Gemini Code Assist offers AI-powered assistance to help your development team build, deploy, and operate applications throughout the software development lifecycle, using the Gemini 2.5 model. Gemini Code Assist is available in the following editions:
-
Gemini Code Assist for individuals , available at no cost.
-
Gemini Code Assist Standard , a product in the Gemini for Google Cloud portfolio.
-
Gemini Code Assist Enterprise , a product in the Gemini for Google Cloud portfolio.
You can use Gemini Code Assist in supported IDEs , such as VS Code, JetBrains IDEs, or Android Studio, for AI-powered coding assistance in many popular languages . You can get code completions as you write your code, generate full functions or code blocks from comments, generate unit tests, and get help with debugging, understanding, and documenting your code.
Gemini Code Assist provides contextualized responses to your prompts, including source citations regarding which documentation and code samples Gemini Code Assist used to generate its responses.
The Gemini large language models (LLMs) that are used by Gemini Code Assist are trained on datasets of publicly available code, Google Cloud-specific material, and other relevant technical information in addition to the datasets used to train the Gemini foundation models . Models are trained so that Gemini Code Assist responses are as useful to Gemini Code Assist users as possible.
- Learn how and when Gemini Code Assist Standard and Enterprise use your data .
- Learn how and when Gemini Code Assist for individuals uses your data .
As an early-stage technology, Gemini Code Assist can generate output that seems plausible but is factually incorrect. We recommend that you validate all output from Gemini Code Assist before you use it. For more information, see Gemini Code Assist and responsible AI .
Gemini Code Assist provides citation information when it directly quotes at length from another source, such as existing open source code. For more information, see How and when Gemini cites sources .
Supported features for Gemini Code Assist for individuals
The following table shows the types of generative AI assistance that are available in supported IDEs at no cost:
Code completion and generation in your IDE project in the following IDEs:
Prompt Gemini to complete complex, multi-step tasks that use system tools and Model Context Protocol (MCP) servers. For more information, see Use agentic chat as a pair programmer .
Quota for using Gemini CLI .
/
on the quick pick bar either with or without selected code ( VS Code
).@
symbol followed by the name of
the tool. For example— @GitHub get issues assigned to me
. For
more information about tools, see the Gemini Code Assist tools overview
.Gemini Code Assist Standard and Enterprise editions overview
The following section compares the Gemini Code Assist Standard and Enterprise editions.
The Standard edition offers AI coding assistance, with enterprise-grade security, for building and running applications. The Enterprise edition offers all of the supported features in the Standard edition, but you can also customize it based on your private source code repositories, and it's integrated with additional Google Cloud services for building applications across a broader tech stack.
The following table helps you to decide which edition aligns best with your organization's development goals by highlighting the intended audience and the benefits for each edition:
- Customers with basic coding needs.
- Organizations with strict data security and compliance requirements.
- Large enterprises with complex software development processes.
- Customers wanting to have AI response customized based on private source code repositories to accelerate development based on organizational best practices.
- Customers needing AI-powered application development assistant across an expanding list of Google Cloud services.
- Code completion and generation for popular programming languages, and available across some Google Cloud services.
- AI-powered chat support.
- Simplified user interface and integration with IDEs.
- Local codebase awareness in your IDE: Use the power of Gemini's large context window for in-depth local codebase understanding.
- Enterprise-grade security: Robust data governance, secure infrastructure, and indemnification for code suggestions.
- Extended integrations: Gemini Code Assist Standard provides AI assistance in Firebase, Colab Enterprise, BigQuery data insights, Cloud Run, and Database Studio.
- All of the benefits mentioned for Gemini Code Assist Standard, with the addition of the following:
- Code customization : Your organization can augment the model with your private codebases for tailored suggestions.
- Extended integrations: Gemini Code Assist Enterprise provides AI assistance across Google Cloud like Apigee, Application Integration, and Gemini Cloud Assist, empowering cloud teams to build, design and operate, and optimize their applications and infrastructure more effectively on Google Cloud.
For a comparison of each edition's features, see Supported features .
Supported features for Gemini Code Assist Standard and Enterprise
The following sections show the types of generative AI assistance that are available in Gemini Code Assist Standard and Enterprise.
Code assistance and chat
The following table shows the types of generative AI assistance that are available in supported IDEs :
Code completion and generation in your IDE project in the following IDEs:
Prompt Gemini to complete complex, multi-step tasks that use system tools and Model Context Protocol (MCP) servers. For more information, see Use agentic chat as a pair programmer .
/
on the quick pick bar either with or without selected code ( VS Code
.@
symbol followed by the name of
the tool. For example— @GitHub get issues assigned to me
. For
more information about tools, see the Gemini Code Assist tools overview
.Additional features outside the IDE
The following sections detail additional features available with the Gemini Code Assist Standard and Enterprise editions that go beyond assistance in your IDE.
Gemini Cloud Assist
The following table shows the types of generative AI assistance in Gemini Cloud Assist in the API Console:
| Gemini Cloud Assist assistance | Gemini Code Assist Standard | Gemini Code Assist Enterprise |
|---|---|---|
|
Gemini Cloud Assist features
(including features available to all Google users and available to Gemini Code Assist Enterprise users)
|
Gemini in Apigee
The following table shows the types of generative AI assistance with API development in Apigee (IDE and the Google API Console):
| Gemini Code Assist for API management | Gemini Code Assist Standard | Gemini Code Assist Enterprise |
|---|---|---|
|
Enterprise context
used when creating API specifications.
|
||
Gemini in Application Integration
The following table shows the types of generative AI assistance in Application Integration in the API Console:
| Integration creation assist | Gemini Code Assist Standard | Gemini Code Assist Enterprise |
|---|---|---|
Gemini in BigQuery features with Gemini Code Assist
The following table shows the types of generative AI assistance for BigQuery in BigQuery Studio :
| Data insights | Gemini Code Assist Standard | Gemini Code Assist Enterprise |
|---|---|---|
|
Data insights
provides an insightful library of queries generated from the metadata of your tables.
|
Gemini in Colab Enterprise
The following table shows the types of generative AI assistance for code in Colab Enterprise :
| Notebook code assist | Gemini Code Assist Standard | Gemini Code Assist Enterprise |
|---|---|---|
Gemini in databases
The following table shows the types of generative AI assistance for coding in databases:
| Generate SQL queries | Gemini Code Assist Standard | Gemini Code Assist Enterprise |
|---|---|---|
|
Write in natural language to generate SQL statements.
|
||
|
Get contextual code that works with your schema.
|
||
|
Optimize and explain existing queries.
|
Gemini in Firebase
The following table shows the types of generative AI assistance for application development provided by Gemini in Firebase :
Set up Gemini Code Assist
For detailed setup steps, see:
Interact with Gemini Code Assist in your IDE
After you set up Gemini Code Assist for individuals , or Gemini Code Assist Standard or Enterprise and install the Gemini Code Assist extension in your IDE ( VS Code or supported JetBrains IDE ), you can ask for assistance in the following ways:
-
Receive code completions or generate code directly in the code editor.
-
Click spark Geminiin the IDE to display the conversational assistant. You can ask questions or select code in your editor and enter prompts such as the following:
-
Write unit tests for my code. -
Help me debug my code. -
Make my code more readable.
-
For more information, see Code with Gemini Code Assist .
What's next
- Learn how to Code with Gemini Code Assist in your IDE .
- Learn how Gemini Code Assist Standard and Enterprise use your data .
- Learn about Gemini Code Assist pricing .
