Checked fact 552120 Nov 2026Models and releases
Google's thinking guide says that for Gemini 2.5 and earlier models, thinking is configured with the thinking_budget parameter, which sets a soft limit on the number of tokens the model can use during internal reasoning.
The exact words it rests on
For Gemini 2.5 and earlier models, configure thinking using the thinking_budget parameter. This parameter sets a soft limit on the number of tokens the model can use during internal reasoning.
What the source said when we opened it, on 19 Nov 2026.
The source
Thinking (Gemini Enterprise Agent Platform)
Checked
Checked by the notis newsroom on , against the source above.
In the story
What a thinking level sets, and how Gemini 4 Neon's four levels differ 20 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.