Questions about Gemini 2.5 Flash Pricing and Thinking Budget in Vertex AI

Gemini API
,
1

Hi everyone,

I’m currently working with Gemini 2.5 Flash on Vertex AI, and I’ve noticed something puzzling regarding pricing and budget control. I would really appreciate it if someone could help clarify the following two points:

1. Reasoning vs No Reasoning Pricing

I noticed a big price difference between “no reasoning” and “reasoning” modes.

  • Does this mean the model charges separately for internal thinking and output?
  • Can I use thinking_budget to control the cost of reasoning?

2. Thinking Budget on Vertex AI

  • Is the thinking_budget option available when calling Gemini 2.5 Flash via Vertex AI ?
  • If yes, I’d really appreciate an example of how to use it with Vertex AI.

Appreciate any help or examples. Thanks!

Best,
Liu

1 Like
3

Hi @Hao_Liu,

Welcome to forum, thank you for filing the question. I hope now you have toggle for thinking in ai studio and as well in vertex ai.

Thank you.