Stay organized with collections Save and categorize content based on your preferences.
AI Applications offers multiple model versions for you to choose when generating answers. You can choose the model versions when using search summaries and answers and follow-ups.
Available models
AI Applications uses two types of models for question and answering use cases:
Vertex AI LLM models that have been tested on question and answering tasks
AI Applications models that are based on Vertex AI LLM models and further trained to address question and answering tasks
AI Applications models share the same discontinuation date as their base Vertex AI LLM models. The base LLM model is available for six months after the release date of the next version of the model, per the Vertex AI model lifecycle policy. Leave enough time to migrate to new models before the discontinuation dates.
The following table lists model version specifications. When you set a model specification, the API uses the specified model to generate answers.
Industry vertical
Custom
Healthcare
Model version
Description
Context window
Discontinuation date
Description
Context window
Discontinuation date
stable
The default model choice if the model version is not set.
The stable model specification points to gemini-2.0-flash-001/answer_gen/v1.
The model designated as stable changes periodically as new models and versions become available.
128K
N/A
The default model choice if the model version is not set.
The stable model specification points to gemini-2.0-flash-001/answer_gen/v1.
The model designated as stable changes periodically as new models and versions become available.
128K
N/A
gemini-2.5-flash/answer_gen/v1
An AI Applications model based on the gemini-2.5-flash model with additional tuning to address question and answering tasks.
The model is frozen after release.
128K
June 17, 2026
An AI Applications model based on the gemini-2.5-flash model with additional tuning to address question and answering tasks.
The model is frozen after release.
128K
June 17, 2026
gemini-2.0-flash-001/answer_gen/v1
An AI Applications model based on the gemini-2.0-flash-001 model with additional tuning to address question and answering tasks.
The model is frozen after release.
128K
Feb 5, 2026
An AI Applications model based on the gemini-2.0-flash-001 model with additional tuning to address question and answering tasks.
The model is frozen after release.
128K
Feb 5, 2026
gemini-1.5-flash-002/answer_gen/v1
An AI Applications model based on the gemini-1.5-flash-002 model with additional tuning to address question and answering tasks.
The model is frozen after release.
128K
Sept 24, 2025
Not Available
gemini-1.5-flash-001/answer_gen/v2
An AI Applications model based on the gemini-1.5-flash-001 model with additional tuning (version 2) on blended structured and unstructured data to address question and answering tasks.
The model is frozen after release.
128K
May 24, 2025
An AI Applications model based on the gemini-1.5-flash-001 model with additional tuning (version 2) on blended structured and unstructured data to address question and answering tasks.
The model is frozen after release.
128K
May 24, 2025
gemini-1.5-flash-001/answer_gen/v1
An AI Applications model based on the gemini-1.5-flash-001 model with additional tuning to address question and answering tasks.
The model is frozen after release.
128K
May 24, 2025
An AI Applications model based on the gemini-1.5-flash-001 model with additional tuning to address question and answering tasks.
The model is frozen after release.
128K
May 24, 2025
preview
The preview model specification points to the latest gemini-1.5-pro-002 model. The preview model is subject to change without notification. If you use preview as the model, you might see changes in the responses when the model changes. If you want consistency in the responses, select a specific model.
128K
N/A
The preview model specification points to the latest gemini-1.5-pro-002 model. The preview model is subject to change without notification. If you use preview as the model, you might see changes in the responses when the model changes. If you want consistency in the responses, select a specific model.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-06-26 UTC."],[[["Vertex AI Search offers a selection of model versions for generating answers, accessible when using search summaries and answers with follow-ups."],["There are two main types of models used by Vertex AI Search for question-and-answer tasks: Vertex AI LLM models and Vertex AI Search models, the latter being further trained based on LLMs."],["The `stable` model designation in Vertex AI Search automatically updates to the most current model version available, whereas other model versions remain frozen after their release."],["Vertex AI Search models share the same discontinuation date as their base Vertex AI LLM models, with the base LLM models being supported for six months after the release of the subsequent version."],["The `preview` model specfication uses the latest `gemini-1.5-pro-002` model, and is subject to change without notification."]]],[]]
