How to Install / Upgrade: Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

Google DeepMind is introducing new Gemini models: Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, and Gemini 3.5 Flash Cyber. These sit in the Gemini Flash family and expand the options available when you build or run workloads against Gemini.

To install or upgrade, open your existing Gemini integration and switch the model selection to one of the new names: Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, or Gemini 3.5 Flash Cyber. Prefer the model that matches the workload you already run on Flash-class models. Apply the change in your app config, client setup, or provider console, then redeploy or restart so every call path uses the new model. Keep the previous model setting recorded so you can roll back if needed.

Confirm that every call path resolves to the intended model name and that responses still look correct for your main prompts. Watch for mixed traffic where some services still point at an older model. If results look off, switch back to your prior model setting, recheck the name you configured against Google DeepMind’s listed models, and retest before you leave the upgrade in place.