Migrate from Gemini 1.5 to Gemini 2.0 with the Gemini API in Vertex AI
Stay organized with collections Save and categorize content based on your preferences.

This guide shows how to migrate from Gemini 1.0 and Gemini 1.5 models (both Flash and Pro) to Gemini 2.0 models.

Differences between Gemini 1.5 and Gemini 2.0

The following are some differences between Gemini 2.0 and our 1.0 and 1.5 models:

Only Gemini 1.5 and 2.0 are supported in the Google Gen AI SDK. Gemini 1.0 is not supported. This is important because your response structure varies based on what SDK you're using.
Gemini 2.0 supports Multimodal Live API and multimodal generation.
Their safety categories are different. To learn about the differences, visit Key differences between Gemini and other model families.

Setup and migration

Gen AI SDK

We recommend that you migrate to the Gen AI SDK when upgrading to Gemini 2.0.

If you choose to use the Gen AI SDK, the setup process is different from the Vertex AI SDK.

For more information, visit Google Gen AI SDK.

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=us-central1
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.0-flash-001",
    contents="How does AI work?",
)
print(response.text)
# Example response:
# Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
#
# Here's a simplified overview:
# ...

Replace GOOGLE_CLOUD_PROJECT with your Google Cloud project ID, and replace GOOGLE_CLOUD_LOCATION with the location of your Google Cloud project (for example, us-central1).

Vertex AI SDK

If you reuse the Vertex AI SDK, the setup process is the same for the 1.0, 1.5, and 2.0 models. For more information, see Introduction to the Vertex AI SDK for Python.

Install the SDK:

pip install --upgrade --quiet google-cloud-aiplatform

The following is a short code sample that uses the Vertex AI SDK for Python:

import vertexai
from vertexai.generative_models import GenerativeModel

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

response = model.generate_content(
    "What's a good name for a flower shop that specializes in selling bouquets of dried flowers?"
)

print(response.text)
# Example response:
# **Emphasizing the Dried Aspect:**
# * Everlasting Blooms
# * Dried & Delightful
# * The Petal Preserve
# ...

Replace PROJECT_ID with your Google Cloud project ID, and replace LOCATION with the location of your Google Cloud project (for example, us-central1). Then, change the model ID from gemini-1.5-flash-002 to gemini-2.0-flash.