Gemini 2.5 Pro and Flash deprecated: from Dec 1, calls reroute to newer models at their prices
What is it?
Google has deprecated gemini-2.5-pro and gemini-2.5-flash and removed them from the Google AI Studio model picker. Starting December 1, gemini-2.5-pro calls will route to gemini-3.8-flash, gemini-2.5-flash calls will route to gemini-3.5-flash-lite, and both will be billed at the new model's rates. API access to gemini-2.5-pro is now limited to existing users who have actually been using it.
Why does it matter?
Your requests keep succeeding even if you change nothing, but a different model answers them, so quality, latency and cost can shift without warning. Google lists the breaking changes: function calling and thought_signature validation, thinking_level replacing thinking_budget, and the removal of sampling parameters and prefilled model turns. If you have prompts or eval sets tuned for 2.5, rerun them against the new models in November.
Maturity
GAWe rated it GA because the cutover date and target models are fixed in the official docs, and the receiving models are already generally available.
How to track it
- Migration guide: see whether the 'what's new' migration pages add more breaking changes.
- Schedule: check the deprecations page in case the Dec 1 date or the target models change.
- Vertex AI: watch for word on whether Google Cloud Vertex AI's 2.5 models follow the same schedule.