evaluation service provides enterprise-grade tools for objective, data-driven assessment of generative AI models.

Gemini icon
Register to learn how AI agents are serving as dual engines for both cost savings and revenue generation

Open and integrated AI platform

Data scientists can move faster with Gemini platform tools for training, tuning, and deploying ML models.

Notebooks in Gemini platform, including your choice of Colab Enterprise or Workbench, are natively integrated with BigQuery providing a single surface across all data and AI workloads.

Training and Prediction in Gemini platform help you reduce training time and deploy models to production easily with your choice of open source frameworks and optimized AI infrastructure.

MLOps for predictive and generative AI

Gemini platform provides purpose-built MLOps tools for data scientists and ML engineers to automate, standardize, and manage ML projects.

Modular tools help you collaborate across teams and improve models throughout the entire development lifecycle—identify the best model for a use case with Model Evaluation, orchestrate workflows with Pipelines, manage any model with Model Registry serve, share, and reuse ML features with Feature Store, and monitor models for input skew and drift.

MLOps with Gemini platform: Model Evaluation
No cost training
Get started

How It Works

Gemini platform provides several options for agent building, model training and deployment:

  • Gemini platform enables you to build, scale, govern and optimize enterprise ready agents in one unified platform
  • Agent Studio gives you access to large generative AI models, including Gemini 4 Argon, so you can evaluate, tune, and deploy them for use in your AI-powered applications
  • Model Garden lets you discover, test, customize, and deploy in Gemini platform and select open-source (OSS) models and assets
  • Custom training gives you complete control over the training process, including using your preferred ML framework, writing your own training code, and choosing hyperparameter tuning options

Common Uses

Build and deploy AI agents

Unlock advanced AI capabilities with Gemini platform

Build production-ready generative AI agents and applications on a platform that scales with you. Gemini platform provides a secure environment for developing and deploying AI models and applications.

For developers, Gemini platform remains our advanced platform where you can build, customize, and fine-tune sophisticated agents using frameworks like the Agent Development Kit (ADK).

Generative AI UI in Gemini platform

Get started with this codelab and build your first AI application today

Unlock advanced AI capabilities with Gemini platform

Build production-ready generative AI agents and applications on a platform that scales with you. Gemini platform provides a secure environment for developing and deploying AI models and applications.

For developers, Gemini platform remains our advanced platform where you can build, customize, and fine-tune sophisticated agents using frameworks like the Agent Development Kit (ADK).

Generative AI UI in Gemini platform

Get started with this codelab and build your first AI application today

Build with Gemini models

Start building with Agent Studio

Use Agent Studio to design, test, and manage prompts for Gemini models using natural language, code, images, or video. Try sample prompts for extracting text from images, image mock up to HTML, and even generate answers about uploaded images or videos.

You can also start testing Gemini models on Gemini platform with an API key.

Generative AI Model Garden dashboard view

Start building with Agent Studio

Use Agent Studio to design, test, and manage prompts for Gemini models using natural language, code, images, or video. Try sample prompts for extracting text from images, image mock up to HTML, and even generate answers about uploaded images or videos.

You can also start testing Gemini models on Gemini platform with an API key.

Generative AI Model Garden dashboard view
Access Gemini models via the Gemini API in Gemini platform
View code samples for Python, JavaScript, Java, Go, and Curl
  • Python
  • JavaScript
  • Java
  • Go
  • Curl
Loading...

Extract, summarize, and classify data

Use gen AI for summarization, classification, and extraction

Learn how to create text prompts for handling any number of tasks with Gemini platform's generative AI support. Some of the most common tasks are classification, summarization, and extraction. Gemini platform lets you design prompts with flexibility in terms of their structure and format.

Data in a spreadsheet

Use gen AI for summarization, classification, and extraction

Learn how to create text prompts for handling any number of tasks with Gemini platform's generative AI support. Some of the most common tasks are classification, summarization, and extraction. Gemini platform lets you design prompts with flexibility in terms of their structure and format.

Data in a spreadsheet

Deploy a model for production use

Deploy for batch or online predictions

When you're ready to use your model to solve a real-world problem, register your model to Model Registry and use the Gemini platform prediction service for batch and online predictions. 

ML model prediction

Watch Prototype to Production, a video series that takes you from notebook code to a deployed model.

Deploy for batch or online predictions

When you're ready to use your model to solve a real-world problem, register your model to Model Registry and use the Gemini platform prediction service for batch and online predictions. 

ML model prediction

Watch Prototype to Production, a video series that takes you from notebook code to a deployed model.

Train custom Models

Custom Model training overview and documentation

Get an overview of the custom training workflow in Gemini platform, the benefits of custom training, and the various training options that are available. This page also details every step involved in the ML training workflow from preparing data to predictions.

Google Gemini platform tracker status

Get a video walkthrough of the steps required to train custom models on Gemini platform.

Custom Model training overview and documentation

Get an overview of the custom training workflow in Gemini platform, the benefits of custom training, and the various training options that are available. This page also details every step involved in the ML training workflow from preparing data to predictions.

Google Gemini platform tracker status

Get a video walkthrough of the steps required to train custom models on Gemini platform.

Generate a solution
What problem are you trying to solve?
What you'll get:
Step-by-step guide
Reference architecture
Available pre-built solutions
This service was built with Gemini. You must be 18 or older to use it. Do not enter sensitive, confidential, or personal info.

Pricing

How Gemini platform pricing worksPay for Gemini platform tools, storage, compute and Cloud resources used. New customers get $300 free credits to try Gemini platform and Google Cloud products.
Tools and usageDescriptionPrice

Generative AI

Imagen model for image generation

Based on image input, character input, or custom training pricing. 

Starting at

$0.0001

Text, chat, and code generation

Based on every 1,000 characters of input (prompt) and every 1,000 characters of output (response).

Starting at

$0.0001

per 1,000 characters

Custom-trained models

Custom model training

Based on machine type used per hour, region, and any accelerators used. Get an estimate using sales or our pricing calculator. 

Contact sales

Notebooks in Gemini platform

Compute and storage resources

Based on the same rates as Compute Engine and Cloud Storage.

Refer to products

Management fees

In addition to the above resource usage, management fees apply based on region, instances, notebooks, and managed notebooks used. View details.

Refer to details

Pipelines in Gemini platform

Execution and additional fees

Based on execution charge, resources used, and any additional service fees. 

Starting at

$0.03

per pipeline run

Vector Search in Gemini platform

Serving and building costs

Based on the size of your data, the amount of queries per second (QPS) you want to run, and the number of nodes you use. View example.

Refer to example

View pricing details for all Gemini platform features and services. 

How Gemini platform pricing works

Pay for Gemini platform tools, storage, compute and Cloud resources used. New customers get $300 free credits to try Gemini platform and Google Cloud products.

Generative AI

Description

Imagen model for image generation

Based on image input, character input, or custom training pricing. 

Price

Starting at

$0.0001

Text, chat, and code generation

Based on every 1,000 characters of input (prompt) and every 1,000 characters of output (response).

Description

Starting at

$0.0001

per 1,000 characters

Custom-trained models

Description

Custom model training

Based on machine type used per hour, region, and any accelerators used. Get an estimate using sales or our pricing calculator. 

Price

Contact sales

Notebooks in Gemini platform

Description

Compute and storage resources

Based on the same rates as Compute Engine and Cloud Storage.

Price

Refer to products

Management fees

In addition to the above resource usage, management fees apply based on region, instances, notebooks, and managed notebooks used. View details.

Description

Refer to details

Pipelines in Gemini platform

Description

Execution and additional fees

Based on execution charge, resources used, and any additional service fees. 

Price

Starting at

$0.03

per pipeline run

Vector Search in Gemini platform

Description

Serving and building costs

Based on the size of your data, the amount of queries per second (QPS) you want to run, and the number of nodes you use. View example.

Price

Refer to example

View pricing details for all Gemini platform features and services. 

Pricing calculator

Estimate your Gemini platform costs, including region-specific pricing and fees.

Custom quote

Connect with our sales team to get a custom quote for your organization.

Start your proof of concept

New customers get up to $300 in free credits to try Gemini platform and other Google Cloud products

Have a large project?

Browse, customize, and deploy machine learning models

Learn how to set up a Gemini platform project environment

Get started with notebooks for machine learning

Business Case

Unlock the full potential of gen AI

GA Telesis logo

"The accuracy of Google Cloud's generative AI solution and practicality of the Gemini platform gives us the confidence we needed to implement this cutting-edge technology into the heart of our business and achieve our long-term goal of a zero-minute response time."

Abdol Moabery, CEO of GA Telesis

Analyst reports

Google named a Leader in the 2025 IDC MarketScape for Worldwide GenAI Life-Cycle Foundation Model Software. Download the report

Google Named a Leader in the Gartner Magic Quadrant™ for AI Application Development Platforms, Q4 2025. Read the report

Google named a leader in the Forrester Wave™: AI/ML Platforms, Q3 2024. Read the report

FAQ

How much does Gemini platform cost?

The cost of the Gemini platform is usage-based and flexible, derived from the specific AI models deployed and infrastructure usage. For models, users pay based on token consumption through several payment tiers—including standard Pay-as-you-go (PayGo), discounted Flex PayGo for latency-tolerant jobs, and premium Priority PayGo for higher reliability—or via Provisioned Throughput subscriptions for predictable, guaranteed throughput. 

Additional infrastructure charges, with the exception of those not available through Gemini platform such as Model Armor or Observability, are metered via three unified dimensions: Agent Compute (vCPU), Agent Memory (RAM), and Agent Storage (GiB) (plus token pass-through). Because expenses vary heavily by model and scale, users should consult contact sales to get granular estimates or explore volume-based enterprise discounts.

Document retrieval on the Gemini platform is handled by Agent Search. The billing is primarily usage-based, calculated per 1,000 successful search queries alongside standard storage charges for indexed data (billed per GiB/month). Standard semantic or keyword-based document retrieval is billed at approximately $4.00 per 1,000 queries, covering tasks like scanning the index, returning document snippets, and querying enterprise connectors.

Yes, Google Cloud offers a free trial that applies directly to the Gemini platform, allowing new users to explore and build AI agents without financial commitment. Eligible new users receive a standard $300 Google Cloud free trial credit valid for 90 days, which can be applied directly toward Gemini platform usage, including agent runtime compute processing, active memory, and underlying generative model queries. In addition to this promotional welcome credit, the platform provides continuous monthly Free Tier allowances (per billing account, per month) for core infrastructure, covering the first 50 hours (180,000 vCPU-seconds) of compute, the first 100 hours (360,000 GiB-seconds) of RAM, and the first 1 gibibyte of storage for agent runtimes. This setup makes it easy for users to prototype agentic workflows, integrate private data stores, and launch pilot programs at no initial cost.

Google Cloud
send
    DocsSupport
    Console
    Sign in
    • Accelerate your digital transformation
    • Whether your business is early in its journey or well on its way to digital transformation, Google Cloud can help solve your toughest challenges.
    • Featured Products
    • Business Intelligence
    • Hybrid and Multicloud
    • Industry Specific
    • Media Services
    • Productivity and Collaboration
    • Save money with our transparent approach to pricing
    • Google Cloud's pay-as-you-go pricing offers automatic savings based on monthly usage and discounted rates for prepaid resources. Contact us today to get a quote.
    Google Cloud