Ctrl+Z Therapy
CasesQuick answersGuides10-minute checklistHow we testCartoonSend it in

Using gemini-2.5-flash? From December 1, Google routes it to gemini-3.5-flash-lite

Ship ItChecked against the official source

Source checked 7 Nov 2026 · Published 8 Nov 2026 · Last reviewed 8 Nov 2026 · By Ctrl+Z Therapy (how we test)

The short answer

Google's Gemini deprecations page: effective December 1, 2026, API requests to gemini-2.5-flash will automatically route to gemini-3.5-flash-lite, and requests to gemini-2.5-pro will automatically route to gemini-3.8-flash, billed at the newer models' rates. gemini-2.5-flash-lite is not deprecated and remains available through the API until further notice.

What to do

  1. Find where your app sets the Gemini model, for example gemini-2.5-flash or gemini-2.5-pro.
  2. Before December 1, 2026, update your model string and review the breaking API changes in Google's migration guide.
  3. Test your prompts on the new model, since a different model answers.

Good to know

  • Both 2.5 models are no longer available to select in Google AI Studio, and API access is limited to users who have actively used them.
  • On the Agent Platform Gemini API (formerly Vertex AI), the 2.5 models were already shut down on October 20, 2026.

Source

Checked on 7 Nov 2026. Prices, limits and settings change, so check the source before you rely on them.

Related