Each Generative AI on Vertex AI language model is initially available in a preview version and then in a stable version. Each stable version has an auto-updated alias. This page explains how model versioning works with all Google models.
To learn about Imagen on Vertex AI model versions and their lifecycle, see Imagen on Vertex AI model versions and lifecycle.
If you tune a Gemini model, then the tuned model shares the same discontinuation date as the base model that you used in the tuning process. For more information, see Overview of model tuning for Gemini.
Gemini stable version
A stable version of a Gemini model does not change and
continues to be available until its discontinuation date.
Don't use a stable version after its discontinuation date; switch to a
newer, available stable version. You can identify the version of a
stable model by the three-digit number that's appended to the model name. For
example, gemini-1.5-pro-001
is version number one of the stable
release of the Gemini 1.5 Pro model.
Google releases stable versions at a regular cadence. You can switch from one stable version to another as long as the other version is still available. When you do this, run your tuning jobs again because there might be prompt, output, and other differences between the versions.
To use the stable version of a Gemini model, append the
three-digit version number to the model with a hyphen (-
). For example, to
specify version one of the stable gemini-1.5-pro
model, append
-001
to the model's name:
https://us-central1-aiplatform.googleapis.com/v1/projects/my_project/locations/us-central1/publishers/google/models/gemini-1.5-pro-001
Available stable Gemini model versions
The following stable model versions are available for generally available Gemini models:
Gemini 1.5 Flash model | Release date | Discontinuation date | Model version highlights |
---|---|---|---|
gemini-1.5-flash-002 | September 24, 2024 | September 24, 2025 | Improved general model quality with significant gains in the following
categories:
Gemini 1.5 Flash 002 uses dynamic shared quota. Sometimes gemini-1.5-flash-002 can respond in your local language, even if the prompt is written in another language. This issue only applies to non-English prompts. To mitigate this issue, we recommend you add the following to your system instructions to ensure the model responds in the same language as the prompt:
|
gemini-1.5-flash-001 | May 24, 2024 | May 24, 2025 | Initial version of Gemini 1.5 Flash. |
Gemini 1.5 Pro model | Release date | Discontinuation date | Model version highlights |
---|---|---|---|
gemini-1.5-pro-002 | September 24, 2024 | September 24, 2025 | Improved general model quality with significant gains in the following
categories:
Gemini 1.5 Pro 002 uses dynamic shared quota. Sometimes gemini-1.5-pro-002 can respond in your local language, even if the prompt is written in another language. This issue only applies to non-English prompts. To mitigate this issue, we recommend you add the following to your system instructions to ensure the model responds in the same language as the prompt:
|
gemini-1.5-pro-001 | May 24, 2024 | May 24, 2025 | Initial version of Gemini 1.5 Pro. |
Gemini 1.0 Pro Vision model | Release date | Discontinuation date |
---|---|---|
gemini-1.0-pro-vision-001 | February 15, 2024 | February 15, 2025 |
Gemini 1.0 Pro model | Release date | Discontinuation date |
---|---|---|
gemini-1.0-pro-001 | February 15, 2024 | February 15, 2025 |
gemini-1.0-pro-002 | April 9, 2024 | April 9, 2025 |
Gemini auto-updated alias
The auto-updated alias of a Gemini model points to the most recent stable version. When a new stable version is released, the auto-updated alias points to the new version. This means that if you specify the auto-updated alias of a Gemini model in your code, the model could behave differently without notice when the next stable version is released. Because of this, use an auto-updated alias with caution if you tune your model.
To use the auto-updated alias for a model, don't append anything to the model name.
For example, the following uses the auto-updated version of the
gemini-1.0-pro-vision
model:
https://us-central1-aiplatform.googleapis.com/v1/projects/my_project/locations/us-central1/publishers/google/models/gemini-1.0-pro-vision
Gemini auto-updated aliases
The following table shows the available auto-updated aliases for Gemini model versions and the stable version each references.
Auto-updated alias | Referenced stable version |
---|---|
gemini-1.5-flash |
gemini-1.5-flash-001 Note: To use the latest version ( 002 ), append -002 to the model
name instead of using the alias. |
gemini-1.0-pro-vision |
gemini-1.0-pro-vision-001 |
gemini-1.5-pro |
gemini-1.5-pro-001 Note: To use the latest version ( 002 ), append -002 to the model name
instead of using the alias. |
gemini-1.0-pro |
gemini-1.0-pro-002 |
gemini-pro-experimental |
See Experimental models. |
gemini-flash-experimental |
See Experimental models. |
Code completion stable model versions
The following stable model versions are available for generally available Generative AI models:
code-gecko model | Release date | Discontinuation date |
---|---|---|
code-gecko@002 | December 6, 2023 | April 9, 2025 |
Embeddings stable model versions
The following stable model versions are available for generally available Generative AI models:
Model name | Release date | Discontinuation date |
---|---|---|
text-embedding-004 | May 14, 2024 | To be determined. |
text-multilingual-embedding-002 | May 14, 2024 | To be determined. |
textembedding-gecko@003 | December 12, 2023 | May 14, 2025 |
textembedding-gecko-multilingual@001 | November 2, 2023 | May 14, 2025 |
textembedding-gecko@002(regressed, but still supported) | November 2, 2023 | April 9, 2025 |
textembedding-gecko@001(regressed, but still supported) | June 7, 2023 | April 9, 2025 |
multimodalembedding@001 | February 12, 2024 | To be determined. |
Legacy models
For information about the discontinuation dates of legacy models like PaLM 2, see Legacy model information.