diff --git a/src/api/providers/__tests__/openai-native-tools.spec.ts b/src/api/providers/__tests__/openai-native-tools.spec.ts
index 7be4814b63..4ce6afd320 100644
--- a/src/api/providers/__tests__/openai-native-tools.spec.ts
+++ b/src/api/providers/__tests__/openai-native-tools.spec.ts
@@ -71,10 +71,13 @@ describe("OpenAiHandler native tools", () => {
 						function: expect.objectContaining({ name: "test_tool" }),
 					}),
 				]),
-				parallel_tool_calls: false,
 			}),
 			expect.anything(),
 		)
+		// Verify parallel_tool_calls is NOT included when parallelToolCalls is not explicitly true
+		// This is required for LiteLLM/Bedrock compatibility (see COM-406)
+		const callArgs = mockCreate.mock.calls[0][0]
+		expect(callArgs).not.toHaveProperty("parallel_tool_calls")
 	})
 })
 
diff --git a/src/api/providers/openai.ts b/src/api/providers/openai.ts
index 43a4fe7ae3..9d632fbdf4 100644
--- a/src/api/providers/openai.ts
+++ b/src/api/providers/openai.ts
@@ -162,9 +162,10 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
 				...(reasoning && reasoning),
 				...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
 				...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
-				...(metadata?.toolProtocol === "native" && {
-					parallel_tool_calls: metadata.parallelToolCalls ?? false,
-				}),
+				...(metadata?.toolProtocol === "native" &&
+					metadata.parallelToolCalls === true && {
+						parallel_tool_calls: true,
+					}),
 			}
 
 			// Add max_tokens if needed
@@ -231,9 +232,10 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
 					: [systemMessage, ...convertToOpenAiMessages(messages)],
 				...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
 				...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
-				...(metadata?.toolProtocol === "native" && {
-					parallel_tool_calls: metadata.parallelToolCalls ?? false,
-				}),
+				...(metadata?.toolProtocol === "native" &&
+					metadata.parallelToolCalls === true && {
+						parallel_tool_calls: true,
+					}),
 			}
 
 			// Add max_tokens if needed
@@ -357,9 +359,10 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
 				temperature: undefined,
 				...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
 				...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
-				...(metadata?.toolProtocol === "native" && {
-					parallel_tool_calls: metadata.parallelToolCalls ?? false,
-				}),
+				...(metadata?.toolProtocol === "native" &&
+					metadata.parallelToolCalls === true && {
+						parallel_tool_calls: true,
+					}),
 			}
 
 			// O3 family models do not support the deprecated max_tokens parameter
@@ -392,9 +395,10 @@ export class OpenAiHandler extends BaseProvider implements SingleCompletionHandl
 				temperature: undefined,
 				...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
 				...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
-				...(metadata?.toolProtocol === "native" && {
-					parallel_tool_calls: metadata.parallelToolCalls ?? false,
-				}),
+				...(metadata?.toolProtocol === "native" &&
+					metadata.parallelToolCalls === true && {
+						parallel_tool_calls: true,
+					}),
 			}
 
 			// O3 family models do not support the deprecated max_tokens parameter