Gemini

Learn how to use Gemini models in Agno.

Use Google’s Gemini models through Google AI Studio or Google Cloud Vertex AI - platforms that provide access to large language models and other services.

We recommend experimenting to find the best-suited model for your use case. Here are some general recommendations in the Gemini 2.x family of models:

• gemini-2.0-flash is good for most use-cases.
• gemini-2.0-flash-lite is the most cost-effective model.
• gemini-2.5-pro-exp-03-25 is the strongest multi-modal model.

Refer to the Google AI Studio documentation and the Vertex AI documentation for information on available model versions.

Authentication

You can use Gemini models through either Google AI Studio or Google Cloud’s Vertex AI:

Google AI Studio

Set the GOOGLE_API_KEY environment variable. You can get one from Google AI Studio.

Mac

export GOOGLE_API_KEY=***

Vertex AI

To use Vertex AI in Google Cloud:

1. Refer to the Vertex AI documentation to set up a project and development environment.

2. Install the gcloud CLI and authenticate (refer to the quickstart for more details):

gcloud auth application-default login

3. Enable Vertex AI API and set the project ID environment variable (alternatively, you can set project_id in the Agent config):

Export the following variables:

export GOOGLE_GENAI_USE_VERTEXAI="true"
export GOOGLE_CLOUD_PROJECT="your-gcloud-project-id"
export GOOGLE_CLOUD_LOCATION="your-gcloud-location"

Or update your Agent configuration:

agent = Agent(
    model=Gemini(
        id="gemini-1.5-flash",
        vertexai=True,
        project_id="your-gcloud-project-id",
        location="your-gcloud-location",
    ),
)

To use Vertex AI Search:

# Replace with your actual datastore ID
datastore_id = "projects/your-project-id/locations/global/collections/default_collection/dataStores/your-datastore-id"

agent = Agent(
    model=Gemini(
        id="gemini-2.5-flash",
        vertexai_search=True,
        vertexai_search_datastore=datastore_id,
        vertexai=True,  # Required for Vertex AI Search
    ),
)

Example

Use Gemini with your Agent:

agent.py

from agno.agent import Agent
from agno.models.google import Gemini

# Using Google AI Studio
agent = Agent(
    model=Gemini(id="gemini-2.0-flash"),
    markdown=True,
)

# Or using Vertex AI
agent = Agent(
    model=Gemini(
        id="gemini-2.0-flash",
        vertexai=True,
        project_id="your-project-id",  # Optional if GOOGLE_CLOUD_PROJECT is set
        location="us-central1",  # Optional
    ),
    markdown=True,
)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")

View more examples here.

Grounding and Search

Gemini models support grounding and search capabilities through optional parameters. This automatically sends tools for grounding or search to Gemini. See more details here.

To enable these features, set the corresponding parameter when initializing the Gemini model:

To use grounding:

from agno.agent import Agent
from agno.models.google import Gemini

agent = Agent(
    model=Gemini(id="gemini-2.0-flash", grounding=True),
    show_tool_calls=True,
    markdown=True,
)

agent.print_response("Any news from USA?")

To use search:

from agno.agent import Agent
from agno.models.google import Gemini

agent = Agent(
    model=Gemini(id="gemini-2.0-flash", search=True),
    show_tool_calls=True,
    markdown=True,
)

agent.print_response("What's happening in France?")

Combine URL context with Google Search to get a more in-depth analysis

Parameters

Parameter	Type	Default	Description
id	str	"gemini-2.0-flash-exp"	The specific Gemini model ID to use.
name	str	"Gemini"	The name of this Gemini model instance.
provider	str	"Google"	The provider of the model.
function_declarations	Optional[List[FunctionDeclaration]]	None	List of function declarations for the model.
generation_config	Optional[Any]	None	Configuration for text generation.
safety_settings	Optional[Any]	None	Safety settings for the model.
generative_model_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for the generative model.
grounding	bool	False	Whether to use grounding.
search	bool	False	Whether to use search.
grounding_dynamic_threshold	Optional[float]	None	The dynamic threshold for grounding.
url_context	bool	None	Whether to use URL context for grounding.
vertexai_search	bool	False	Whether to use Vertex AI Search for private knowledge base grounding.
vertexai_search_datastore	Optional[str]	None	The Vertex AI Search datastore ID for private knowledge base search.
api_key	Optional[str]	None	API key for authentication.
vertexai	bool	False	Whether to use Vertex AI instead of Google AI Studio.
project_id	Optional[str]	None	Google Cloud project ID for Vertex AI.
location	Optional[str]	None	Google Cloud region for Vertex AI.
client_params	Optional[Dict[str, Any]]	None	Additional parameters for the client.
client	Optional[GeminiClient]	None	The underlying generative model client.
temperature	Optional[float]	None	Controls randomness in the output. Higher values (e.g., 0.8) make the output more random, while lower values (e.g., 0.2) make it more focused and deterministic.
top_p	Optional[float]	None	Nucleus sampling parameter. Only consider tokens whose cumulative probability exceeds this value.
top_k	Optional[int]	None	Only consider the top k tokens for text generation.
max_output_tokens	Optional[int]	None	The maximum number of tokens to generate in the response.
stop_sequences	Optional[list[str]]	None	List of sequences where the model should stop generating further tokens.
logprobs	Optional[bool]	None	Whether to return log probabilities of the output tokens.
presence_penalty	Optional[float]	None	Penalizes new tokens based on whether they appear in the text so far.
frequency_penalty	Optional[float]	None	Penalizes new tokens based on their frequency in the text so far.
seed	Optional[int]	None	Random seed for deterministic text generation.
request_params	Optional[Dict[str, Any]]	None	Additional parameters for the request.

Gemini is a subclass of the Model class and has access to the same params.