Wirestack
Gemini 2.5 Pro and 2.5 Flash deprecated: calls route to 3.8 Flash and 3.5 Flash-Lite from December 1, 2026
From Dec 1, 2026 gemini-2.5-pro calls go to gemini-3.8-flash and gemini-2.5-flash to gemini-3.5-flash-lite. Switch and test first.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- Google Gemini API API keyGEMINI_API_KEYGet key
Click Create API key
What you get
On November 2, 2026 Google deprecated gemini-2.5-pro and gemini-2.5-flash. Both are no longer selectable in Google AI Studio, and API access is limited to people who used them recently.
From December 1, 2026 API requests are routed automatically:
gemini-2.5-progoes togemini-3.8-flash, billed at Gemini 3.8 Flash ratesgemini-2.5-flashgoes togemini-3.5-flash-lite, billed at Gemini 3.5 Flash-Lite rates
gemini-2.5-flash-lite is not deprecated and stays available until further notice.
Prerequisites
Steps
- Search your code and settings for
gemini-2.5-proandgemini-2.5-flash(notgemini-2.5-flash-lite). - Before December 1, 2026, change the model string to
gemini-3.8-flash(from 2.5 Pro) orgemini-3.5-flash-lite(from 2.5 Flash). - Read Google's migration guide. The changelog lists breaking changes: function calling and
thought_signaturevalidation,thinking_levelreplacesthinking_budget, sampling parameters are removed, and prefilled model turns are removed. - Check your costs at the new model's rates, since routed calls are billed that way.
Test it
Send one request with the new model string and the same prompt you use today. It should return a normal answer with no error about thinking_budget or sampling settings.
Not confirmed
- Google's deprecations page says shutdown dates are the earliest possible ones and exact dates are announced in advance; the changelog states December 1, 2026 for the routing.