Vertex AI in express mode overview Stay organized with collections Save and categorize content based on your preferences.
Preview
This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of theService Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see thelaunch stage descriptions.
With Vertex AI in express mode, you can quickly sign up and beginbuilding generative AI applications on Google Cloud. Thissimplified setup experience streamlines access to Google Cloud APIs bysimplifying organization, billing, and project management.
To learn more about Vertex AI in express mode, seeGoogle Cloud express mode FAQs.
Sign up for express mode
Vertex AI is available in express mode for developers with a@gmail.comGoogle Account, regardless of whether they arenew or existing Google Cloud users:
New users: New users to Google Cloud can sign up for an expressmode account in a free tier to try Vertex AI for free for up to 90days, within the specified quotas. You don't need to provide billinginformation to sign up in the free tier. You can upgrade to a paid tier byadding a billing account.
Vertex AI in express mode is separate from, and not availablethrough, theGoogle Cloud Free Program.If you are in theGoogle Cloud Free Program, see theother quickstarts in theGet Started section to start usingGenerative AI on Vertex AI.
Existing users: If you're an existing Google Cloud user, you canalso use Vertex AI directly in express mode. In this case, you signup for the paid tier and can use your existing billing account. With expressmode, you can still use any existing credits on your account.
To sign up for Vertex AI in express mode, accessExpress Mode fromthe Google Cloud console:
After you're set up, you can start using Vertex AI in express mode byfollowing one of the tutorials:
Learn about Vertex AI in express mode
When you sign up for express mode, Google Cloud enables APIs on yourbehalf. This process happens in the background, so you can start usingVertex AI without needing to manually configure resources.
When you sign up for express mode, you get access to the following:
- Core Vertex AI Studio features. Quickly test and customize promptsfor different generative AI models, and get the corresponding code to use inyour application.
- An API key. Authenticate fast from your application.
- Free tier for new Google Cloud users during 90 days. During the 90day limit of the free tier for new Google Cloud users, you can use theVertex AI APIs that support express modefor free, up to theirquotas. You don't have to provide billinginformation. You can increase your quota limits at any time byenabling billing.
If you are an existing Google Cloud user or after enabling billing, the 90day free tier is removed. You transition to a paid tier to access extended quotalimits and additional Google Cloud features. As your quotas are increased,you only pay for what you use. At any time, you can choose toend express mode and start using all the Google Cloudservices and capabilities.
The following table lists the differences between the express mode experiencesand the full Vertex AI experience:
| Item | Vertex AI express mode in the free tier | Vertex AI express mode in the paid tier | Full Vertex AI |
|---|---|---|---|
| Time limit | 90 days | Unlimited | Unlimited |
| Available services | Basic Generative AI on Vertex AI services. | Expanded Vertex AI services and select Google Cloud services. | All Google Cloud services, including Vertex AI. |
| Data sources | Google Drive |
| All data sources available in Google Cloud. |
| Quota | Free tier limits. SeeAvailable models and rate limits in express mode. | Standard pay-as-you-go limits. SeeRate limits. | Standard pay-as-you-go limits. SeeRate limits. |
| Service level agreement (SLA) | None | Vertex AI SLA | Vertex AI SLA |
| Standard format of API endpoints | Specify API key instead of project ID and location. For example:https://aiplatform.googleapis.com/v1/publishers/google/models/{model}:streamGenerateContent?key={API_KEY} | Specify API key instead of project ID and location. For example:https://aiplatform.googleapis.com/v1/publishers/google/models/{model}:streamGenerateContent?key={API_KEY} | Specify project ID and location. For example:https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/google/models/{model}:streamGenerateContent |
Available models and rate limits in express mode
You can try out several models in express mode, including the latestGemini Flash models. The following table lists the models that areavailable in express mode, along with their rate limits:
| Model category | Available models | Requests per minute | Discontinuation date |
|---|---|---|---|
| Gemini | gemini-2.5-flash-image | 10 | |
gemini-2.5-flash-preview-09-2025 | 10 | ||
gemini-2.5-flash-lite-preview-09-2025 | 10 | ||
gemini-2.5-flash-lite | 10 | July 22, 2026 | |
gemini-2.5-pro | 10 | June 17, 2026 | |
gemini-2.5-flash | 10 | June 17, 2026 | |
gemini-2.5-flash-image-preview | 10 | October 31, 2025 | |
gemini-2.0-flash-001 | 10 | February 5, 2026 | |
gemini-2.0-flash-lite-001 | 10 | February 25, 2026 |
For Gemini 2.0 models, theMultimodal LiveAPI isn't available in theGoogle Cloud console in express mode. To use the Multimodal Live API in expressmode, use the Vertex AI API or the Google Gen AI SDK.
Vertex AI in express mode workflow
You can start sending requests from your application to Vertex AI APIsin three steps:
Aftersigning up for express mode, useVertex AI Studio to quickly try Vertex AI features:
For example, selectVertex AI Studio > Create prompt to create andoptimize multimodal prompts using a variety of Gemini models.
Get the code for what you implemented with the UI.
On the prompt page, clickBuild with code > Get code. A panel opensshowing code that programmatically sends the same requests that youimplemented in the UI. You can get the code for a programming language orcurl. You can useGoogle Colab to trythe Python code.
Use your API key to authenticate with the Vertex AI API.
In Google Cloud console in express mode, openAPIs & Services > Credentials:
Then, copy your Generative Language API Key into your code where it says
"YOUR_API_KEY". For example:Python
The Google Gen AI SDK for Python is available on PyPI and GitHub:
To learn more, see thePython SDK reference (opens in a new tab).
fromgoogleimportgenai# TODO(developer): Update below lineAPI_KEY="YOUR_API_KEY"client=genai.Client(vertexai=True,api_key=API_KEY)response=client.models.generate_content(model="gemini-2.5-flash",contents="Explain bubble sort to me.",)print(response.text)# Example response:# Bubble Sort is a simple sorting algorithm that repeatedly steps through the list
What's different in express mode
Vertex AI in express mode provides a subset of the features forGenerative AI on Vertex AI. Therefore, some of the Vertex AIdocumentation is not relevant if you signed up in express mode. For details onthe available API endpoints in express mode, see theVertex AI in express mode REST API reference.
In addition, customers in Google Cloud typically useorganizations andprojects to work with resources (for example, to call anAPI endpoint). When using Vertex AI in express mode, you don't need toworry about organizations or projects. However, you might see them mentioned insome of the Google Cloud documentation that you reference while you'reusing Vertex AI in express mode. You can still use the documentation,but ignore concepts and instructions that refer to organizations and projects.In addition, thelocation you selectedwhen signing up in express mode is used throughout your experience.
When calling REST API endpoints in express mode, you'lluse the endpoint format for express mode and specify your API key. For example:
| Standard endpoint URL | https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/google/models/{model}:streamGenerateContent |
| Endpoint URL in express mode | https://aiplatform.googleapis.com/v1/publishers/google/models/{model}:streamGenerateContent?key={API_KEY} |
View and manage API keys
To authenticate withVertex AI API endpoints that support express mode, use the API key that was created for youduring sign-up or any key that you've created in express mode. An API key is anencrypted string that is auto-generated for you when you sign up in expressmode. These API keys can be viewed and managed on theAPIs & Services page.
To learn more about the best practices for managing API keys, seeBest practices for managing API keys.
To view and manage your API keys, do the following:
In the Google Cloud console, go to theCredentials page:
In theAPI Keys section, you can manage your API keys.
View quotas
Your free use of Vertex AI in express mode is restricted by quotas.These quotas restrict the rate at which you can use Vertex AI inexpress mode at no cost. A quota limits how much of a Google Cloud resource youcan use.
To view your current usage and quotas, do the following:
Go to the Vertex AI Studio Overview page in express mode.
In Google Cloud console in express mode, openQuotas & System Limits:
Explore your service quotas.
Enable and manage billing
You can increase your quotas and remove the 90 day limit by enabling billing.
After enabling billing, you pay only for what you use. You can also save yourprompts and access additional settings in the Google Cloud console that are thatgrayed out when billing isn't enabled.
To manage billing, do the following:
Go to the Vertex AI Studio Overview page in express mode.
In Google Cloud console in express mode, openBilling:
Manage your billing accounts.
Start using all Google Cloud capabilities and services
Express mode is designed to help you get started quickly. When you're ready touse other Google Cloud services or need more control over yourenvironment, you can transition your express mode account to a standardGoogle Cloud account. This process is sometimes calledupgrade.
You can start using all the capabilities and services available inGoogle Cloud in your project by upgrading your express mode account.
To upgrade from express mode, do the following:
Go to the Vertex AI Studio Overview page in express mode.
In Google Cloud console in express mode, openBilling:
In theAccess all Google Cloud section, clickLearn more and get started.
After you upgrade from express mode, specify your project ID and locationinstead of your API key when you call the REST API endpoints. For example:
https://{location}-aiplatform.googleapis.com/v1/projects/{projectid}/locations/{location}/publishers/google/models/{model}:streamGenerateContentWhat's next
- Try theVertex AI Studio tutorial for Vertex AI inexpress mode.
- Try theAPI tutorial for Vertex AI in express mode.
- See the completeAPI reference for Vertex AI in express mode.
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-02-19 UTC.