Google Vertex AI

Google GenAI supports a wide range of state-of-the-art generative AI models hosted on Google's advanced, global infrastructure.

Installation

opsmate install opsmate-provider-google-genai

After installation you can list all the models via

$ opsmate list-models --provider google-genai
                    Models
┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Provider     ┃ Model                        ┃
┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ google-genai │ gemini-2.5-pro-preview-03-25 │
├──────────────┼──────────────────────────────┤
│ google-genai │ gemini-2.5-pro-exp-03-25     │
├──────────────┼──────────────────────────────┤
│ google-genai │ gemini-2.0-flash-001         │
├──────────────┼──────────────────────────────┤
│ google-genai │ gemini-2.0-flash-lite        │
└──────────────┴──────────────────────────────┘

Limitations

Only Vertex AI models are supported

This provider currently does not support Gemini API, because the Gemini API does not support default value in the response schema.

As the result, currently only vertex AI models are supported, meaning you need to have a Google Cloud account in order to use this provider.

Limited region support for gemini-2.5-pro

By the time the provider is published, the gemini-2.5-pro-preview-03-25 and gemini-2.5-pro-exp-03-25 models are only available in the us-central1 region. To use it you will need to set GOOGLE_CLOUD_LOCATION as below:

export GOOGLE_CLOUD_LOCATION=us-central1

# or
export GOOGLE_CLOUD_LOCATION=global

Usage

export GOOGLE_CLOUD_PROJECT=<your-project-id>
export GOOGLE_CLOUD_LOCATION=<your-location>

opsmate chat -m gemini-2.0-flash-001

Uninstall

opsmate uninstall -y opsmate-provider-google-genai