diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index d4fd060630..6208111406 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -511,7 +511,6 @@ class AmazonConverseConfig(BaseConfig):
             "response_format",
             "requestMetadata",
             "service_tier",
-            "parallel_tool_calls",
         ]
 
         if (
@@ -914,13 +913,6 @@ class AmazonConverseConfig(BaseConfig):
                 )
                 if _tool_choice_value is not None:
                     optional_params["tool_choice"] = _tool_choice_value
-            if param == "parallel_tool_calls":
-                disable_parallel = not value
-                optional_params["_parallel_tool_use_config"] = {
-                    "tool_choice": {
-                        "disable_parallel_tool_use": disable_parallel
-                    }
-                }
             if param == "thinking":
                 optional_params["thinking"] = value
             elif param == "reasoning_effort" and isinstance(value, str):
@@ -1215,17 +1207,6 @@ class AmazonConverseConfig(BaseConfig):
             k: v for k, v in inference_params.items() if k in total_supported_params
         }
 
-        # Handle parallel_tool_calls configuration
-        parallel_tool_use_config = additional_request_params.pop("_parallel_tool_use_config", None)
-        if parallel_tool_use_config is not None:
-            # Merge the tool_choice config from parallel_tool_calls into additional_request_params
-            for key, value in parallel_tool_use_config.items():
-                if key in additional_request_params and isinstance(additional_request_params[key], dict) and isinstance(value, dict):
-                    # Merge dictionaries
-                    additional_request_params[key].update(value)
-                else:
-                    additional_request_params[key] = value
-
         # Only set the topK value in for models that support it
         additional_request_params.update(
             self._handle_top_k_value(model, inference_params)
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 2639559716..c773db2107 100644
--- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
+++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
@@ -2616,11 +2616,11 @@ def test_empty_assistant_message_handling():
     empty or whitespace-only content with a placeholder to prevent AWS Bedrock
     Converse API 400 Bad Request errors.
     """
-    # Import the litellm module that factory.py uses to ensure we patch the correct reference
-    import litellm.litellm_core_utils.prompt_templates.factory as factory_module
     from litellm.litellm_core_utils.prompt_templates.factory import (
         _bedrock_converse_messages_pt,
     )
+    # Import the litellm module that factory.py uses to ensure we patch the correct reference
+    import litellm.litellm_core_utils.prompt_templates.factory as factory_module
 
     # Test case 1: Empty string content - test with modify_params=True to prevent merging
     messages = [
@@ -3135,12 +3135,7 @@ def test_native_structured_output_no_fake_stream():
 
 def test_transform_request_with_output_config():
     """Test that outputConfig flows through _transform_request_helper into the final request."""
-    from litellm.types.llms.bedrock import (
-        JsonSchemaDefinition,
-        OutputConfigBlock,
-        OutputFormat,
-        OutputFormatStructure,
-    )
+    from litellm.types.llms.bedrock import OutputConfigBlock, OutputFormat, OutputFormatStructure, JsonSchemaDefinition
 
     config = AmazonConverseConfig()
 
@@ -3382,61 +3377,6 @@ def test_output_config_applies_additional_properties():
 
 
 
-def test_parallel_tool_calls_in_request_transformation():
-    """Test that parallel_tool_calls is correctly placed in additionalModelRequestFields after full transformation"""
-    config = AmazonConverseConfig()
-    
-    messages = [
-        {"role": "user", "content": "What's the weather in SF and NYC?"}
-    ]
-    
-    non_default_params = {
-        "parallel_tool_calls": False,
-        "tools": [
-            {
-                "type": "function",
-                "function": {
-                    "name": "get_weather",
-                    "description": "Get the weather",
-                    "parameters": {
-                        "type": "object",
-                        "properties": {
-                            "location": {
-                                "type": "string",
-                                "description": "The location to get weather for"
-                            }
-                        },
-                        "required": ["location"]
-                    }
-                }
-            }
-        ],
-        "max_tokens": 100,
-    }
-    
-    optional_params = config.map_openai_params(
-        non_default_params=non_default_params,
-        optional_params={},
-        model="anthropic.claude-sonnet-4-5-v2:0",
-        drop_params=False,
-    )
-    
-    # Transform the request
-    request_data = config.transform_request(
-        model="anthropic.claude-sonnet-4-5-v2:0",
-        messages=messages,
-        optional_params=optional_params,
-        litellm_params={},
-        headers={},
-    )
-    
-    # Verify the structure
-    assert "additionalModelRequestFields" in request_data
-    assert "tool_choice" in request_data["additionalModelRequestFields"]
-    assert "disable_parallel_tool_use" in request_data["additionalModelRequestFields"]["tool_choice"]
-    assert request_data["additionalModelRequestFields"]["tool_choice"]["disable_parallel_tool_use"] is True
-
-
 class TestBedrockMinThinkingBudgetTokens:
     """Test that thinking.budget_tokens is clamped to the Bedrock minimum (1024)."""