diff --git a/tests/local_testing/test_streaming.py b/tests/local_testing/test_streaming.py index ef2f89cdaf5..56f0e5fe826 100644 --- a/tests/local_testing/test_streaming.py +++ b/tests/local_testing/test_streaming.py @@ -1029,7 +1029,7 @@ def test_completion_claude_stream_bad_key(): }, ] response = completion( - model="claude-3-5-haiku-20241022", + model="claude-haiku-4-5-20251001", messages=messages, stream=True, max_tokens=50, diff --git a/tests/local_testing/test_timeout.py b/tests/local_testing/test_timeout.py index 7f9837e81dd..bca299f817b 100644 --- a/tests/local_testing/test_timeout.py +++ b/tests/local_testing/test_timeout.py @@ -260,7 +260,7 @@ async def test_anthropic_timeout(streaming, sync_mode): try: if sync_mode: response = litellm.completion( - model="claude-3-5-sonnet-20240620", + model="claude-sonnet-4-5-20250929", timeout=0.01, messages=[{"role": "user", "content": "hello, write a 20 pg essay"}], stream=streaming, @@ -270,7 +270,7 @@ async def test_anthropic_timeout(streaming, sync_mode): pass else: response = await litellm.acompletion( - model="claude-3-5-sonnet-20240620", + model="claude-sonnet-4-5-20250929", timeout=0.01, messages=[{"role": "user", "content": "hello, write a 20 pg essay"}], stream=streaming, diff --git a/tests/logging_callback_tests/test_alerting.py b/tests/logging_callback_tests/test_alerting.py index 524cc00d5f7..f77cbcb4bb1 100644 --- a/tests/logging_callback_tests/test_alerting.py +++ b/tests/logging_callback_tests/test_alerting.py @@ -589,7 +589,7 @@ async def test_webhook_alerting(alerting_type): None, None, ), - ("gemini-pro", None, "vertex_ai", "hardy-device-38811", "us-central1"), + ("gemini-2.0-flash", None, "vertex_ai", "hardy-device-38811", "us-central1"), ], ) @pytest.mark.parametrize("error_code", [500, 408, 400]) @@ -695,7 +695,7 @@ async def test_outage_alerting_called( None, None, ), - ("gemini-pro", None, "vertex_ai", "hardy-device-38811", "us-central1"), + ("gemini-2.0-flash", None, "vertex_ai", "hardy-device-38811", "us-central1"), ], ) @pytest.mark.parametrize("error_code", [500, 408, 400]) @@ -782,7 +782,7 @@ async def test_region_outage_alerting_called( await slack_alerting.region_outage_alerts( exception=error_to_raise, deployment_id=deployment_id # type: ignore ) - if model == "gemini-pro" and (error_code == 500 or error_code == 408): + if model == "gemini-2.0-flash" and (error_code == 500 or error_code == 408): mock_send_alert.assert_called_once() else: mock_send_alert.assert_not_called()