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.