ainotis Join
My notis

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)
Google Cloud · 2026-11-19

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.