diff --git a/integrations/llms/gemini.mdx b/integrations/llms/gemini.mdx
index 3b5d6061..6b20c841 100644
--- a/integrations/llms/gemini.mdx
+++ b/integrations/llms/gemini.mdx
@@ -2135,7 +2135,7 @@ Note that you will have to set [`strict_open_ai_compliance=False`](/product/ai-g
 
 ### Using reasoning_effort Parameter
 
-You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:
+You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`. The value is passed directly to Gemini as the `thinkingLevel`:
 
 ```python
 response = portkey.chat.completions.create(
@@ -2149,8 +2149,10 @@ response = portkey.chat.completions.create(
 | reasoning_effort | Gemini thinkingLevel |
 |------------------|---------------------|
 | `none` | Disabled |
-| `minimal`, `low` | `low` |
-| `medium`, `high` | `high` |
+| `minimal` | `minimal` |
+| `low` | `low` |
+| `medium` | `medium` |
+| `high` | `high` |
 
 <Info>
 Gemini grounding mode may not work via Portkey SDK. Contact support@portkey.ai for assistance.
diff --git a/integrations/llms/vertex-ai.mdx b/integrations/llms/vertex-ai.mdx
index 5f3f2a23..e95a1ac8 100644
--- a/integrations/llms/vertex-ai.mdx
+++ b/integrations/llms/vertex-ai.mdx
@@ -723,7 +723,7 @@ Note that you will have to set [`strict_open_ai_compliance=False`](/product/ai-g
 
 ### Using reasoning_effort Parameter
 
-You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:
+You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`. The value is passed directly to Gemini as the `thinkingLevel`:
 
 ```python
 response = portkey.chat.completions.create(
@@ -737,8 +737,10 @@ response = portkey.chat.completions.create(
 | reasoning_effort | Vertex thinkingLevel |
 |------------------|---------------------|
 | `none` | Disabled |
-| `minimal`, `low` | `low` |
-| `medium`, `high` | `high` |
+| `minimal` | `minimal` |
+| `low` | `low` |
+| `medium` | `medium` |
+| `high` | `high` |
 
 ### Multi turn conversation