diff --git a/tests/entrypoints/openai/parser/__init__.py b/tests/entrypoints/openai/parser/__init__.py
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/tests/entrypoints/test_harmony_utils.py b/tests/entrypoints/openai/parser/test_harmony_utils.py
similarity index 99%
rename from tests/entrypoints/test_harmony_utils.py
rename to tests/entrypoints/openai/parser/test_harmony_utils.py
index 82ff562d5c6d2..ae6f558f22b03 100644
--- a/tests/entrypoints/test_harmony_utils.py
+++ b/tests/entrypoints/openai/parser/test_harmony_utils.py
@@ -4,7 +4,7 @@
 from openai.types.responses import ResponseFunctionToolCall, ResponseReasoningItem
 from openai_harmony import Author, Message, Role, TextContent
 
-from vllm.entrypoints.harmony_utils import (
+from vllm.entrypoints.openai.parser.harmony_utils import (
     has_custom_tools,
     parse_input_to_harmony_message,
     parse_output_message,
diff --git a/tests/entrypoints/openai/test_response_api_with_harmony.py b/tests/entrypoints/openai/test_response_api_with_harmony.py
index 8fd3545eccffa..6f2a50020699c 100644
--- a/tests/entrypoints/openai/test_response_api_with_harmony.py
+++ b/tests/entrypoints/openai/test_response_api_with_harmony.py
@@ -726,7 +726,7 @@ async def test_function_calling_required(client: OpenAI, model_name: str):
 @pytest.mark.asyncio
 @pytest.mark.parametrize("model_name", [MODEL_NAME])
 async def test_system_message_with_tools(client: OpenAI, model_name: str):
-    from vllm.entrypoints.harmony_utils import get_system_message
+    from vllm.entrypoints.openai.parser.harmony_utils import get_system_message
 
     # Test with custom tools enabled - commentary channel should be available
     sys_msg = get_system_message(with_custom_tools=True)
diff --git a/vllm/entrypoints/context.py b/vllm/entrypoints/context.py
index f50c473d7a773..a484a437c853e 100644
--- a/vllm/entrypoints/context.py
+++ b/vllm/entrypoints/context.py
@@ -19,7 +19,7 @@ from vllm import envs
 from vllm.entrypoints.chat_utils import (
     ChatTemplateContentFormatOption,
 )
-from vllm.entrypoints.harmony_utils import (
+from vllm.entrypoints.openai.parser.harmony_utils import (
     get_encoding,
     get_streamable_parser_for_assistant,
     render_for_completion,
diff --git a/vllm/entrypoints/harmony_utils.py b/vllm/entrypoints/openai/parser/harmony_utils.py
similarity index 100%
rename from vllm/entrypoints/harmony_utils.py
rename to vllm/entrypoints/openai/parser/harmony_utils.py
diff --git a/vllm/entrypoints/openai/serving_chat.py b/vllm/entrypoints/openai/serving_chat.py
index 9b7bc461e4511..c6333d170c663 100644
--- a/vllm/entrypoints/openai/serving_chat.py
+++ b/vllm/entrypoints/openai/serving_chat.py
@@ -21,7 +21,8 @@ from vllm.entrypoints.chat_utils import (
     get_history_tool_calls_cnt,
     make_tool_call_id,
 )
-from vllm.entrypoints.harmony_utils import (
+from vllm.entrypoints.logger import RequestLogger
+from vllm.entrypoints.openai.parser.harmony_utils import (
     get_developer_message,
     get_stop_tokens_for_assistant_actions,
     get_streamable_parser_for_assistant,
@@ -30,7 +31,6 @@ from vllm.entrypoints.harmony_utils import (
     parse_input_to_harmony_message,
     render_for_completion,
 )
-from vllm.entrypoints.logger import RequestLogger
 from vllm.entrypoints.openai.protocol import (
     ChatCompletionLogProb,
     ChatCompletionLogProbs,
diff --git a/vllm/entrypoints/openai/serving_responses.py b/vllm/entrypoints/openai/serving_responses.py
index 1eb1243e7e5bc..91616a78e11dc 100644
--- a/vllm/entrypoints/openai/serving_responses.py
+++ b/vllm/entrypoints/openai/serving_responses.py
@@ -64,7 +64,8 @@ from vllm.entrypoints.context import (
     SimpleContext,
     StreamingHarmonyContext,
 )
-from vllm.entrypoints.harmony_utils import (
+from vllm.entrypoints.logger import RequestLogger
+from vllm.entrypoints.openai.parser.harmony_utils import (
     construct_harmony_previous_input_messages,
     get_developer_message,
     get_stop_tokens_for_assistant_actions,
@@ -76,7 +77,6 @@ from vllm.entrypoints.harmony_utils import (
     parse_response_input,
     render_for_completion,
 )
-from vllm.entrypoints.logger import RequestLogger
 from vllm.entrypoints.openai.protocol import (
     DeltaMessage,
     ErrorResponse,
diff --git a/vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py b/vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py
index 8bdf35d408805..387e87f208e66 100644
--- a/vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py
+++ b/vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py
@@ -4,7 +4,7 @@ import json
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from vllm.entrypoints.harmony_utils import parse_output_into_messages
+from vllm.entrypoints.openai.parser.harmony_utils import parse_output_into_messages
 from vllm.entrypoints.openai.protocol import (
     ChatCompletionRequest,
     DeltaMessage,
diff --git a/vllm/reasoning/gptoss_reasoning_parser.py b/vllm/reasoning/gptoss_reasoning_parser.py
index fa45b12856c7d..e0920ef3160b2 100644
--- a/vllm/reasoning/gptoss_reasoning_parser.py
+++ b/vllm/reasoning/gptoss_reasoning_parser.py
@@ -5,7 +5,7 @@ from collections.abc import Sequence
 
 from transformers import PreTrainedTokenizerBase
 
-from vllm.entrypoints.harmony_utils import parse_chat_output
+from vllm.entrypoints.openai.parser.harmony_utils import parse_chat_output
 from vllm.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage
 from vllm.entrypoints.tool_server import ToolServer
 from vllm.logger import init_logger