Gemini 2.5 Pro and Flash route onward on 1 December
Google's 2 November notes deprecate gemini-2.5-pro and gemini-2.5-flash. From 1 December, requests route to newer models and bill at those rates.
Official source (opens in a new tab)
Google's Gemini API release notes for 2 November 2026 deprecate gemini-2.5-pro and gemini-2.5-flash. Both are no longer available to select in Google AI Studio. Effective 1 December 2026, API requests to gemini-2.5-pro automatically route to gemini-3.8-flash and are billed at Gemini 3.8 Flash rates. Requests to gemini-2.5-flash route to gemini-3.5-flash-lite and are billed at Gemini 3.5 Flash-Lite rates. Google says to update the model string before that date.
The note lists breaking API changes on the move: function calling and thought_signature validation, thinking_level replacing thinking_budget, and removed sampling parameters and prefilled model turns. It points Pro callers to the Gemini 3.8 Flash migration guide and Flash callers to the Gemini 3.5 Flash-Lite migration guide.
Who it's for: a developer whose code still sends gemini-2.5-pro or gemini-2.5-flash.
Fits: Best for Writing stays Claude. Gemini stays third, and the current writing note is about the chat app, not these older API ids. The Gemini start guide and the Gemini alternatives are unchanged. The verdict is unchanged.