This page gives you information about the model that's deployed to Gemini Experimental in Vertex AI Studio. Gemini Experimental lets you test out Google's experimental models. Experimental models don't follow Google's standard model lifecycle plan and versioning scheme and one model can be swapped for another without prior notice. We don't guarantee that an experimental model will become a stable model in the future.
Test Gemini Experimental models
Console
To test the Gemini Experimental model, do the following:
In the Google Cloud console, go to Vertex AI Studio.
Click Try Gemini.
In the Model drop-down, select Gemini Experimental.
In the Prompt field, enter your prompt.
Click Submit.
API
To send requests to the Gemini Experimental by using the
Vertex AI Gemini API, specify gemini-experimental as the model. For details
on how to use the Vertex AI Gemini API, see
Send multimodal prompt requests.
Current model
The following table shows you the details of the model that's deployed to Gemini Experimental:
| Specification | Details |
|---|---|
| Model ID | gemini-experimental |
| Date deployed | May 14, 2024 |
| Model family | Gemini 1.5 |
| Model characteristics/features |
|
Previous model
The following table shows you the details of the model that's previously deployed to Gemini Experimental:
| Specification | Details |
|---|---|
| Model ID | gemini-experimental |
| Date deployed | April 22, 2024 |
| Model family | Gemini 1.5 |
| Model characteristics/features |
|
Pricing
Gemini Experimental is not billed.
Data privacy and feedback
Gemini Experimental does not log your input or output data, and we need your feedback to help improve our experimental models. To provide feedback, fill out the feedback form.
Quota and limitations
Gemini Experimental has a quota of 2 queries per minute (QPM). This quota can't be increased.
Gemini Experimental doesn't let you configure advanced parameters
or the region, which is set to us-central1.