test: remove o1-preview

tests/llm_translation/test_openai.py

@@ -337,7 +337,7 @@ def test_openai_max_retries_0(mock_get_openai_client):
     assert mock_get_openai_client.call_args.kwargs["max_retries"] == 0
 
 
-@pytest.mark.parametrize("model", ["o1", "o1-preview", "o1-mini", "o3-mini"])
+@pytest.mark.parametrize("model", ["o1", "o1-mini", "o3-mini"])
 def test_o1_parallel_tool_calls(model):
     litellm.completion(
         model=model,
@@ -544,6 +544,7 @@ async def test_openai_codex(sync_mode):
 
     assert response.choices[0].message.content is not None
 
+
 @pytest.mark.asyncio
 async def test_openai_via_gemini_streaming_bridge():
     """
@@ -586,6 +587,7 @@ async def test_openai_via_gemini_streaming_bridge():
 
     assert len(printed_chunks) > 0
 
+
 def test_openai_deepresearch_model_bridge():
     """
     Test that the deepresearch model bridge works correctly

tests/llm_translation/test_openai_o1.py

@@ -18,7 +18,7 @@ from litellm import Choices, Message, ModelResponse
 from base_llm_unit_tests import BaseLLMChatTest, BaseOSeriesModelsTest
 
 
-@pytest.mark.parametrize("model", ["o1-preview", "o1-mini", "o1"])
+@pytest.mark.parametrize("model", ["o1-mini", "o1"])
 @pytest.mark.asyncio
 async def test_o1_handle_system_role(model):
     """
@@ -68,7 +68,7 @@ async def test_o1_handle_system_role(model):
 
 @pytest.mark.parametrize(
     "model, expected_tool_calling_support",
-    [("o1-preview", False), ("o1-mini", False), ("o1", True)],
+    [("o1-mini", False), ("o1", True)],
 )
 @pytest.mark.asyncio
 async def test_o1_handle_tool_calling_optional_params(
@@ -96,7 +96,7 @@ async def test_o1_handle_tool_calling_optional_params(
 
 
 @pytest.mark.asyncio
-@pytest.mark.parametrize("model", ["gpt-4", "gpt-4-0314", "gpt-4-32k", "o1-preview"])
+@pytest.mark.parametrize("model", ["gpt-4", "gpt-4-0314", "gpt-4-32k"])
 async def test_o1_max_completion_tokens(model: str):
     """
     Tests that:
@@ -210,7 +210,7 @@ def test_o3_reasoning_effort():
     assert resp.choices[0].message.content is not None
 
 
-@pytest.mark.parametrize("model", ["o1-preview", "o1-mini", "o1", "o3-mini"])
+@pytest.mark.parametrize("model", ["o1-mini", "o1", "o3-mini"])
 def test_streaming_response(model):
     """Test that streaming response is returned correctly"""
     from litellm import completion

tests/local_testing/test_streaming.py

@@ -1989,7 +1989,6 @@ def test_openai_chat_completion_complete_response_call():
         "gpt-3.5-turbo",
         "azure/chatgpt-v-3",
         "claude-3-haiku-20240307",
-        "o1-preview",
         "o1",
         "azure/fake-o1-mini",
     ],
@@ -2156,54 +2155,6 @@ def test_together_ai_completion_call_mistral():
 
 
 # # test on together ai completion call - starcoder
-@pytest.mark.parametrize("sync_mode", [True, False])
-@pytest.mark.asyncio
-async def test_openai_o1_completion_call_streaming(sync_mode):
-    try:
-        litellm.set_verbose = False
-        if sync_mode:
-            response = completion(
-                model="o1-preview",
-                messages=messages,
-                stream=True,
-            )
-            complete_response = ""
-            print(f"returned response object: {response}")
-            has_finish_reason = False
-            for idx, chunk in enumerate(response):
-                chunk, finished = streaming_format_tests(idx, chunk)
-                has_finish_reason = finished
-                if finished:
-                    break
-                complete_response += chunk
-            if has_finish_reason is False:
-                raise Exception("Finish reason not set for last chunk")
-            if complete_response == "":
-                raise Exception("Empty response received")
-        else:
-            response = await acompletion(
-                model="o1-preview",
-                messages=messages,
-                stream=True,
-            )
-            complete_response = ""
-            print(f"returned response object: {response}")
-            has_finish_reason = False
-            idx = 0
-            async for chunk in response:
-                chunk, finished = streaming_format_tests(idx, chunk)
-                has_finish_reason = finished
-                if finished:
-                    break
-                complete_response += chunk
-                idx += 1
-            if has_finish_reason is False:
-                raise Exception("Finish reason not set for last chunk")
-            if complete_response == "":
-                raise Exception("Empty response received")
-        print(f"complete response: {complete_response}")
-    except Exception:
-        pytest.fail(f"error occurred: {traceback.format_exc()}")
 
 
 def test_together_ai_completion_call_starcoder_bad_key():

tests/test_litellm/llms/openai/test_o_series_transformation.py

@@ -10,13 +10,11 @@ from litellm.llms.openai.chat.o_series_transformation import OpenAIOSeriesConfig
         ("o1", True),
         ("o3", True),
         ("o4-mini", True),
-        ("o1-preview", True),
         ("o3-mini", True),
         # Valid O-series models with provider prefix
         ("openai/o1", True),
         ("openai/o3", True),
         ("openai/o4-mini", True),
-        ("openai/o1-preview", True),
         ("openai/o3-mini", True),
         # Non-O-series models
         ("gpt-4", False),