diff --git a/.buildkite/test_areas/entrypoints.yaml b/.buildkite/test_areas/entrypoints.yaml
index a04ead99a..9de9c3fd2 100644
--- a/.buildkite/test_areas/entrypoints.yaml
+++ b/.buildkite/test_areas/entrypoints.yaml
@@ -34,7 +34,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
   mirror:
     amd:
diff --git a/.github/mergify.yml b/.github/mergify.yml
index d974aa4af..0373c0448 100644
--- a/.github/mergify.yml
+++ b/.github/mergify.yml
@@ -334,7 +334,7 @@ pull_request_rules:
     - or:
       - files~=^tests/tool_use/
       - files~=^tests/entrypoints/openai/tool_parsers/
-      - files=tests/entrypoints/openai/test_chat_with_tool_reasoning.py
+      - files=tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py
       - files~=^vllm/entrypoints/openai/tool_parsers/
       - files=docs/features/tool_calling.md
       - files~=^examples/tool_chat_*
diff --git a/tests/entrypoints/anthropic/__init__.py b/tests/entrypoints/anthropic/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/tests/entrypoints/openai/test_anthropic_messages_conversion.py b/tests/entrypoints/anthropic/test_anthropic_messages_conversion.py
similarity index 100%
rename from tests/entrypoints/openai/test_anthropic_messages_conversion.py
rename to tests/entrypoints/anthropic/test_anthropic_messages_conversion.py
diff --git a/tests/entrypoints/openai/chat_completion/__init__.py b/tests/entrypoints/openai/chat_completion/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/tests/entrypoints/openai/test_chat.py b/tests/entrypoints/openai/chat_completion/test_chat.py
similarity index 99%
rename from tests/entrypoints/openai/test_chat.py
rename to tests/entrypoints/openai/chat_completion/test_chat.py
index c480adcc1..25f4c7d7a 100644
--- a/tests/entrypoints/openai/test_chat.py
+++ b/tests/entrypoints/openai/chat_completion/test_chat.py
@@ -14,13 +14,12 @@ import requests
 import torch
 from openai import BadRequestError
 
+from tests.utils import RemoteOpenAIServer
 from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionRequest,
 )
 from vllm.sampling_params import SamplingParams
 
-from ...utils import RemoteOpenAIServer
-
 # any model with a chat template should work here
 MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
 
diff --git a/tests/entrypoints/openai/test_chat_echo.py b/tests/entrypoints/openai/chat_completion/test_chat_echo.py
similarity index 98%
rename from tests/entrypoints/openai/test_chat_echo.py
rename to tests/entrypoints/openai/chat_completion/test_chat_echo.py
index b3b8b7003..45f22463a 100644
--- a/tests/entrypoints/openai/test_chat_echo.py
+++ b/tests/entrypoints/openai/chat_completion/test_chat_echo.py
@@ -7,10 +7,9 @@ import openai  # use the official client for correctness check
 import pytest
 import pytest_asyncio
 
+from tests.utils import RemoteOpenAIServer
 from vllm.config import ModelConfig
 
-from ...utils import RemoteOpenAIServer
-
 # # any model with a chat template should work here
 MODEL_NAME = "Qwen/Qwen2-1.5B-Instruct"
 
diff --git a/tests/entrypoints/openai/test_chat_error.py b/tests/entrypoints/openai/chat_completion/test_chat_error.py
similarity index 100%
rename from tests/entrypoints/openai/test_chat_error.py
rename to tests/entrypoints/openai/chat_completion/test_chat_error.py
diff --git a/tests/entrypoints/openai/test_chat_logit_bias_validation.py b/tests/entrypoints/openai/chat_completion/test_chat_logit_bias_validation.py
similarity index 97%
rename from tests/entrypoints/openai/test_chat_logit_bias_validation.py
rename to tests/entrypoints/openai/chat_completion/test_chat_logit_bias_validation.py
index 6539613ed..22e17a14d 100644
--- a/tests/entrypoints/openai/test_chat_logit_bias_validation.py
+++ b/tests/entrypoints/openai/chat_completion/test_chat_logit_bias_validation.py
@@ -5,10 +5,9 @@ import openai
 import pytest
 import pytest_asyncio
 
+from tests.utils import RemoteOpenAIServer
 from vllm.config import ModelConfig
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"
 
 
diff --git a/tests/entrypoints/openai/test_chat_with_tool_reasoning.py b/tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py
similarity index 99%
rename from tests/entrypoints/openai/test_chat_with_tool_reasoning.py
rename to tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py
index 445fa389d..295b55889 100644
--- a/tests/entrypoints/openai/test_chat_with_tool_reasoning.py
+++ b/tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py
@@ -5,7 +5,7 @@ import openai  # use the official client for correctness check
 import pytest
 import pytest_asyncio
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # a reasoning and tool calling model
 MODEL_NAME = "Qwen/QwQ-32B"
diff --git a/tests/entrypoints/openai/test_completion_with_function_calling.py b/tests/entrypoints/openai/chat_completion/test_completion_with_function_calling.py
similarity index 99%
rename from tests/entrypoints/openai/test_completion_with_function_calling.py
rename to tests/entrypoints/openai/chat_completion/test_completion_with_function_calling.py
index 39ab13213..704598a57 100644
--- a/tests/entrypoints/openai/test_completion_with_function_calling.py
+++ b/tests/entrypoints/openai/chat_completion/test_completion_with_function_calling.py
@@ -10,7 +10,7 @@ import pytest
 import pytest_asyncio
 
 # downloading lora to test lora requests
-from ...utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
+from tests.utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "Qwen/Qwen3-0.6B"
diff --git a/tests/entrypoints/openai/test_enable_force_include_usage.py b/tests/entrypoints/openai/chat_completion/test_enable_force_include_usage.py
similarity index 98%
rename from tests/entrypoints/openai/test_enable_force_include_usage.py
rename to tests/entrypoints/openai/chat_completion/test_enable_force_include_usage.py
index 8e7e34ee2..0d53b545d 100644
--- a/tests/entrypoints/openai/test_enable_force_include_usage.py
+++ b/tests/entrypoints/openai/chat_completion/test_enable_force_include_usage.py
@@ -4,7 +4,7 @@ import openai
 import pytest
 import pytest_asyncio
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 
 @pytest.fixture(scope="module")
diff --git a/tests/entrypoints/openai/test_serving_chat.py b/tests/entrypoints/openai/chat_completion/test_serving_chat.py
similarity index 99%
rename from tests/entrypoints/openai/test_serving_chat.py
rename to tests/entrypoints/openai/chat_completion/test_serving_chat.py
index 3791faa38..b7dcf7938 100644
--- a/tests/entrypoints/openai/test_serving_chat.py
+++ b/tests/entrypoints/openai/chat_completion/test_serving_chat.py
@@ -10,6 +10,12 @@ import pytest
 import pytest_asyncio
 from openai import OpenAI
 
+from tests.entrypoints.openai.utils import (
+    accumulate_streaming_response,
+    verify_chat_response,
+    verify_harmony_messages,
+)
+from tests.utils import RemoteOpenAIServer
 from vllm._aiter_ops import is_aiter_found_and_supported
 from vllm.config import MultiModalConfig
 from vllm.entrypoints.openai.chat_completion.protocol import (
@@ -39,13 +45,6 @@ from vllm.tokenizers.registry import tokenizer_args_from_config
 from vllm.tool_parsers import ToolParserManager
 from vllm.v1.engine.async_llm import AsyncLLM
 
-from ...utils import RemoteOpenAIServer
-from .utils import (
-    accumulate_streaming_response,
-    verify_chat_response,
-    verify_harmony_messages,
-)
-
 GPT_OSS_MODEL_NAME = "openai/gpt-oss-20b"
 GPT_OSS_SPECULATOR_NAME = "RedHatAI/gpt-oss-20b-speculator.eagle3"
 
diff --git a/tests/entrypoints/openai/test_serving_chat_stream_harmony.py b/tests/entrypoints/openai/chat_completion/test_serving_chat_stream_harmony.py
similarity index 100%
rename from tests/entrypoints/openai/test_serving_chat_stream_harmony.py
rename to tests/entrypoints/openai/chat_completion/test_serving_chat_stream_harmony.py