In addition to the base models, the Gemini API offers experimental models available in Preview, as defined in the Terms, meaning it is not for production use. We release experimental models to gather feedback, get our latest updates into the hands of developers quickly, and highlight the pace of innovation happening at Google. What we learn from experimental launches informs how we release models more widely. An experimental 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.
Use an experimental model
The Gemini API's experimental models are available for all users. You can use the experimental models either in your code directly using the Gemini API, or you can use an experimental model in Google AI Studio:
Gemini API
To use an experimental model, specify the model code when you initialize the generative model. For example:
model = genai.GenerativeModel(model_name="gemini-exp-1121")
AI Studio
Select the model code of the experimental model you want to use in the Model drop-down menu in the Settings pane. Experimental models are labeled Preview in the drop-down menu.
Available models
| Model code | Base model | Highlights | Release date |
|---|---|---|---|
gemini-exp-1121 |
Gemini | Improved coding, reasoning, and vision capabilities | November 21, 2024 |
gemini-exp-1114 |
Gemini | Quality improvements | November 14, 2024 |
learnlm-1.5-pro-experimental |
LearnLM 1.5 Pro Experimental |
Inputs: Audio, images, videos, and text
Output: Text |
November 19, 2024 |
Provide feedback
You can provide feedback on the Gemini API's experimental models using our developer forum.