diff --git a/tests/local_testing/test_completion.py b/tests/local_testing/test_completion.py index 2b01b4c2a12..5e92c10fbdc 100644 --- a/tests/local_testing/test_completion.py +++ b/tests/local_testing/test_completion.py @@ -286,7 +286,7 @@ def test_completion_claude_3_empty_response(): }, ] try: - response = litellm.completion(model="claude-3-opus-20240229", messages=messages) + response = litellm.completion(model="claude-3-7-sonnet-20250219", messages=messages) print(response) except litellm.InternalServerError as e: pytest.skip(f"InternalServerError - {str(e)}") @@ -313,7 +313,7 @@ def test_completion_claude_3(): try: # test without max tokens response = completion( - model="anthropic/claude-3-opus-20240229", + model="anthropic/claude-3-7-sonnet-20250219", messages=messages, ) # Add any assertions, here to check response args @@ -326,7 +326,7 @@ def test_completion_claude_3(): @pytest.mark.parametrize( "model", - ["anthropic/claude-3-opus-20240229", "anthropic.claude-3-sonnet-20240229-v1:0"], + ["anthropic/claude-3-7-sonnet-20250219", "anthropic.claude-3-sonnet-20240229-v1:0"], ) def test_completion_claude_3_function_call(model): litellm.set_verbose = True @@ -411,7 +411,7 @@ def test_completion_claude_3_function_call(model): "model, api_key, api_base", [ ("gpt-3.5-turbo", None, None), - ("claude-3-opus-20240229", None, None), + ("claude-3-7-sonnet-20250219", None, None), ("anthropic.claude-3-sonnet-20240229-v1:0", None, None), # ( # "azure_ai/command-r-plus", @@ -512,7 +512,7 @@ async def test_anthropic_no_content_error(): try: litellm.drop_params = True response = await litellm.acompletion( - model="anthropic/claude-3-opus-20240229", + model="anthropic/claude-3-7-sonnet-20250219", api_key=os.getenv("ANTHROPIC_API_KEY"), messages=[ { @@ -630,7 +630,7 @@ def test_completion_claude_3_multi_turn_conversations(): ] try: response = completion( - model="anthropic/claude-3-opus-20240229", + model="anthropic/claude-3-7-sonnet-20250219", messages=messages, ) print(response) @@ -644,7 +644,7 @@ def test_completion_claude_3_stream(): try: # test without max tokens response = completion( - model="anthropic/claude-3-opus-20240229", + model="anthropic/claude-3-7-sonnet-20250219", messages=messages, max_tokens=10, stream=True, @@ -669,7 +669,7 @@ def encode_image(image_path): [ "gpt-4o", "azure/gpt-4.1-mini", - "anthropic/claude-3-opus-20240229", + "anthropic/claude-3-7-sonnet-20250219", ], ) # def test_completion_base64(model): diff --git a/tests/local_testing/test_streaming.py b/tests/local_testing/test_streaming.py index 0d9f84a301c..b9b5d0fdb07 100644 --- a/tests/local_testing/test_streaming.py +++ b/tests/local_testing/test_streaming.py @@ -1418,7 +1418,7 @@ def test_bedrock_claude_3_streaming(): @pytest.mark.parametrize( "model", [ - "claude-3-opus-20240229", + "claude-3-7-sonnet-20250219", "cohere.command-r-plus-v1:0", # bedrock "gpt-3.5-turbo", ], @@ -2914,7 +2914,7 @@ def test_completion_claude_3_function_call_with_streaming(): try: # test without max tokens response = completion( - model="claude-3-opus-20240229", + model="claude-3-7-sonnet-20250219", messages=messages, tools=tools, tool_choice="required", @@ -2946,7 +2946,7 @@ def test_completion_claude_3_function_call_with_streaming(): "model", [ "gemini/gemini-2.5-flash-lite", - ], # "claude-3-opus-20240229" + ], ) # @pytest.mark.asyncio async def test_acompletion_function_call_with_streaming(model):