Captured photo
Gemini 3.6 Flash
30 +

About

Google's current Flash-tier model, GA July 2026 — successor to Gemini 3.5 Flash with faster throughput and the same agentic/coding focus.

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.