diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index 4fa407701cb..ebb8ca759ef 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -51,6 +51,7 @@ from litellm.types.llms.openai import (
 )
 from litellm.types.utils import (
     ChatCompletionMessageToolCall,
+    CompletionTokensDetailsWrapper,
     Function,
     Message,
     ModelResponse,
@@ -63,6 +64,7 @@ from litellm.utils import (
     has_tool_call_blocks,
     last_assistant_with_tool_calls_has_no_thinking_blocks,
     supports_reasoning,
+    token_counter,
 )
 
 from ..common_utils import (
@@ -1621,7 +1623,11 @@ class AmazonConverseConfig(BaseConfig):
                 thinking_blocks_list.append(_redacted_block)
         return thinking_blocks_list
 
-    def _transform_usage(self, usage: ConverseTokenUsageBlock) -> Usage:
+    def _transform_usage(
+        self,
+        usage: ConverseTokenUsageBlock,
+        reasoning_content: Optional[str] = None,
+    ) -> Usage:
         input_tokens = usage["inputTokens"]
         output_tokens = usage["outputTokens"]
         total_tokens = usage["totalTokens"]
@@ -1638,6 +1644,19 @@ class AmazonConverseConfig(BaseConfig):
         prompt_tokens_details = PromptTokensDetailsWrapper(
             cached_tokens=cache_read_input_tokens
         )
+        reasoning_tokens = (
+            token_counter(text=reasoning_content, count_response_tokens=True)
+            if reasoning_content
+            else 0
+        )
+        completion_tokens_details = CompletionTokensDetailsWrapper(
+            reasoning_tokens=reasoning_tokens,
+            text_tokens=(
+                output_tokens - reasoning_tokens
+                if reasoning_tokens > 0
+                else output_tokens
+            ),
+        )
         openai_usage = Usage(
             prompt_tokens=input_tokens,
             completion_tokens=output_tokens,
@@ -1645,6 +1664,7 @@ class AmazonConverseConfig(BaseConfig):
             prompt_tokens_details=prompt_tokens_details,
             cache_creation_input_tokens=cache_creation_input_tokens,
             cache_read_input_tokens=cache_read_input_tokens,
+            completion_tokens_details=completion_tokens_details,
         )
         return openai_usage
 
@@ -1981,7 +2001,10 @@ class AmazonConverseConfig(BaseConfig):
             chat_completion_message["tool_calls"] = filtered_tools
 
         ## CALCULATING USAGE - bedrock returns usage in the headers
-        usage = self._transform_usage(completion_response["usage"])
+        usage = self._transform_usage(
+            completion_response["usage"],
+            reasoning_content=chat_completion_message.get("reasoning_content"),
+        )
 
         ## HANDLE TOOL CALLS
         _message = Message(**chat_completion_message)
diff --git a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
index 7e1f235c49e..9892a0403b5 100644
--- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
+++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
@@ -43,6 +43,29 @@ def test_transform_usage():
     )
     assert openai_usage._cache_creation_input_tokens == usage["cacheWriteInputTokens"]
     assert openai_usage._cache_read_input_tokens == usage["cacheReadInputTokens"]
+    # completion_tokens_details should always be populated
+    assert openai_usage.completion_tokens_details is not None
+    assert openai_usage.completion_tokens_details.reasoning_tokens == 0
+    assert openai_usage.completion_tokens_details.text_tokens == usage["outputTokens"]
+
+
+def test_transform_usage_with_reasoning_content():
+    """Test that completion_tokens_details correctly tracks reasoning vs text tokens."""
+    usage = ConverseTokenUsageBlock(
+        **{
+            "inputTokens": 10,
+            "outputTokens": 100,
+            "totalTokens": 110,
+        }
+    )
+    config = AmazonConverseConfig()
+    reasoning_text = "Let me think about this step by step."
+    openai_usage = config._transform_usage(usage, reasoning_content=reasoning_text)
+    assert openai_usage.completion_tokens_details is not None
+    assert openai_usage.completion_tokens_details.reasoning_tokens > 0
+    assert openai_usage.completion_tokens_details.text_tokens == (
+        usage["outputTokens"] - openai_usage.completion_tokens_details.reasoning_tokens
+    )
 
 
 def test_transform_system_message():