Using Google Gemini With BIGGI

BIGGI supports Google's Gemini family of models through the Google AI Gemini API.

Website: https://ai.google.dev/

Getting an API Key

  1. Go to Google AI Studio: Navigate to https://ai.google.dev/.
  2. Sign In: Sign in with your Google account.
  3. Create API Key: Click on "Create API key" in the left-hand menu.
  4. Copy API Key: Copy the generated API key.

API key requirements

Google AI Studio creates auth keys by default. BIGGI sends these keys in the x-goog-api-key header required by the Gemini API. An auth key is not an OAuth access token, so you do not need to configure OAuth.

Google began rejecting unrestricted Standard keys on June 19, 2026. If Gemini returns Request had invalid authentication credentials, open the key in Google AI Studio and check its type and status. Replace a Standard key with a new auth key. If the rejected key is already an auth key, check its Gemini API access or create a replacement before updating BIGGI.

You can temporarily keep a Standard key working by restricting it to the Gemini API (generativelanguage.googleapis.com), but Google will reject all Standard keys in September 2026. See Google's Gemini API key documentation for restriction and migration steps.

Configuration in BIGGI

Open Settings (gear icon) and go to the Providers tab to add Google Gemini and enter your API key.

The extension stores this in your biggi.json config file. You can also edit the file directly.

Tips and Notes

  • Pricing: Gemini API usage is priced based on input and output tokens. Refer to the Gemini pricing page for detailed information.
  • Codebase Indexing: The gemini-embedding-001 model is specifically supported for codebase indexing, providing high-quality embeddings for semantic code search.