Checked fact 551720 Nov 2026Models and releases
Google's Neon developer guide says reasoning tokens generated at HIGH (default) and XHIGH count toward max_output_tokens, and advises setting max_output_tokens high enough for both thinking and final output, or setting thinking_level="MEDIUM" on latency-sensitive tool turns.
The exact words it rests on
Reasoning tokens generated at HIGH (default) and XHIGH count toward max_output_tokens and accumulate in multi-turn context when you preserve thought signatures across turns. Set max_output_tokens high enough for both thinking and final output, avoid overly low context-compaction thresholds in multi-turn coding harnesses, or set thinking_level="MEDIUM" on latency-sensitive tool turns.
What the source said when we opened it, on 19 Nov 2026.
The source
Developer's guide to Gemini 4 Neon (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.