Gemini 2.5 pro reasoning budget like with Claude?

[miscusi-p33k]

The token reasoning budget is available in their google ai portal, but I think not available through API yet?

[LeeJiaMing1192]

Actually I think it might depends on what model you are using, in fact currently Gemini 2.5 Flash does offers your control over the model thinking budget but for other Gemini breeds I haven't try it yet !. Currently I had tried and setup like this and it worked !

from google import genai
from google.genai import types

client = genai.Client(api_key="")

model_name = "gemini-2.5-flash"

prompt_text = ""
response = client.models.generate_content(
model=model_name,
contents=prompt_text,
config=types.GenerateContentConfig(
thinking_config=types.ThinkingConfig(
thinking_budget=1024 # ###
)
)
)

print(response.text)