Model versions and lifecycle

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:
  • Factuality and reduce model hallucinations.
  • Openbook Q&A for RAG use cases.
  • Instruction following.
  • Multilingual understanding in 102 languages, especially in Korean, French, German, Spanish, Japanese, Russian, and Chinese.
  • SQL generation.
  • Audio understanding.
  • Document understanding.
  • Long context.
  • Math and reasoning.

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:

All questions should be answered comprehensively with details, unless the user requests a concise response specifically. Respond in the same language as the query.

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:
  • Factuality and reduce model hallucinations.
  • Openbook Q&A for RAG use cases.
  • Instruction following.
  • Multilingual understanding in 102 languages, especially in Korean, French, German, Spanish, Japanese, Russian, and Chinese.
  • SQL generation.
  • Audio understanding.
  • Document understanding.
  • Long context.
  • Math and reasoning.

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:

All questions should be answered comprehensively with details, unless the user requests a concise response specifically. Respond in the same language as the query.

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-002
gemini-1.0-pro-vision gemini-1.0-pro-vision-001
gemini-1.5-pro gemini-1.5-pro-002
gemini-1.0-pro gemini-1.0-pro-002

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 December 12, 2024
textembedding-gecko@001
(regressed, but still supported)
June 7, 2023 November 2, 2024
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.