Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.

Model versions and lifecycle

This document explains the lifecycle stages for Gemini and embedding models on Google Cloud Vertex AI. You can also find recommended upgrades for the models and links to migration guides.

This page covers the following topics:

Key terms: Learn the definitions of model lifecycle stages like stable, legacy, and retired.
Latest stable models: Find the most recent and recommended model versions for new and active projects.
Legacy stable models: View older, but still supported, model versions and their recommended upgrades.
Migrate to a latest stable model: Get guidance on how to update your applications to use the latest models.
Gemini auto-updated aliases: Understand how to use aliases that automatically point to the latest stable model version.
Retired models: See a list of models that are no longer available and their recommended replacements.

Key terms

The following terms describe the lifecycle stages of a model:

Stable model: A publicly released version of a model that is available and supported for production use. When a stable model version is released, it typically includes a retirement date. After the retirement date, the model is no longer accessible or supported.
- Latest stable model: The most recent version within a model family. This version is recommended for new and active projects and is the target for migrations from earlier versions. For more information, see Latest stable models.
- Legacy stable model: A model version that has been replaced by a newer, latest stable model. Although legacy stable models are still supported, you should migrate to the latest model to get the newest features and improvements. Access to legacy stable models might be restricted for new projects. For more information, see Legacy stable models.
Retired model: A model version that is past its retirement date and has been permanently deactivated. Retired models are no longer accessible or supported. API requests that reference a retired model ID typically return a 404 error. For more information, see Retired models.
Recommended upgrade: The latest stable model that you should switch to. Latest stable models offer better performance and more capabilities than legacy models. You can find the recommended upgrades in the Legacy stable models and Retired models sections.

The following table summarizes the different model lifecycle stages.

Model Type	Description	Recommendation
Latest stable model	The most recent version in a model family.	Recommended for all new and active projects. Target for migrations from older versions.
Legacy stable model	An older version that has been superseded by a latest stable model.	Still supported, but you should migrate to the latest stable model to get new features and improvements. Access might be restricted for new projects.
Retired model	A model version that is past its retirement date.	Permanently deactivated and no longer accessible. You must migrate to a recommended upgrade.

Latest stable models

The following table lists the latest stable models:

Model ID	Release date	Retirement date	Details
`gemini-2.5-pro`	June 17, 2025	June 17, 2026
`gemini-2.5-flash`	June 17, 2025	June 17, 2026
`gemini-2.5-flash-lite`	July 22, 2025	July 22, 2026
`gemini-2.0-flash-001`	February 5, 2025	February 5, 2026	Gemini 2.0: Flash, Flash-Lite and Pro - Google Developers Blog
`gemini-2.0-flash-lite-001`	February 25, 2025	February 25, 2026	Gemini 2.0: Flash, Flash-Lite and Pro - Google Developers Blog
`gemini-embedding-001`	May 20, 2025	No retirement date announced
`text-embedding-005`	November 18, 2024	No retirement date announced
`text-embedding-004`	May 14, 2024	No retirement date announced
`text-multilingual-embedding-002`	May 14, 2024	No retirement date announced
`multimodalembedding@001`	February 12, 2024	No retirement date announced

Legacy stable models

The following table lists legacy stable models:

Model ID	Release date	Retirement date	Recommended upgrade
`gemini-1.5-pro-002`^*	September 24, 2024	September 24, 2025	`gemini-2.0-flash`
`gemini-1.5-flash-002`^*	September 24, 2024	September 24, 2025	`gemini-2.0-flash-lite`

*: Restricted for new projects.

Migrate to a latest stable model

To learn how to migrate to a latest stable model, see Migrate your application to Gemini 2 with the Gemini API in Vertex AI. This guide provides migration steps to help you minimize potential risks and use new models effectively.

If you need to quickly resolve errors caused by a model reaching its retirement date, follow these steps:

Update your application to point to the recommended upgrade.
Test all mission-critical features to ensure they work as expected.
Deploy the updates.

Gemini auto-updated aliases

An auto-updated alias for a Gemini model always points to its latest stable version. When a new stable version is released, the alias automatically points to the new version.

The following table shows the auto-updated aliases for Gemini models and the stable versions they point to.

Auto-updated alias	Stable version reference
`gemini-2.0-flash-lite`	`gemini-2.0-flash-lite-001`
`gemini-2.0-flash`	`gemini-2.0-flash-001`
`gemini-1.5-pro`	`gemini-1.5-pro-002`
`gemini-1.5-flash`	`gemini-1.5-flash-002`

Retired models

The following table lists the retired models (click to expand)

Model ID	Release date	Retirement date	Recommended upgrade
`gemini-1.5-pro-001`	May 24, 2024	May 24, 2025	`gemini-2.0-flash`
`gemini-1.5-flash-001`	May 24, 2024	May 24, 2025	`gemini-2.0-flash-lite`
`textembedding-gecko@003^*`	December 12, 2023	May 24, 2025	`gemini-embedding-001`
`textembedding-gecko-multilingual@001`	November 2, 2023	May 24, 2025	`gemini-embedding-001`
`gemini-1.0-pro-001`	February 15, 2024	April 21, 2025	`gemini-2.0-flash`
`gemini-1.0-pro-002`	April 9, 2024	April 21, 2025	`gemini-2.0-flash`
`gemini-1.0-pro-vision-001`	February 15, 2024	April 21, 2025	`gemini-2.0-flash`
`text-bison`	May 2023	April 21, 2025	`gemini-2.0-flash-lite`
`chat-bison`	May 2023	April 21, 2025	`gemini-2.0-flash-lite`
`code-gecko`	May 2023	April 21, 2025	`gemini-2.0-flash-lite`
`textembedding-gecko@002`	November 2, 2023	April 21, 2025	`gemini-embedding-001`
`textembedding-gecko@001`	June 7, 2023	April 21, 2025	`gemini-embedding-001`

What's next

To learn which regions models are available, see Deployments and endpoints.
For details about individual models, see Google models and click the model that you want to learn more about.

Model versions and lifecycle Stay organized with collections Save and categorize content based on your preferences.