Captured photo
Gemini 3.5 Flash-Lite
10 +

About

Google's fastest, cheapest current Flash tier (~350 tok/s) — GA July 2026, for high-volume low-latency text tasks.

Settings

Temperature-  The temperature of the model. Higher values make the model more creative and lower values make it more focused.
Top P-  Tokens are selected from the most to least probable until the sum of their probabilities equals this value.
Top K-  For each token selection step, the top_k tokens with the highest probabilities are sampled.
Context length-  The maximum number of tokens to use as input for a model.
Response length-  The maximum number of tokens to generate in the output.