With gemini-2.5-flash, in the python SDK, I can use this thinking config to disable thinking tokens: thinking_config=ThinkingConfig( thinking_budget=0 ) With gemini-2.5-flash-preview-09-2025 Setting that has no impact. It still includes thinking tokens in the output. For example, in the retur…

Hi @Joe1 , Thanks for sharing! I’m trying to reproduce the issue where thinking_budget=0 isn’t being respected by the gemini-2.5-flash-preview-09-2025 model. My tests with simpler prompts are showing the expected behavior, where thoughts_token_count=None confirms the budget is being respected, as sh…

[image] chunduriv: To help me debug this further, could you please share the exact prompt and any other relevant Here is an example prompt that reproduces this issue: Task: Translate this text to native fluent English. Text: Yardım bile ediyor bana küçük hanım. Generation config: c…

Gemini-2.5-flash-preview-09-2025 breaks the thinking_budget parameter

Gemini API

Joe1 October 21, 2025, 7:27pm 6

Is there any plan to fix this? It’s a clear regression.

I thought gemini-2.5-flash was supposed to be a stable version, supported for at least a year. Why are you releasing a new snapshot for that model?

Topic		Replies	Views
Thinking in flash-preview-09-2025 Gemini API gemini-flash	5	206	January 5, 2026
Latest @google/genai with 2.5 flash ignoring thinking budget Gemini API generative-ai , gemini-flash	11	763	December 2, 2025
Gemini-2.5-flash-preview-04-17 not honoring thinking_budget=0 Gemini API help_request	5	1791	April 22, 2025
Gemini 2.5 Flash Overthinking by a lot Gemini API prompt , gemini-2	6	703	September 5, 2025
Big Problem! Gemini 3.0 pro preview thought token exceeding problem Gemini API bug , api , gemini , thinking	8	842	March 29, 2026

Gemini-2.5-flash-preview-09-2025 breaks the thinking_budget parameter

Related topics