diff --git a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
index f1fe2496f3d..a61ac7ab0f9 100644
--- a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
+++ b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
@@ -862,10 +862,12 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         # Covers gemini-3-flash, gemini-3-flash-preview, gemini-3.1-flash, gemini-3.1-flash-lite-preview,
         # gemini-3.5-flash, and any future 3.x-flash variants.
         is_gemini3flash: Final = model and ("flash" in model.lower() and "gemini-3" in model.lower())
-        is_gemini37flash: Final = model and "gemini-3.7-flash" in model.lower()
+        requires_low_minimum_thinking: Final = model and (
+            "gemini-3.7-flash" in model.lower() or "gemini-3.8-flash" in model.lower()
+        )
         is_gemini31pro: Final = model and ("gemini-3.1-pro-preview" in model.lower())
         if reasoning_effort == "minimal":
-            if is_gemini3flash and not is_gemini37flash:
+            if is_gemini3flash and not requires_low_minimum_thinking:
                 return {"thinkingLevel": "minimal", "includeThoughts": True}
             else:
                 return {"thinkingLevel": "low", "includeThoughts": True}
@@ -880,13 +882,13 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             return {"thinkingLevel": "high", "includeThoughts": True}
         elif reasoning_effort == "disable":
             # Gemini 3 cannot fully disable thinking, so we use "minimal" for gemini-3-flash-preview, "low" for others
-            if is_gemini3flash and not is_gemini37flash:
+            if is_gemini3flash and not requires_low_minimum_thinking:
                 return {"thinkingLevel": "minimal", "includeThoughts": False}
             else:
                 return {"thinkingLevel": "low", "includeThoughts": False}
         elif reasoning_effort == "none":
             # For gemini-3-flash-preview, use "minimal" instead of "low"
-            if is_gemini3flash and not is_gemini37flash:
+            if is_gemini3flash and not requires_low_minimum_thinking:
                 return {"thinkingLevel": "minimal", "includeThoughts": False}
             else:
                 return {"thinkingLevel": "low", "includeThoughts": False}
diff --git a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py
index de198754103..29b67df07e2 100644
--- a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py
+++ b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py
@@ -2666,16 +2666,18 @@ def test_reasoning_effort_maps_to_thinking_level_gemini_3():
     assert result["thinkingConfig"]["includeThoughts"] is False
 
 
+@pytest.mark.parametrize("model", ["vertex_ai/gemini-3.7-flash", "vertex_ai/gemini-3.8-flash"])
 @pytest.mark.parametrize("reasoning_effort", ["minimal", "disable", "none"])
-def test_gemini_37_flash_uses_low_minimum_thinking_level(reasoning_effort: str):
+def test_gemini_flash_uses_low_minimum_thinking_level(model: str, reasoning_effort: str):
     result = VertexGeminiConfig().map_openai_params(
         non_default_params={"reasoning_effort": reasoning_effort},
         optional_params={},
-        model="vertex_ai/gemini-3.7-flash",
+        model=model,
         drop_params=False,
     )
 
     assert result["thinkingConfig"]["thinkingLevel"] == "low"
+    assert result["thinkingConfig"]["includeThoughts"] is (reasoning_effort == "minimal")
 
 
 def test_reasoning_effort_dict_format_gemini_3():