fix(vertex_and_google_ai_studio_gemini.py): allow thinking budget = 0

Fixes https://github.com/BerriAI/litellm/issues/10121

litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py

@@ -390,7 +390,7 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         params: GeminiThinkingConfig = {}
         if thinking_enabled:
             params["includeThoughts"] = True
-        if thinking_budget:
+        if thinking_budget is not None and isinstance(thinking_budget, int):
             params["thinkingBudget"] = thinking_budget
 
         return params

tests/llm_translation/test_gemini.py

@@ -116,4 +116,22 @@ def test_gemini_thinking():
         messages=messages, # make sure call works
     )
     print(response.choices[0].message)
-    assert response.choices[0].message.content is not None
+    assert response.choices[0].message.content is not None
+
+
+def test_gemini_thinking_budget_0():
+    litellm._turn_on_debug()
+    from litellm.types.utils import Message, CallTypes
+    from litellm.utils import return_raw_request
+    import json
+
+    raw_request = return_raw_request(
+        endpoint=CallTypes.completion,
+        kwargs={
+            "model": "gemini/gemini-2.5-flash-preview-04-17",
+            "messages": [{"role": "user", "content": "Explain the concept of Occam's Razor and provide a simple, everyday example"}],
+            "thinking": {"type": "enabled", "budget_tokens": 0}
+        }
+    )
+    print(raw_request)
+    assert "0" in json.dumps(raw_request["raw_request_body"])