Skip to main content

Google Generative AI

Overview​

Google Generative AI provides access to Google's powerful Gemini family of models through the Google AI Studio API. These models offer advanced language understanding, multi-modal capabilities, and high-quality text generation.

Configuration​

To use Google Generative AI, configure it in the Config Manager under the AI Gateway section:

ai:
  providers:
    google:
      apiKey: your-google-api-key
      baseURL: https://ai-gateway.example.com/google # Optional, to point at a gateway
      headers: # Optional, e.g. for authentication with gateway
        - key: X-Custom-Header
          value: custom-value

Then set the default language model (or configure it per-plugin):

ai:
  models:
    languageModel: google|gemini-2.5-flash  # or any supported model below

Supported Models​

Language Models:

  • gemini-2.5-pro
  • gemini-2.5-flash (recommended)
  • gemini-2.5-flash-lite
  • gemini-2.0-flash
  • gemini-1.5-pro
  • gemini-1.5-flash
  • gemini-1.5-flash-8b
  • gemma-3-27b-it

Embedding Models:

  • gemini-embedding-001
  • text-embedding-004

A full list of available models can be found in the Google Generative AI documentation.

Getting an API Key​

To obtain a Google Generative AI API key:

  1. Visit Google AI Studio
  2. Sign in with your Google account
  3. Click on "Get API Key" in the left sidebar
  4. Create a new API key or use an existing one
  5. Copy the API key and add it to your configuration

Notes​

  • Google Generative AI does not currently support re-ranking models