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.