gemini-2.5-flash

Google (Gemini API) retires gemini-2.5-flash on 1 December 2026 (in 15 days). Replacement: gemini-3.5-flash-lite.

ProviderGoogle (Gemini API)
Statusretiring
Shutdown date
Deprecated on
Replacementgemini-3.5-flash-lite
Sourcehttps://ai.google.dev/gemini-api/docs/deprecations
Noterel 2025-06-17; deprecated 2026-11-02 (release notes); no longer selectable in AI Studio, API limited to existing users. Google lists 2026-12-01 as the shutdown date: from then every API request to gemini-2.5-flash routes to gemini-3.5-flash-lite, billed at Gemini 3.5 Flash-Lite rates (its migration guide lists breaking API changes). (Retired on Vertex AI 2026-10-20)

Before 1 December 2026: move off it safely

  1. Find every call to it in your code (Python, JS/TS, Go, Java, configs, notebooks), with nothing to install:
    uvx llmshift scan
  2. Turn your real traffic into tests, so you compare on what your users send:
    llmshift snapshot logs/ --model "gemini-2.5-flash"
  3. See exactly what changes on the replacement: formats, facts, tone, tool calls and settings it rejects:
    llmshift compare --to gemini-3.5-flash-lite
  4. Swap the model in your code and open a pull request with the results:
    llmshift upgrade --from "gemini-2.5-flash" --apply --compare --pr

Then llmshift init --github keeps the check on every pull request. LLMShift is free and open source (MIT) and runs on your machine.

Other Google (Gemini API) retirements

Wrong date or replacement? Tell us on GitHub, with a link to the provider's page.

Lifecycle data updated 2026-11-14, collected from the providers' official deprecation pages. Dates can move: check the source before you plan around one. Visits are counted with GoatCounter, which sets no cookies.