Using Gemini Deep Research on Google AI Studio
Implementation guide · Gemini 2.5 · Google DeepMind
Serverless
Quick Start
- 1
- 2Use the Google AI Studio SDK or REST API to call
gemini-deep-research— see the documentation for request format.
Code Examples
Install
pip install google-genaiAPI key
GOOGLE_API_KEYModel ID
gemini-deep-researchUse the model name directly, e.g. "gemini-2.0-flash", "gemini-1.5-pro", or "gemini-2.5-pro-preview-05-06".
import os
from google import genai
client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
response = client.models.generate_content(
model="gemini-deep-research",
contents="Hello"
)
print(response.text)About Google AI Studio
Google AI Studio is a model prototyping environment and API access point for Gemini models, offering an inference playground for developers to test and build AI applications.
Pricing on Google AI Studio
Capabilities
Function CallingTool UseStructured Outputs
About Gemini Deep Research
Gemini Deep Research is Google DeepMind's Gemini 2.5 model. It offers a 128K-token context window.
Model Specs
Released2024-12-11
Context128K
ArchitectureDecoder Only
Knowledge cutoff2025-01