diff --git a/tests/llm_translation/test_anthropic_text_completion.py b/tests/llm_translation/test_anthropic_text_completion.py
deleted file mode 100644
index c0aa5b5d88..0000000000
--- a/tests/llm_translation/test_anthropic_text_completion.py
+++ /dev/null
@@ -1,73 +0,0 @@
-import asyncio
-import os
-import sys
-import traceback
-
-from dotenv import load_dotenv
-
-import litellm.types
-import litellm.types.utils
-from litellm.llms.anthropic.chat import ModelResponseIterator
-
-load_dotenv()
-import io
-import os
-
-sys.path.insert(
-    0, os.path.abspath("../..")
-)  # Adds the parent directory to the system path
-from typing import Optional
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize("model", ["claude-2", "anthropic/claude-2"])
-@pytest.mark.flaky(retries=6, delay=1)
-async def test_acompletion_claude2(model):
-    try:
-        litellm.set_verbose = True
-        messages = [
-            {
-                "role": "system",
-                "content": "Your goal is generate a joke on the topic user gives.",
-            },
-            {"role": "user", "content": "Generate a 3 liner joke for me"},
-        ]
-        # test without max-tokens
-        response = await litellm.acompletion(model=model, messages=messages)
-        # Add any assertions here to check the response
-        print(response)
-        print(response.usage)
-        print(response.usage.completion_tokens)
-        print(response["usage"]["completion_tokens"])
-        # print("new cost tracking")
-    except litellm.InternalServerError:
-        pytest.skip("model is overloaded.")
-    except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
-
-
-@pytest.mark.asyncio
-async def test_acompletion_claude2_stream():
-    try:
-        litellm.set_verbose = False
-        messages = [
-            {
-                "role": "system",
-                "content": "Your goal is generate a joke on the topic user gives.",
-            },
-            {"role": "user", "content": "Generate a 3 liner joke for me"},
-        ]
-        # test without max-tokens
-        response = await litellm.acompletion(
-            model="anthropic_text/claude-2",
-            messages=messages,
-            stream=True,
-            max_tokens=10,
-        )
-        async for chunk in response:
-            print(chunk)
-    except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
diff --git a/tests/local_testing/test_streaming.py b/tests/local_testing/test_streaming.py
index d989302c63..5db4094677 100644
--- a/tests/local_testing/test_streaming.py
+++ b/tests/local_testing/test_streaming.py
@@ -642,7 +642,6 @@ def test_completion_ollama_hosted_stream():
     "model",
     [
         # "claude-3-5-haiku-20241022",
-        # "claude-2",
         # "mistral/mistral-small-latest",
         "openrouter/openai/gpt-4o-mini",
     ],
@@ -673,36 +672,6 @@ def test_completion_model_stream(model):
         pytest.fail(f"Error occurred: {e}")
 
 
-@pytest.mark.asyncio
-async def test_acompletion_claude_2_stream():
-    try:
-        litellm.set_verbose = True
-        response = await litellm.acompletion(
-            model="claude-2.1",
-            messages=[{"role": "user", "content": "hello from litellm"}],
-            stream=True,
-        )
-        complete_response = ""
-        # Add any assertions here to check the response
-        idx = 0
-        async for chunk in response:
-            print(chunk)
-            # print(chunk.choices[0].delta)
-            chunk, finished = streaming_format_tests(idx, chunk)
-            if finished:
-                break
-            complete_response += chunk
-            idx += 1
-        if complete_response.strip() == "":
-            raise Exception("Empty response received")
-        print(f"completion_response: {complete_response}")
-    except litellm.InternalServerError:
-        pass
-    except litellm.RateLimitError:
-        pass
-    except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
-
 
 @pytest.mark.parametrize(
     "sync_mode",