Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

Automaticlly set reasoning budget to 0 for 2.5 flash, because we do it with thinking for memory

Magnus Müller653fa4206f4d
diff --git a/browser_use/llm/google/chat.py b/browser_use/llm/google/chat.py
index 076d24348..d03b1b7d3 100644
--- a/browser_use/llm/google/chat.py
+++ b/browser_use/llm/google/chat.py
@@ -198,8 +198,8 @@ class ChatGoogle(BaseChatModel):
if self.seed is not None:
config['seed'] = self.seed
- # if self.thinking_budget is None and 'gemini-2.5' in self.model:
- self.thinking_budget = 0
+ if self.thinking_budget is None and 'gemini-2.5-flash' in self.model:
+ self.thinking_budget = 0
if self.thinking_budget is not None:
thinking_config_dict: types.ThinkingConfigDict = {'thinking_budget': self.thinking_budget}