diff --git a/integrations/llms/gemini.mdx b/integrations/llms/gemini.mdx
index fc9236d0..34f6229f 100644
--- a/integrations/llms/gemini.mdx
+++ b/integrations/llms/gemini.mdx
@@ -2135,17 +2135,32 @@ 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`. The value is passed directly to Gemini as the `thinkingLevel`:
+You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:
 
 ```python
 response = portkey.chat.completions.create(
     model="gemini-2.5-flash-preview-04-17",
     max_tokens=3000,
-    reasoning_effort="medium",  # Options: "none", "minimal", "low", "medium", "high"
+    reasoning_effort="medium",  # Options: "none", "low", "medium", "high"
     messages=[{"role": "user", "content": "Explain quantum computing"}]
 )
 ```
 
+#### Gemini 2.5 Models
+
+For Gemini 2.5 models, `reasoning_effort` maps to `thinking_budget` with specific token allocations:
+
+| reasoning_effort | thinking_budget (tokens) |
+|------------------|--------------------------|
+| `none` | Disabled |
+| `low` | 1,024 |
+| `medium` | 8,192 |
+| `high` | 24,576 |
+
+#### Gemini 3.0+ Models
+
+For Gemini 3.0 and later models, `reasoning_effort` maps directly to `thinkingLevel`:
+
 | reasoning_effort | Gemini thinkingLevel |
 |------------------|---------------------|
 | `none` | Disabled |
diff --git a/integrations/llms/vertex-ai.mdx b/integrations/llms/vertex-ai.mdx
index 08a0c4f4..c9d508fd 100644
--- a/integrations/llms/vertex-ai.mdx
+++ b/integrations/llms/vertex-ai.mdx
@@ -723,17 +723,32 @@ 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`. The value is passed directly to Gemini as the `thinkingLevel`:
+You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:
 
 ```python
 response = portkey.chat.completions.create(
     model="@VERTEX_PROVIDER/google.gemini-2.5-flash-preview-04-17",
     max_tokens=3000,
-    reasoning_effort="medium",  # Options: "none", "minimal", "low", "medium", "high"
+    reasoning_effort="medium",  # Options: "none", "low", "medium", "high"
     messages=[{"role": "user", "content": "Explain quantum computing"}]
 )
 ```
 
+#### Gemini 2.5 Models
+
+For Gemini 2.5 models, `reasoning_effort` maps to `thinking_budget` with specific token allocations:
+
+| reasoning_effort | thinking_budget (tokens) |
+|------------------|--------------------------|
+| `none` | Disabled |
+| `low` | 1,024 |
+| `medium` | 8,192 |
+| `high` | 24,576 |
+
+#### Gemini 3.0+ Models
+
+For Gemini 3.0 and later models, `reasoning_effort` maps directly to `thinkingLevel`:
+
 | reasoning_effort | Vertex thinkingLevel |
 |------------------|---------------------|
 | `none` | Disabled |