This quickstart shows you how to get started with the Gemini API using the SDK of your choice.
View on Google AI | Run in Google Colab | View notebook on GitHub |
Prerequisites
To complete this quickstart locally, ensure that your development environment meets the following requirements:
- Python 3.9+
- An installation of
jupyter
to run the notebook.
Install the Gemini API SDK
The Python SDK for the Gemini API is contained in the
google-generativeai
package. Install the dependency using pip:
pip install -q -U google-generativeai
Authenticate
Set up your API key
To use the Gemini API, you'll need an API key. If you don't already have one, create a key in Google AI Studio.
Then, configure your key.
It is strongly recommended that you do not check an API key into your version control system but assign it as an environment variable instead:
export API_KEY=<YOUR_API_KEY>
Initialize the model
Before you can make any API calls, you need to import and initialize the model. Gemini 1.5 models are versatile and work with both text-only and multimodal prompts.
import google.generativeai as genai
import os
genai.configure(api_key=os.environ["API_KEY"])
model = genai.GenerativeModel('gemini-1.5-flash')
Make your first request
Generate text
response = model.generate_content("Write a story about an AI and magic")
print(response.text)
What's next
Now that you're set up to make requests to the Gemini API, you can use the full range of Gemini API capabilities to build your apps and workflows. To get started with Gemini API capabilities, see the following guides:
- Text generation
- Vision
- Audio
- Long context
- Code execution
- JSON mode
- Model tuning
- Function calling
- System instructions
- Embeddings
- Safety settings
- Context caching
If you're new to working with generative AI or the Gemini API, check out the following guides, which will help you understand the Gemini API programming model:
For in-depth documentation of Gemini API methods and request parameters, see the guides in the API reference.