In its November 2 Gemini API changelog, Google deprecated gemini-2.5-pro and gemini-2.5-flash and removed both from the Google AI Studio model picker. From December 1, 2026, requests to gemini-2.5-pro will automatically route to gemini-3.8-flash and requests to gemini-2.5-flash to gemini-3.5-flash-lite, billed at the new models' rates. Google flags breaking API changes: stricter function calling and thought_signature validation, thinking_level replacing thinking_budget, and removal of sampling parameters such as temperature and of prefilled model turns. The model string stays valid but behavior can change, so developers should switch model strings and rerun tests before December 1.
Key Takeaways
- ✓Deadline: from December 1, 2026, gemini-2.5-pro routes to gemini-3.8-flash and gemini-2.5-flash routes to gemini-3.5-flash-lite; API access to 2.5 Pro is already limited to existing users who actively used it.
- ✓Price change (official price list, per 1M tokens): 2.5 Pro is $1.25 input / $10.00 output for prompts up to 200k; 3.8 Flash is an introductory $0.75 / $3.75 through 2026, rising to $1.50 / $7.50 on January 1, 2027.
- ✓2.5 Flash and 3.5 Flash-Lite both cost $0.30 input / $2.50 output for text, while audio input drops from $1.00 to $0.30.
- ✓The migration guide says to replace thinking_budget with thinking_level (3.8 Flash has no minimal level), drop temperature/top_p/top_k, candidate_count and prefilled model turns, and include call_id and name in every FunctionResponse.
- ✓It follows the October deprecation of 3.7 Flash, another case of an old model string silently routing to a newer model; 2.5 Pro users will actually land on a Flash-tier model.
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background and Industry Pain Points
Many production apps still hard-code gemini-2.5-pro or gemini-2.5-flash. In its official Gemini API changelog on November 2, Google deprecated both models and removed them from the Google AI Studio picker. Instead of shutting them off, it will route requests that use the old model names to newer models from December 1. Calls will not suddenly fail, but the same model string will be backed by a different model, a different price and possibly different behavior. Developers on X, including Kerem (@mkeremturhan), have flagged this.
Architecture and Mechanism
The official routing rules: gemini-2.5-pro goes to gemini-3.8-flash and gemini-2.5-flash goes to gemini-3.5-flash-lite, both billed at the new models' rates. The replacements use the Gemini 3 API, whose breaking changes include function calling and thought_signature validation, thinking_level replacing thinking_budget, and removal of sampling parameters and prefilled model turns.
Benchmarks and Measured Results
This is a deprecation notice, and Google has not published benchmarks comparing the 2.5 models with their replacements. From the official price list: 2.5 Pro costs $1.25 input and $10.00 output per 1M tokens; 3.8 Flash is an introductory $0.75 / $3.75 through 2026 and $1.50 / $7.50 from 2027. 2.5 Flash and 3.5 Flash-Lite share the same $0.30 / $2.50 text pricing.
Developer Guide
Switch model strings to gemini-3.8-flash or gemini-3.5-flash-lite before December 1 and follow the migration guide: replace thinking_budget with thinking_level (low, medium or high), remove temperature, top_p, top_k and candidate_count, move multi-turn chats to server-side previous_interaction_id, and include call_id and name in each FunctionResponse. Regression-test multi-turn tool calls and output quality before shipping.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.