diff --git a/tests/enterprise/litellm_enterprise/integrations/test_prometheus_unit_tests.py b/tests/enterprise/litellm_enterprise/integrations/test_prometheus_unit_tests.py index b0bd88b4e3..9d142beae1 100644 --- a/tests/enterprise/litellm_enterprise/integrations/test_prometheus_unit_tests.py +++ b/tests/enterprise/litellm_enterprise/integrations/test_prometheus_unit_tests.py @@ -166,7 +166,7 @@ async def test_prometheus_metric_tracking(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/litellm_utils_tests/test_health_check.py b/tests/litellm_utils_tests/test_health_check.py index 35eef1ed47..c7291c6ef1 100644 --- a/tests/litellm_utils_tests/test_health_check.py +++ b/tests/litellm_utils_tests/test_health_check.py @@ -20,7 +20,7 @@ import litellm async def test_azure_health_check(): response = await litellm.ahealth_check( model_params={ - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [{"role": "user", "content": "Hey, how's it going?"}], "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/llm_translation/test_azure_ai.py b/tests/llm_translation/test_azure_ai.py index b5499fc61f..c007fda547 100644 --- a/tests/llm_translation/test_azure_ai.py +++ b/tests/llm_translation/test_azure_ai.py @@ -322,7 +322,7 @@ def test_completion_azure(): litellm.set_verbose = False ## Test azure call response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ { "role": "user", diff --git a/tests/llm_translation/test_azure_openai.py b/tests/llm_translation/test_azure_openai.py index b9f20ffd25..b450da9939 100644 --- a/tests/llm_translation/test_azure_openai.py +++ b/tests/llm_translation/test_azure_openai.py @@ -137,7 +137,7 @@ def test_azure_extra_headers(input, call_type, header_value): func = image_generation data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_base": "https://openai-gpt-4-test-v-1.openai.azure.com", "api_version": "2023-07-01-preview", "api_key": "my-azure-api-key", @@ -339,7 +339,7 @@ def test_azure_gpt_4o_with_tool_call_and_response_format(api_version): with patch.object(client.chat.completions.with_raw_response, "create") as mock_post: response = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ { "role": "system", @@ -474,7 +474,7 @@ def test_azure_max_retries_0( try: completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hello world"}], max_retries=max_retries, stream=stream, @@ -502,7 +502,7 @@ async def test_async_azure_max_retries_0( try: await acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hello world"}], max_retries=max_retries, stream=stream, @@ -598,7 +598,7 @@ def test_azure_safety_result(): litellm._turn_on_debug() response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hello world"}], ) print(f"response: {response}") diff --git a/tests/local_testing/example_config_yaml/azure_config.yaml b/tests/local_testing/example_config_yaml/azure_config.yaml index a0300bd6d1..0a015aefde 100644 --- a/tests/local_testing/example_config_yaml/azure_config.yaml +++ b/tests/local_testing/example_config_yaml/azure_config.yaml @@ -1,7 +1,7 @@ model_list: - model_name: gpt-4-team1 litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: https://openai-gpt-4-test-v-1.openai.azure.com/ api_version: "2023-05-15" api_key: os.environ/AZURE_API_KEY diff --git a/tests/local_testing/test_acooldowns_router.py b/tests/local_testing/test_acooldowns_router.py index 79345b60b1..6c9067ac5c 100644 --- a/tests/local_testing/test_acooldowns_router.py +++ b/tests/local_testing/test_acooldowns_router.py @@ -26,7 +26,7 @@ model_list = [ { # list of model deployments "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -180,7 +180,7 @@ async def test_cooldown_same_model_name(sync_mode): model_ids.append(model["model_info"]["id"]) print("\n litellm model ids ", model_ids) - # example litellm_model_names ['azure/gpt-4.1-nano-ModelID-64321', 'azure/gpt-4.1-nano-ModelID-63960'] + # example litellm_model_names ['azure/gpt-4.1-mini-ModelID-64321', 'azure/gpt-4.1-mini-ModelID-63960'] assert ( model_ids[0] != model_ids[1] ) # ensure both models have a uuid added, and they have different names @@ -197,7 +197,7 @@ async def test_cooldown_same_model_name(sync_mode): model_ids.append(model["model_info"]["id"]) print("\n litellm model ids ", model_ids) - # example litellm_model_names ['azure/gpt-4.1-nano-ModelID-64321', 'azure/gpt-4.1-nano-ModelID-63960'] + # example litellm_model_names ['azure/gpt-4.1-mini-ModelID-64321', 'azure/gpt-4.1-mini-ModelID-63960'] assert ( model_ids[0] != model_ids[1] ) # ensure both models have a uuid added, and they have different names diff --git a/tests/local_testing/test_alangfuse.py b/tests/local_testing/test_alangfuse.py index c196e4a3b3..a20370135f 100644 --- a/tests/local_testing/test_alangfuse.py +++ b/tests/local_testing/test_alangfuse.py @@ -194,7 +194,7 @@ def create_async_task(**completion_kwargs): By default a standard set of arguments are used for the litellm.acompletion function. """ completion_args = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_version": "2024-02-01", "messages": [{"role": "user", "content": "This is a test"}], "max_tokens": 5, diff --git a/tests/local_testing/test_azure_openai.py b/tests/local_testing/test_azure_openai.py index 0c6147b584..13869f1adf 100644 --- a/tests/local_testing/test_azure_openai.py +++ b/tests/local_testing/test_azure_openai.py @@ -47,7 +47,7 @@ async def test_aaaaazure_tenant_id_auth(respx_mock: MockRouter): { "model_name": "gpt-3.5-turbo", "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_base": os.getenv("AZURE_API_BASE"), "tenant_id": os.getenv("AZURE_TENANT_ID"), "client_id": os.getenv("AZURE_CLIENT_ID"), diff --git a/tests/local_testing/test_azure_perf.py b/tests/local_testing/test_azure_perf.py index 0ec3718983..1e2d5cc4f7 100644 --- a/tests/local_testing/test_azure_perf.py +++ b/tests/local_testing/test_azure_perf.py @@ -18,7 +18,7 @@ # { # "model_name": "azure-test", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_base": os.getenv("AZURE_API_BASE"), # "api_version": os.getenv("AZURE_API_VERSION"), diff --git a/tests/local_testing/test_caching.py b/tests/local_testing/test_caching.py index 30bacfff8b..2b2c9853db 100644 --- a/tests/local_testing/test_caching.py +++ b/tests/local_testing/test_caching.py @@ -1226,7 +1226,7 @@ async def test_s3_cache_stream_azure(sync_mode): if sync_mode: response1 = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, max_tokens=40, temperature=1, @@ -1239,7 +1239,7 @@ async def test_s3_cache_stream_azure(sync_mode): print(response_1_content) else: response1 = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, max_tokens=40, temperature=1, @@ -1259,7 +1259,7 @@ async def test_s3_cache_stream_azure(sync_mode): if sync_mode: response2 = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, max_tokens=40, temperature=1, @@ -1272,7 +1272,7 @@ async def test_s3_cache_stream_azure(sync_mode): print(response_2_content) else: response2 = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, max_tokens=40, temperature=1, @@ -1335,7 +1335,7 @@ async def test_s3_cache_acompletion_azure(): print("s3 Cache: test for caching, streaming + completion") response1 = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, max_tokens=40, temperature=1, @@ -1345,7 +1345,7 @@ async def test_s3_cache_acompletion_azure(): time.sleep(2) response2 = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, max_tokens=40, temperature=1, diff --git a/tests/local_testing/test_caching_ssl.py b/tests/local_testing/test_caching_ssl.py index 574b8ccaea..523976f123 100644 --- a/tests/local_testing/test_caching_ssl.py +++ b/tests/local_testing/test_caching_ssl.py @@ -58,7 +58,7 @@ def test_caching_router(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_class.py b/tests/local_testing/test_class.py index b83a915770..e02f59a294 100644 --- a/tests/local_testing/test_class.py +++ b/tests/local_testing/test_class.py @@ -55,7 +55,7 @@ # # { # # "model_name": "gpt-3.5-turbo", # openai model name # # "litellm_params": { # params for litellm completion/embedding call -# # "model": "azure/gpt-4.1-nano", +# # "model": "azure/gpt-4.1-mini", # # "api_key": os.getenv("AZURE_API_KEY"), # # "api_version": os.getenv("AZURE_API_VERSION"), # # "api_base": os.getenv("AZURE_API_BASE"), @@ -93,7 +93,7 @@ # # { # # "model_name": "gpt-3.5-turbo", # openai model name # # "litellm_params": { # params for litellm completion/embedding call -# # "model": "azure/gpt-4.1-nano", +# # "model": "azure/gpt-4.1-mini", # # "api_key": os.getenv("AZURE_API_KEY"), # # "api_version": os.getenv("AZURE_API_VERSION"), # # "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_completion.py b/tests/local_testing/test_completion.py index d91306b020..9c6060c979 100644 --- a/tests/local_testing/test_completion.py +++ b/tests/local_testing/test_completion.py @@ -712,7 +712,7 @@ def encode_image(image_path): "model", [ "gpt-4o", - "azure/gpt-4.1-nano", + "azure/gpt-4.1-mini", "anthropic/claude-3-opus-20240229", ], ) # @@ -1746,7 +1746,7 @@ def test_completion_openai(): "model, api_version", [ # ("gpt-4o-2024-08-06", None), - # ("azure/gpt-4.1-nano", None), + # ("azure/gpt-4.1-mini", None), ("bedrock/anthropic.claude-3-sonnet-20240229-v1:0", None), # ("azure/gpt-4o-new-test", "2024-08-01-preview"), ], @@ -2417,7 +2417,7 @@ def test_completion_azure_extra_headers(): litellm.client_session = http_client try: response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, api_base=os.getenv("AZURE_API_BASE"), api_version="2023-07-01-preview", @@ -2466,7 +2466,7 @@ def test_completion_azure_ad_token(): litellm.client_session = http_client try: response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, azure_ad_token="my-special-token", ) @@ -2497,7 +2497,7 @@ def test_completion_azure_key_completion_arg(): litellm.set_verbose = True ## Test azure call response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, api_key=old_key, logprobs=True, @@ -2530,7 +2530,7 @@ async def test_re_use_azure_async_client(): ## Test azure call for _ in range(3): response = await litellm.acompletion( - model="azure/gpt-4.1-nano", messages=messages, client=client + model="azure/gpt-4.1-mini", messages=messages, client=client ) print(f"response: {response}") except Exception as e: @@ -2577,7 +2577,7 @@ def test_azure_openai_ad_token(): litellm.input_callback = [tester] try: response = litellm.completion( - model="azure/gpt-4.1-nano", # e.g. gpt-35-instant + model="azure/gpt-4.1-mini", # e.g. gpt-35-instant messages=[ { "role": "user", @@ -2615,7 +2615,7 @@ def test_completion_azure2(): ## Test azure call response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, api_base=api_base, api_key=api_key, @@ -2652,7 +2652,7 @@ def test_completion_azure3(): ## Test azure call response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, max_tokens=10, ) @@ -2700,7 +2700,7 @@ def test_completion_azure_with_litellm_key(): openai.api_key = "ymca" response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, ) # Add any assertions here to check the response @@ -4041,7 +4041,7 @@ async def test_completion_ai21_chat(): @pytest.mark.parametrize( "model", - ["gpt-4o", "azure/gpt-4.1-nano"], + ["gpt-4o", "azure/gpt-4.1-mini"], ) @pytest.mark.parametrize( "stream", @@ -4063,7 +4063,7 @@ def test_completion_response_ratelimit_headers(model, stream): assert "x-ratelimit-remaining-requests" in additional_headers assert "x-ratelimit-remaining-tokens" in additional_headers - if model == "azure/gpt-4.1-nano": + if model == "azure/gpt-4.1-mini": # Azure OpenAI header assert "llm_provider-azureml-model-session" in additional_headers if model == "claude-3-sonnet-20240229": diff --git a/tests/local_testing/test_config.py b/tests/local_testing/test_config.py index 5d8fae282c..e74f92ca7a 100644 --- a/tests/local_testing/test_config.py +++ b/tests/local_testing/test_config.py @@ -46,7 +46,7 @@ async def test_delete_deployment(): import base64 litellm_params = LiteLLM_Params( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", api_key=os.getenv("AZURE_API_KEY"), api_base=os.getenv("AZURE_API_BASE"), api_version=os.getenv("AZURE_API_VERSION"), @@ -232,7 +232,7 @@ async def test_db_error_new_model_check(): litellm_params = LiteLLM_Params( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", api_key=os.getenv("AZURE_API_KEY"), api_base=os.getenv("AZURE_API_BASE"), api_version=os.getenv("AZURE_API_VERSION"), @@ -250,7 +250,7 @@ def _create_model_list(flag_value: Literal[0, 1], master_key: str): import base64 new_litellm_params = LiteLLM_Params( - model="azure/gpt-4.1-nano-3", + model="azure/gpt-4.1-mini-3", api_key=os.getenv("AZURE_API_KEY"), api_base=os.getenv("AZURE_API_BASE"), api_version=os.getenv("AZURE_API_VERSION"), diff --git a/tests/local_testing/test_configs/test_bad_config.yaml b/tests/local_testing/test_configs/test_bad_config.yaml index ae699fdecb..4a70886a93 100644 --- a/tests/local_testing/test_configs/test_bad_config.yaml +++ b/tests/local_testing/test_configs/test_bad_config.yaml @@ -5,12 +5,12 @@ model_list: model: gpt-3.5-turbo - model_name: working-azure-gpt-3.5-turbo litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: os.environ/AZURE_API_BASE api_key: os.environ/AZURE_API_KEY - model_name: azure-gpt-3.5-turbo litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: os.environ/AZURE_API_BASE api_key: bad-key - model_name: azure-embedding diff --git a/tests/local_testing/test_configs/test_cloudflare_azure_with_cache_config.yaml b/tests/local_testing/test_configs/test_cloudflare_azure_with_cache_config.yaml index acb0785850..9902835618 100644 --- a/tests/local_testing/test_configs/test_cloudflare_azure_with_cache_config.yaml +++ b/tests/local_testing/test_configs/test_cloudflare_azure_with_cache_config.yaml @@ -1,7 +1,7 @@ model_list: - model_name: azure-cloudflare litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1 api_key: os.environ/AZURE_API_KEY api_version: 2023-07-01-preview diff --git a/tests/local_testing/test_configs/test_config_no_auth.yaml b/tests/local_testing/test_configs/test_config_no_auth.yaml index 1ddfee464f..cdc447a5ee 100644 --- a/tests/local_testing/test_configs/test_config_no_auth.yaml +++ b/tests/local_testing/test_configs/test_config_no_auth.yaml @@ -12,7 +12,7 @@ model_list: - litellm_params: api_base: https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1 api_key: os.environ/AZURE_API_KEY - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini model_name: azure-cloudflare-model - litellm_params: api_base: https://openai-france-1234.openai.azure.com diff --git a/tests/local_testing/test_configs/test_custom_logger.yaml b/tests/local_testing/test_configs/test_custom_logger.yaml index eb3d623f47..22bbfe42be 100644 --- a/tests/local_testing/test_configs/test_custom_logger.yaml +++ b/tests/local_testing/test_configs/test_custom_logger.yaml @@ -1,7 +1,7 @@ model_list: - model_name: Azure OpenAI GPT-4 Canada litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: os.environ/AZURE_API_BASE api_key: os.environ/AZURE_API_KEY api_version: "2023-07-01-preview" diff --git a/tests/local_testing/test_custom_callback_input.py b/tests/local_testing/test_custom_callback_input.py index b3c81b9906..e711344f65 100644 --- a/tests/local_testing/test_custom_callback_input.py +++ b/tests/local_testing/test_custom_callback_input.py @@ -450,12 +450,12 @@ def test_chat_azure_stream(): customHandler = CompletionCustomHandler() litellm.callbacks = [customHandler] response = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}], ) # test streaming response = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}], stream=True, ) @@ -464,7 +464,7 @@ def test_chat_azure_stream(): # test failure callback try: response = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}], api_key="my-bad-key", stream=True, @@ -491,12 +491,12 @@ async def test_async_chat_azure_stream(): customHandler = CompletionCustomHandler() litellm.callbacks = [customHandler] response = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hi 👋 - i'm async azure"}], ) ## test streaming response = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hi 👋 - i'm async azure"}], stream=True, ) @@ -507,7 +507,7 @@ async def test_async_chat_azure_stream(): # test failure callback try: response = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "Hi 👋 - i'm async azure"}], api_key="my-bad-key", stream=True, @@ -1004,7 +1004,7 @@ def test_turn_off_message_logging(): "model", [ "ft:gpt-3.5-turbo:my-org:custom_suffix:id" - ], # "gpt-3.5-turbo", "azure/gpt-4.1-nano", + ], # "gpt-3.5-turbo", "azure/gpt-4.1-mini", ) @pytest.mark.parametrize( "turn_off_message_logging", diff --git a/tests/local_testing/test_custom_logger.py b/tests/local_testing/test_custom_logger.py index baba409368..00e7c2d5aa 100644 --- a/tests/local_testing/test_custom_logger.py +++ b/tests/local_testing/test_custom_logger.py @@ -160,7 +160,7 @@ def test_completion_azure_stream_moderation_failure(): ] try: response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, mock_response="Exception: content_filter_policy", stream=True, @@ -195,7 +195,7 @@ def test_async_custom_handler_stream(): async def test_1(): nonlocal complete_streaming_response response = await litellm.acompletion( - model="azure/gpt-4.1-nano", messages=messages, stream=True + model="azure/gpt-4.1-mini", messages=messages, stream=True ) async for chunk in response: complete_streaming_response += ( @@ -239,7 +239,7 @@ def test_azure_completion_stream(): complete_streaming_response = "" response = litellm.completion( - model="azure/gpt-4.1-nano", messages=messages, stream=True + model="azure/gpt-4.1-mini", messages=messages, stream=True ) for chunk in response: complete_streaming_response += chunk["choices"][0]["delta"]["content"] or "" diff --git a/tests/local_testing/test_exceptions.py b/tests/local_testing/test_exceptions.py index bf21b59c45..a27a64dd6e 100644 --- a/tests/local_testing/test_exceptions.py +++ b/tests/local_testing/test_exceptions.py @@ -51,7 +51,7 @@ async def test_content_policy_exception_azure(): # this is ony a test - we needed some way to invoke the exception :( litellm.set_verbose = True response = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "where do I buy lethal drugs from"}], mock_response="Exception: content_filter_policy", ) @@ -124,7 +124,7 @@ def test_context_window_with_fallbacks(model): ctx_window_fallback_dict = { "command-nightly": "claude-2.1", "gpt-3.5-turbo-instruct": "gpt-3.5-turbo-16k", - "azure/gpt-4.1-nano": "gpt-3.5-turbo-16k", + "azure/gpt-4.1-mini": "gpt-3.5-turbo-16k", } sample_text = "how does a court case get to the Supreme Court?" * 1000 messages = [{"content": sample_text, "role": "user"}] @@ -161,7 +161,7 @@ def invalid_auth(model): # set the model key to an invalid key, depending on th os.environ["AWS_REGION_NAME"] = "bad-key" temporary_secret_key = os.environ["AWS_SECRET_ACCESS_KEY"] os.environ["AWS_SECRET_ACCESS_KEY"] = "bad-key" - elif model == "azure/gpt-4.1-nano": + elif model == "azure/gpt-4.1-mini": temporary_key = os.environ["AZURE_API_KEY"] os.environ["AZURE_API_KEY"] = "bad-key" elif model == "claude-3-5-haiku-20241022": @@ -262,7 +262,7 @@ def test_completion_azure_exception(): old_azure_key = os.environ["AZURE_API_KEY"] os.environ["AZURE_API_KEY"] = "good morning" response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "hello"}], ) os.environ["AZURE_API_KEY"] = old_azure_key @@ -306,7 +306,7 @@ async def asynctest_completion_azure_exception(): old_azure_key = os.environ["AZURE_API_KEY"] os.environ["AZURE_API_KEY"] = "good morning" response = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "hello"}], ) print(f"response: {response}") @@ -525,7 +525,7 @@ def test_content_policy_violation_error_streaming(): async def test_get_response(): try: response = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "say 1"}], temperature=0, top_p=1, @@ -554,7 +554,7 @@ def test_content_policy_violation_error_streaming(): async def test_get_error(): try: response = await litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ {"role": "user", "content": "where do i buy lethal drugs from"} ], @@ -751,7 +751,7 @@ def test_litellm_predibase_exception(): # return False # # Repeat each model 500 times # # extended_models = [model for model in models for _ in range(250)] -# extended_models = ["azure/gpt-4.1-nano" for _ in range(250)] +# extended_models = ["azure/gpt-4.1-mini" for _ in range(250)] # def worker(model): # return test_model_call(model) @@ -1023,7 +1023,7 @@ def _pre_call_utils_httpx( ("openai", "gpt-3.5-turbo", "chat_completion", False), ("openai", "gpt-3.5-turbo", "chat_completion", True), ("openai", "gpt-3.5-turbo-instruct", "completion", True), - ("azure", "azure/gpt-4.1-nano", "chat_completion", True), + ("azure", "azure/gpt-4.1-mini", "chat_completion", True), ("azure", "azure/text-embedding-ada-002", "embedding", True), ("azure", "azure_text/gpt-3.5-turbo-instruct", "completion", True), ], @@ -1298,7 +1298,7 @@ async def test_exception_with_headers_httpx( @pytest.mark.asyncio -@pytest.mark.parametrize("model", ["azure/gpt-4.1-nano", "openai/gpt-3.5-turbo"]) +@pytest.mark.parametrize("model", ["azure/gpt-4.1-mini", "openai/gpt-3.5-turbo"]) async def test_bad_request_error_contains_httpx_response(model): """ Test that the BadRequestError contains the httpx response diff --git a/tests/local_testing/test_gcs_bucket.py b/tests/local_testing/test_gcs_bucket.py index 284efce528..b3eaf4d9ca 100644 --- a/tests/local_testing/test_gcs_bucket.py +++ b/tests/local_testing/test_gcs_bucket.py @@ -108,7 +108,7 @@ async def test_aaabasic_gcs_logger(): }, "endpoint": "http://localhost:4000/chat/completions", "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", "model_info": { "id": "4bad40a1eb6bebd1682800f16f44b9f06c52a6703444c99c7f9f32e9de3693b4", "db_model": False, @@ -216,7 +216,7 @@ async def test_basic_gcs_logger_failure(): }, "endpoint": "http://localhost:4000/chat/completions", "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", "model_info": { "id": "4bad40a1eb6bebd1682800f16f44b9f06c52a6703444c99c7f9f32e9de3693b4", "db_model": False, @@ -626,7 +626,7 @@ async def test_basic_gcs_logger_with_folder_in_bucket_name(): }, "endpoint": "http://localhost:4000/chat/completions", "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", "model_info": { "id": "4bad40a1eb6bebd1682800f16f44b9f06c52a6703444c99c7f9f32e9de3693b4", "db_model": False, diff --git a/tests/local_testing/test_helicone_integration.py b/tests/local_testing/test_helicone_integration.py index d825026ef4..ad8fe92d1e 100644 --- a/tests/local_testing/test_helicone_integration.py +++ b/tests/local_testing/test_helicone_integration.py @@ -78,7 +78,7 @@ async def make_async_calls(metadata=None, **completion_kwargs): def create_async_task(**completion_kwargs): completion_args = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_version": "2024-02-01", "messages": [{"role": "user", "content": "This is a test"}], "max_tokens": 5, diff --git a/tests/local_testing/test_least_busy_routing.py b/tests/local_testing/test_least_busy_routing.py index b30c4f3943..479b805aaa 100644 --- a/tests/local_testing/test_least_busy_routing.py +++ b/tests/local_testing/test_least_busy_routing.py @@ -33,7 +33,7 @@ def test_model_added(): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": "1234"}, } @@ -47,7 +47,7 @@ def test_get_available_deployments(): test_cache = DualCache() least_busy_logger = LeastBusyLoggingHandler(router_cache=test_cache) model_group = "gpt-3.5-turbo" - deployment = "azure/gpt-4.1-nano" + deployment = "azure/gpt-4.1-mini" kwargs = { "litellm_params": { "metadata": { @@ -113,7 +113,7 @@ async def test_router_get_available_deployments(async_test): router.leastbusy_logger.test_flag = True model_group = "azure-model" - deployment = "azure/gpt-4.1-nano" + deployment = "azure/gpt-4.1-mini" request_count_dict = {1: 10, 2: 54, 3: 100} cache_key = f"{model_group}_request_count" if async_test is True: diff --git a/tests/local_testing/test_load_test_router_s3.py b/tests/local_testing/test_load_test_router_s3.py index 6b0b605061..70a4e873b6 100644 --- a/tests/local_testing/test_load_test_router_s3.py +++ b/tests/local_testing/test_load_test_router_s3.py @@ -46,7 +46,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_base": os.getenv("AZURE_API_BASE"), # "api_version": os.getenv("AZURE_API_VERSION"), diff --git a/tests/local_testing/test_loadtest_router.py b/tests/local_testing/test_loadtest_router.py index 14f6cf627a..3f6e4af4fb 100644 --- a/tests/local_testing/test_loadtest_router.py +++ b/tests/local_testing/test_loadtest_router.py @@ -38,7 +38,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_base": os.getenv("AZURE_API_BASE"), # "api_version": os.getenv("AZURE_API_VERSION"), diff --git a/tests/local_testing/test_lowest_cost_routing.py b/tests/local_testing/test_lowest_cost_routing.py index 3ae123e587..17978133f9 100644 --- a/tests/local_testing/test_lowest_cost_routing.py +++ b/tests/local_testing/test_lowest_cost_routing.py @@ -60,7 +60,7 @@ async def test_get_available_deployments_custom_price(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00003, }, diff --git a/tests/local_testing/test_lowest_latency_routing.py b/tests/local_testing/test_lowest_latency_routing.py index bb2c02caca..429aae88b8 100644 --- a/tests/local_testing/test_lowest_latency_routing.py +++ b/tests/local_testing/test_lowest_latency_routing.py @@ -47,7 +47,7 @@ async def test_latency_memory_leak(sync_mode): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } @@ -128,7 +128,7 @@ def test_latency_updated(): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } @@ -171,7 +171,7 @@ def test_latency_updated_custom_ttl(): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } @@ -198,12 +198,12 @@ def test_get_available_deployments(): model_list = [ { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "1234"}, }, { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "5678"}, }, ] @@ -217,7 +217,7 @@ def test_get_available_deployments(): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } @@ -238,7 +238,7 @@ def test_get_available_deployments(): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } @@ -273,7 +273,7 @@ async def _deploy(lowest_latency_logger, deployment_id, tokens_used, duration): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } @@ -315,12 +315,12 @@ def test_get_available_endpoints_tpm_rpm_check_async(ans_rpm): model_list = [ { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "1234", "rpm": ans_rpm}, }, { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "5678", "rpm": non_ans_rpm}, }, ] @@ -364,12 +364,12 @@ def test_get_available_endpoints_tpm_rpm_check(ans_rpm): model_list = [ { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "1234", "rpm": ans_rpm}, }, { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "5678", "rpm": non_ans_rpm}, }, ] @@ -383,7 +383,7 @@ def test_get_available_endpoints_tpm_rpm_check(ans_rpm): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } @@ -405,7 +405,7 @@ def test_get_available_endpoints_tpm_rpm_check(ans_rpm): "litellm_params": { "metadata": { "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", }, "model_info": {"id": deployment_id}, } diff --git a/tests/local_testing/test_mem_usage.py b/tests/local_testing/test_mem_usage.py index 85ecd56878..927ebc4ae4 100644 --- a/tests/local_testing/test_mem_usage.py +++ b/tests/local_testing/test_mem_usage.py @@ -29,7 +29,7 @@ # { # "model_name": "gpt-3.5-turbo", # openai model name # "litellm_params": { # params for litellm completion/embedding call -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), @@ -40,7 +40,7 @@ # { # "model_name": "bad-model", # openai model name # "litellm_params": { # params for litellm completion/embedding call -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": "bad-key", # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_prompt_injection_detection.py b/tests/local_testing/test_prompt_injection_detection.py index b438ebad7f..c4cc4cde32 100644 --- a/tests/local_testing/test_prompt_injection_detection.py +++ b/tests/local_testing/test_prompt_injection_detection.py @@ -107,7 +107,7 @@ async def test_prompt_injection_llm_eval(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_provider_specific_config.py b/tests/local_testing/test_provider_specific_config.py index f4df8995a9..412457960a 100644 --- a/tests/local_testing/test_provider_specific_config.py +++ b/tests/local_testing/test_provider_specific_config.py @@ -729,7 +729,7 @@ def azure_openai_test_completion(): try: # OVERRIDE WITH DYNAMIC MAX TOKENS response_1 = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ { "content": "Hello, how are you? Be as verbose as possible", @@ -743,7 +743,7 @@ def azure_openai_test_completion(): # USE CONFIG TOKENS response_2 = litellm.completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ { "content": "Hello, how are you? Be as verbose as possible", diff --git a/tests/local_testing/test_router.py b/tests/local_testing/test_router.py index a433ea500a..fc60207bb2 100644 --- a/tests/local_testing/test_router.py +++ b/tests/local_testing/test_router.py @@ -266,7 +266,7 @@ def test_router_sensitive_keys(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "special-key", }, "model_info": {"id": 12345}, @@ -415,7 +415,7 @@ def test_exception_raising(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -527,7 +527,7 @@ def test_reading_key_from_model_list(): def test_call_one_endpoint(): # [PROD TEST CASE] # user passes one deployment they want to call on the router, we call the specified one - # this test makes a completion calls azure/gpt-4.1-nano, it should work + # this test makes a completion calls azure/gpt-4.1-mini, it should work try: print("Testing calling a specific deployment") old_api_key = os.environ["AZURE_API_KEY"] @@ -536,7 +536,7 @@ def test_call_one_endpoint(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": old_api_key, "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -566,7 +566,7 @@ def test_call_one_endpoint(): async def call_azure_completion(): response = await router.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "hello this request will pass"}], specific_deployment=True, ) @@ -612,7 +612,7 @@ def test_router_azure_acompletion(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": old_api_key, "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -785,7 +785,7 @@ def test_router_context_window_check_pre_call_check_in_group_custom_model_info() { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -839,7 +839,7 @@ def test_router_context_window_check_pre_call_check(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -893,7 +893,7 @@ def test_router_context_window_check_pre_call_check_out_group(): { "model_name": "gpt-3.5-turbo-small", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -972,7 +972,7 @@ def test_router_region_pre_call_check(allowed_model_region): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -2572,7 +2572,7 @@ def test_is_team_specific_model(): # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_base": os.getenv("AZURE_API_BASE"), # "tpm": 100000, @@ -2582,7 +2582,7 @@ def test_is_team_specific_model(): # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_base": os.getenv("AZURE_API_BASE"), # "tpm": 500, diff --git a/tests/local_testing/test_router_budget_limiter.py b/tests/local_testing/test_router_budget_limiter.py index 3242e997ae..c78bf2bee6 100644 --- a/tests/local_testing/test_router_budget_limiter.py +++ b/tests/local_testing/test_router_budget_limiter.py @@ -74,7 +74,7 @@ async def test_provider_budgets_e2e_test(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_router_caching.py b/tests/local_testing/test_router_caching.py index 52fc5b8858..6fc220bf72 100644 --- a/tests/local_testing/test_router_caching.py +++ b/tests/local_testing/test_router_caching.py @@ -267,7 +267,7 @@ async def test_acompletion_caching_on_router_caching_groups(): { "model_name": "azure-gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), diff --git a/tests/local_testing/test_router_client_init.py b/tests/local_testing/test_router_client_init.py index a0a274911d..34425d4b03 100644 --- a/tests/local_testing/test_router_client_init.py +++ b/tests/local_testing/test_router_client_init.py @@ -43,7 +43,7 @@ async def test_router_init(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), diff --git a/tests/local_testing/test_router_cooldown_handlers.py b/tests/local_testing/test_router_cooldown_handlers.py index 7d3fdda22c..131c5d9fe0 100644 --- a/tests/local_testing/test_router_cooldown_handlers.py +++ b/tests/local_testing/test_router_cooldown_handlers.py @@ -44,7 +44,7 @@ async def test_cooldown_badrequest_error(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_router_debug_logs.py b/tests/local_testing/test_router_debug_logs.py index 9b12aa13f0..0ccbf5ab0a 100644 --- a/tests/local_testing/test_router_debug_logs.py +++ b/tests/local_testing/test_router_debug_logs.py @@ -33,7 +33,7 @@ def test_async_fallbacks(caplog): { "model_name": "azure/gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -93,7 +93,7 @@ def test_async_fallbacks(caplog): # - error request, falling back notice, success notice expected_logs = [ "Falling back to model_group = azure/gpt-3.5-turbo", - "litellm.acompletion(model=azure/gpt-4.1-nano)\x1b[32m 200 OK\x1b[0m", + "litellm.acompletion(model=azure/gpt-4.1-mini)\x1b[32m 200 OK\x1b[0m", "Successful fallback b/w models.", ] diff --git a/tests/local_testing/test_router_fallbacks.py b/tests/local_testing/test_router_fallbacks.py index 52c37f4cb6..ffa41bfddf 100644 --- a/tests/local_testing/test_router_fallbacks.py +++ b/tests/local_testing/test_router_fallbacks.py @@ -67,7 +67,7 @@ def test_sync_fallbacks(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -78,7 +78,7 @@ def test_sync_fallbacks(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo-context-fallback", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -150,7 +150,7 @@ async def test_async_fallbacks(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -161,7 +161,7 @@ async def test_async_fallbacks(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo-context-fallback", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -345,7 +345,7 @@ def test_dynamic_fallbacks_sync(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -356,7 +356,7 @@ def test_dynamic_fallbacks_sync(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo-context-fallback", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -422,7 +422,7 @@ async def test_dynamic_fallbacks_async(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -433,7 +433,7 @@ async def test_dynamic_fallbacks_async(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo-context-fallback", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -505,7 +505,7 @@ async def test_async_fallbacks_streaming(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -516,7 +516,7 @@ async def test_async_fallbacks_streaming(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo-context-fallback", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -590,7 +590,7 @@ def test_sync_fallbacks_streaming(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -601,7 +601,7 @@ def test_sync_fallbacks_streaming(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo-context-fallback", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -671,7 +671,7 @@ async def test_async_fallbacks_max_retries_per_request(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -682,7 +682,7 @@ async def test_async_fallbacks_max_retries_per_request(): { # list of model deployments "model_name": "azure/gpt-3.5-turbo-context-fallback", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -885,7 +885,7 @@ def test_custom_cooldown_times(): { # list of model deployments "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -895,7 +895,7 @@ def test_custom_cooldown_times(): { # list of model deployments "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_router_get_deployments.py b/tests/local_testing/test_router_get_deployments.py index 7fda8a2be2..358ed74f55 100644 --- a/tests/local_testing/test_router_get_deployments.py +++ b/tests/local_testing/test_router_get_deployments.py @@ -41,7 +41,7 @@ def test_weighted_selection_router(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), @@ -54,7 +54,7 @@ def test_weighted_selection_router(): ) selection_counts = defaultdict(int) - # call get_available_deployment 1k times, it should pick azure/gpt-4.1-nano about 90% of the time + # call get_available_deployment 1k times, it should pick azure/gpt-4.1-mini about 90% of the time for _ in range(1000): selected_model = router.get_available_deployment("gpt-3.5-turbo") selected_model_id = selected_model["litellm_params"]["model"] @@ -64,10 +64,10 @@ def test_weighted_selection_router(): total_requests = sum(selection_counts.values()) - # Assert that 'azure/gpt-4.1-nano' has about 90% of the total requests + # Assert that 'azure/gpt-4.1-mini' has about 90% of the total requests assert ( - selection_counts["azure/gpt-4.1-nano"] / total_requests > 0.89 - ), f"Assertion failed: 'azure/gpt-4.1-nano' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" + selection_counts["azure/gpt-4.1-mini"] / total_requests > 0.89 + ), f"Assertion failed: 'azure/gpt-4.1-mini' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" router.reset() except Exception as e: @@ -97,7 +97,7 @@ def test_weighted_selection_router_tpm(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), @@ -110,7 +110,7 @@ def test_weighted_selection_router_tpm(): ) selection_counts = defaultdict(int) - # call get_available_deployment 1k times, it should pick azure/gpt-4.1-nano about 90% of the time + # call get_available_deployment 1k times, it should pick azure/gpt-4.1-mini about 90% of the time for _ in range(1000): selected_model = router.get_available_deployment("gpt-3.5-turbo") selected_model_id = selected_model["litellm_params"]["model"] @@ -120,10 +120,10 @@ def test_weighted_selection_router_tpm(): total_requests = sum(selection_counts.values()) - # Assert that 'azure/gpt-4.1-nano' has about 90% of the total requests + # Assert that 'azure/gpt-4.1-mini' has about 90% of the total requests assert ( - selection_counts["azure/gpt-4.1-nano"] / total_requests > 0.89 - ), f"Assertion failed: 'azure/gpt-4.1-nano' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" + selection_counts["azure/gpt-4.1-mini"] / total_requests > 0.89 + ), f"Assertion failed: 'azure/gpt-4.1-mini' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" router.reset() except Exception as e: @@ -153,7 +153,7 @@ def test_weighted_selection_router_tpm_as_router_param(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), @@ -166,7 +166,7 @@ def test_weighted_selection_router_tpm_as_router_param(): ) selection_counts = defaultdict(int) - # call get_available_deployment 1k times, it should pick azure/gpt-4.1-nano about 90% of the time + # call get_available_deployment 1k times, it should pick azure/gpt-4.1-mini about 90% of the time for _ in range(1000): selected_model = router.get_available_deployment("gpt-3.5-turbo") selected_model_id = selected_model["litellm_params"]["model"] @@ -176,10 +176,10 @@ def test_weighted_selection_router_tpm_as_router_param(): total_requests = sum(selection_counts.values()) - # Assert that 'azure/gpt-4.1-nano' has about 90% of the total requests + # Assert that 'azure/gpt-4.1-mini' has about 90% of the total requests assert ( - selection_counts["azure/gpt-4.1-nano"] / total_requests > 0.89 - ), f"Assertion failed: 'azure/gpt-4.1-nano' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" + selection_counts["azure/gpt-4.1-mini"] / total_requests > 0.89 + ), f"Assertion failed: 'azure/gpt-4.1-mini' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" router.reset() except Exception as e: @@ -210,7 +210,7 @@ def test_weighted_selection_router_rpm_as_router_param(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), @@ -224,7 +224,7 @@ def test_weighted_selection_router_rpm_as_router_param(): ) selection_counts = defaultdict(int) - # call get_available_deployment 1k times, it should pick azure/gpt-4.1-nano about 90% of the time + # call get_available_deployment 1k times, it should pick azure/gpt-4.1-mini about 90% of the time for _ in range(1000): selected_model = router.get_available_deployment("gpt-3.5-turbo") selected_model_id = selected_model["litellm_params"]["model"] @@ -234,10 +234,10 @@ def test_weighted_selection_router_rpm_as_router_param(): total_requests = sum(selection_counts.values()) - # Assert that 'azure/gpt-4.1-nano' has about 90% of the total requests + # Assert that 'azure/gpt-4.1-mini' has about 90% of the total requests assert ( - selection_counts["azure/gpt-4.1-nano"] / total_requests > 0.89 - ), f"Assertion failed: 'azure/gpt-4.1-nano' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" + selection_counts["azure/gpt-4.1-mini"] / total_requests > 0.89 + ), f"Assertion failed: 'azure/gpt-4.1-mini' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" router.reset() except Exception as e: @@ -266,7 +266,7 @@ def test_weighted_selection_router_no_rpm_set(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), @@ -286,7 +286,7 @@ def test_weighted_selection_router_no_rpm_set(): ) selection_counts = defaultdict(int) - # call get_available_deployment 1k times, it should pick azure/gpt-4.1-nano about 90% of the time + # call get_available_deployment 1k times, it should pick azure/gpt-4.1-mini about 90% of the time for _ in range(1000): selected_model = router.get_available_deployment("claude-1") selected_model_id = selected_model["litellm_params"]["model"] @@ -296,7 +296,7 @@ def test_weighted_selection_router_no_rpm_set(): total_requests = sum(selection_counts.values()) - # Assert that 'azure/gpt-4.1-nano' has about 90% of the total requests + # Assert that 'azure/gpt-4.1-mini' has about 90% of the total requests assert ( selection_counts["bedrock/claude1.2"] / total_requests == 1 ), f"Assertion failed: Selection counts {selection_counts}" @@ -325,7 +325,7 @@ def test_model_group_aliases(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), @@ -358,7 +358,7 @@ def test_model_group_aliases(): ) # test that - # call get_available_deployment 1k times, it should pick azure/gpt-4.1-nano about 90% of the time + # call get_available_deployment 1k times, it should pick azure/gpt-4.1-mini about 90% of the time selection_counts = defaultdict(int) for _ in range(1000): selected_model = router.get_available_deployment("gpt-3.5-turbo") @@ -369,10 +369,10 @@ def test_model_group_aliases(): total_requests = sum(selection_counts.values()) - # Assert that 'azure/gpt-4.1-nano' has about 90% of the total requests + # Assert that 'azure/gpt-4.1-mini' has about 90% of the total requests assert ( - selection_counts["azure/gpt-4.1-nano"] / total_requests > 0.89 - ), f"Assertion failed: 'azure/gpt-4.1-nano' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" + selection_counts["azure/gpt-4.1-mini"] / total_requests > 0.89 + ), f"Assertion failed: 'azure/gpt-4.1-mini' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" router.reset() except Exception as e: @@ -553,7 +553,7 @@ async def test_weighted_selection_router_async(rpm_list, tpm_list): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "api_version": os.getenv("AZURE_API_VERSION"), @@ -567,7 +567,7 @@ async def test_weighted_selection_router_async(rpm_list, tpm_list): ) selection_counts = defaultdict(int) - # call get_available_deployment 1k times, it should pick azure/gpt-4.1-nano about 90% of the time + # call get_available_deployment 1k times, it should pick azure/gpt-4.1-mini about 90% of the time for _ in range(1000): selected_model = await router.async_get_available_deployment( "gpt-3.5-turbo", request_kwargs={} @@ -580,13 +580,13 @@ async def test_weighted_selection_router_async(rpm_list, tpm_list): total_requests = sum(selection_counts.values()) if rpm_list[0] is not None or tpm_list[0] is not None: - # Assert that 'azure/gpt-4.1-nano' has about 90% of the total requests + # Assert that 'azure/gpt-4.1-mini' has about 90% of the total requests assert ( - selection_counts["azure/gpt-4.1-nano"] / total_requests > 0.89 - ), f"Assertion failed: 'azure/gpt-4.1-nano' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" + selection_counts["azure/gpt-4.1-mini"] / total_requests > 0.89 + ), f"Assertion failed: 'azure/gpt-4.1-mini' does not have about 90% of the total requests in the weighted load balancer. Selection counts {selection_counts}" else: # Assert both are used - assert selection_counts["azure/gpt-4.1-nano"] > 0 + assert selection_counts["azure/gpt-4.1-mini"] > 0 assert selection_counts["gpt-3.5-turbo"] > 0 router.reset() except Exception as e: diff --git a/tests/local_testing/test_router_init.py b/tests/local_testing/test_router_init.py index 1c7ab45908..e232ff105d 100644 --- a/tests/local_testing/test_router_init.py +++ b/tests/local_testing/test_router_init.py @@ -40,7 +40,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), @@ -96,7 +96,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), @@ -134,7 +134,7 @@ # { # "model_name": "azure-cloudflare", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": "https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1", @@ -201,7 +201,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), @@ -254,7 +254,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), @@ -615,7 +615,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), @@ -660,7 +660,7 @@ # { # "model_name": "gpt-3.5-turbo", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_version": os.getenv("AZURE_API_VERSION"), # "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_router_retries.py b/tests/local_testing/test_router_retries.py index 9246ea1801..789e5e9b35 100644 --- a/tests/local_testing/test_router_retries.py +++ b/tests/local_testing/test_router_retries.py @@ -166,7 +166,7 @@ async def test_router_retry_policy(error_type): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -175,7 +175,7 @@ async def test_router_retry_policy(error_type): { "model_name": "bad-model", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -275,7 +275,7 @@ async def test_dynamic_router_retry_policy(model_group): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -287,7 +287,7 @@ async def test_dynamic_router_retry_policy(model_group): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -299,7 +299,7 @@ async def test_dynamic_router_retry_policy(model_group): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -311,7 +311,7 @@ async def test_dynamic_router_retry_policy(model_group): { "model_name": "bad-model", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -393,7 +393,7 @@ def test_retry_rate_limit_error_with_healthy_deployments(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -426,7 +426,7 @@ def test_do_retry_rate_limit_error_with_no_fallbacks_and_no_healthy_deployments( { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -459,14 +459,14 @@ def test_raise_context_window_exceeded_error(): llm_provider="azure", model="gpt-3.5-turbo", ) - context_window_fallbacks = [{"gpt-3.5-turbo": ["azure/gpt-4.1-nano"]}] + context_window_fallbacks = [{"gpt-3.5-turbo": ["azure/gpt-4.1-mini"]}] router = Router( model_list=[ { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -508,7 +508,7 @@ def test_raise_context_window_exceeded_error_no_retry(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -562,7 +562,7 @@ def test_timeout_for_rate_limit_error_with_healthy_deployments( { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -589,7 +589,7 @@ def test_timeout_for_rate_limit_error_with_healthy_deployments( "litellm_params": { "api_key": "my-key", "api_base": "https://openai-gpt-4-test-v-1.openai.azure.com", - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", }, "model_info": { "id": "0e30bc8a63fa91ae4415d4234e231b3f9e6dd900cac57d118ce13a720d95e9d6", @@ -615,7 +615,7 @@ def test_timeout_for_rate_limit_error_with_no_healthy_deployments(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -650,7 +650,7 @@ def test_no_retry_for_not_found_error_404(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -709,7 +709,7 @@ def test_no_retry_when_no_healthy_deployments(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_router_timeout.py b/tests/local_testing/test_router_timeout.py index 7a04db1b3b..100c01fcdb 100644 --- a/tests/local_testing/test_router_timeout.py +++ b/tests/local_testing/test_router_timeout.py @@ -30,7 +30,7 @@ def test_router_timeouts(): { "model_name": "openai-gpt-4", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "os.environ/AZURE_API_KEY", "api_base": "os.environ/AZURE_API_BASE", "api_version": "os.environ/AZURE_API_VERSION", diff --git a/tests/local_testing/test_router_utils.py b/tests/local_testing/test_router_utils.py index e27588babc..09ed29b7ba 100644 --- a/tests/local_testing/test_router_utils.py +++ b/tests/local_testing/test_router_utils.py @@ -32,7 +32,7 @@ def test_returned_settings(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -96,7 +96,7 @@ def test_update_kwargs_before_fallbacks_unit_test(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -133,7 +133,7 @@ async def test_update_kwargs_before_fallbacks(call_type): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/local_testing/test_streaming.py b/tests/local_testing/test_streaming.py index 0520c464df..34ab0ad728 100644 --- a/tests/local_testing/test_streaming.py +++ b/tests/local_testing/test_streaming.py @@ -243,7 +243,7 @@ tools_schema = [ def test_completion_azure_stream_special_char(): litellm.set_verbose = True messages = [{"role": "user", "content": "hi. respond with the tag only"}] - response = completion(model="azure/gpt-4.1-nano", messages=messages, stream=True) + response = completion(model="azure/gpt-4.1-mini", messages=messages, stream=True) response_str = "" for part in response: response_str += part.choices[0].delta.content or "" @@ -451,7 +451,7 @@ def test_completion_azure_stream(): }, ] response = completion( - model="azure/gpt-4.1-nano", messages=messages, stream=True, max_tokens=50 + model="azure/gpt-4.1-mini", messages=messages, stream=True, max_tokens=50 ) complete_response = "" # Add any assertions here to check the response @@ -589,7 +589,7 @@ def test_completion_azure_function_calling_stream(): user_message = "What is the current weather in Boston?" messages = [{"content": user_message, "role": "user"}] response = completion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=messages, stream=True, tools=tools_schema, @@ -1952,7 +1952,7 @@ def test_openai_chat_completion_complete_response_call(): "model", [ "gpt-3.5-turbo", - "azure/gpt-4.1-nano", + "azure/gpt-4.1-mini", "claude-3-haiku-20240307", "o1", ], diff --git a/tests/local_testing/test_timeout.py b/tests/local_testing/test_timeout.py index 92f6435ea9..7f9837e81d 100644 --- a/tests/local_testing/test_timeout.py +++ b/tests/local_testing/test_timeout.py @@ -22,7 +22,7 @@ import litellm "model, provider", [ ("gpt-3.5-turbo", "openai"), - ("azure/gpt-4.1-nano", "azure"), + ("azure/gpt-4.1-mini", "azure"), ], ) @pytest.mark.parametrize("sync_mode", [True, False]) @@ -157,7 +157,7 @@ def test_hanging_request_openai(): { "model_name": "azure-gpt", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_base": os.environ["AZURE_API_BASE"], "api_key": os.environ["AZURE_API_KEY"], }, diff --git a/tests/local_testing/test_tpm_rpm_routing_v2.py b/tests/local_testing/test_tpm_rpm_routing_v2.py index a418cd5b0e..a3218bc987 100644 --- a/tests/local_testing/test_tpm_rpm_routing_v2.py +++ b/tests/local_testing/test_tpm_rpm_routing_v2.py @@ -44,7 +44,7 @@ def test_tpm_rpm_updated(): ) model_group = "gpt-3.5-turbo" deployment_id = "1234" - deployment = "azure/gpt-4.1-nano" + deployment = "azure/gpt-4.1-mini" total_tokens = 50 standard_logging_payload: StandardLoggingPayload = create_standard_logging_payload() standard_logging_payload["model_group"] = model_group @@ -99,12 +99,12 @@ def test_get_available_deployments(): model_list = [ { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "1234"}, }, { "model_name": "gpt-3.5-turbo", - "litellm_params": {"model": "azure/gpt-4.1-nano"}, + "litellm_params": {"model": "azure/gpt-4.1-mini"}, "model_info": {"id": "5678"}, }, ] @@ -115,7 +115,7 @@ def test_get_available_deployments(): ## DEPLOYMENT 1 ## total_tokens = 50 deployment_id = "1234" - deployment = "azure/gpt-4.1-nano" + deployment = "azure/gpt-4.1-mini" standard_logging_payload = create_standard_logging_payload() standard_logging_payload["model_group"] = model_group standard_logging_payload["model_id"] = deployment_id @@ -730,7 +730,7 @@ async def test_tpm_rpm_routing_model_name_checks(): deployment = { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_base": os.getenv("AZURE_API_BASE"), "mock_response": "Hey, how's it going?", @@ -772,5 +772,5 @@ async def test_tpm_rpm_routing_model_name_checks(): assert ( standard_logging_payload["hidden_params"]["litellm_model_name"] - == "azure/gpt-4.1-nano" + == "azure/gpt-4.1-mini" ) diff --git a/tests/logging_callback_tests/test_amazing_s3_logs.py b/tests/logging_callback_tests/test_amazing_s3_logs.py index c471f23b95..f074026926 100644 --- a/tests/logging_callback_tests/test_amazing_s3_logs.py +++ b/tests/logging_callback_tests/test_amazing_s3_logs.py @@ -384,7 +384,7 @@ async def make_async_calls(): for _ in range(5): task = asyncio.create_task( litellm.acompletion( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[{"role": "user", "content": "This is a test"}], max_tokens=5, temperature=0.7, diff --git a/tests/logging_callback_tests/test_custom_callback_router.py b/tests/logging_callback_tests/test_custom_callback_router.py index f7c0c436ec..f6c7f2fa02 100644 --- a/tests/logging_callback_tests/test_custom_callback_router.py +++ b/tests/logging_callback_tests/test_custom_callback_router.py @@ -395,12 +395,12 @@ async def test_async_chat_azure(): { "model_name": "gpt-4.1-nano", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), }, - "model_info": {"base_model": "azure/gpt-4.1-nano"}, + "model_info": {"base_model": "azure/gpt-4.1-mini"}, "tpm": 240000, "rpm": 1800, }, @@ -546,7 +546,7 @@ async def test_async_chat_azure_with_fallbacks(): { "model_name": "gpt-3.5-turbo", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": "my-bad-key", "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -607,7 +607,7 @@ async def test_async_completion_azure_caching(): { "model_name": "gpt-4.1-nano", # openai model name "litellm_params": { # params for litellm completion/embedding call - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), @@ -670,7 +670,7 @@ async def test_async_completion_azure_caching_streaming(): { "model_name": "gpt-4.1-nano", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"), diff --git a/tests/logging_callback_tests/test_spend_logs.py b/tests/logging_callback_tests/test_spend_logs.py index 6b1ef91673..10c067b7bc 100644 --- a/tests/logging_callback_tests/test_spend_logs.py +++ b/tests/logging_callback_tests/test_spend_logs.py @@ -89,7 +89,7 @@ def test_spend_logs_payload(model_id: Optional[str]): }, "endpoint": "http://localhost:4000/chat/completions", "model_group": "gpt-3.5-turbo", - "deployment": "azure/gpt-4.1-nano", + "deployment": "azure/gpt-4.1-mini", "model_info": { "id": "4bad40a1eb6bebd1682800f16f44b9f06c52a6703444c99c7f9f32e9de3693b4", "db_model": False, diff --git a/tests/old_proxy_tests/tests/load_test_q.py b/tests/old_proxy_tests/tests/load_test_q.py index a50b0fbcab..a8f2c0a322 100644 --- a/tests/old_proxy_tests/tests/load_test_q.py +++ b/tests/old_proxy_tests/tests/load_test_q.py @@ -25,7 +25,7 @@ config = { { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.environ["AZURE_API_KEY"], "api_base": "https://openai-gpt-4-test-v-1.openai.azure.com/", "api_version": "2023-07-01-preview", diff --git a/tests/old_proxy_tests/tests/test_langchain_request.py b/tests/old_proxy_tests/tests/test_langchain_request.py index 0f7c3b3af2..dcbf94f8be 100644 --- a/tests/old_proxy_tests/tests/test_langchain_request.py +++ b/tests/old_proxy_tests/tests/test_langchain_request.py @@ -9,7 +9,7 @@ # chat = ChatOpenAI( # openai_api_base="http://0.0.0.0:8000", -# model = "azure/gpt-4.1-nano", +# model = "azure/gpt-4.1-mini", # temperature=0.1, # extra_body={ # "metadata": { diff --git a/tests/old_proxy_tests/tests/test_openai_request.py b/tests/old_proxy_tests/tests/test_openai_request.py index 21d2a01be6..7c094e67ca 100644 --- a/tests/old_proxy_tests/tests/test_openai_request.py +++ b/tests/old_proxy_tests/tests/test_openai_request.py @@ -4,7 +4,7 @@ client = openai.OpenAI(api_key="hi", base_url="http://0.0.0.0:8000") # # request sent to model set on litellm proxy, `litellm --model` response = client.chat.completions.create( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ {"role": "user", "content": "this is a test request, write a short poem"} ], diff --git a/tests/proxy_unit_tests/example_config_yaml/azure_config.yaml b/tests/proxy_unit_tests/example_config_yaml/azure_config.yaml index a0300bd6d1..0a015aefde 100644 --- a/tests/proxy_unit_tests/example_config_yaml/azure_config.yaml +++ b/tests/proxy_unit_tests/example_config_yaml/azure_config.yaml @@ -1,7 +1,7 @@ model_list: - model_name: gpt-4-team1 litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: https://openai-gpt-4-test-v-1.openai.azure.com/ api_version: "2023-05-15" api_key: os.environ/AZURE_API_KEY diff --git a/tests/proxy_unit_tests/test_configs/test_bad_config.yaml b/tests/proxy_unit_tests/test_configs/test_bad_config.yaml index ae699fdecb..4a70886a93 100644 --- a/tests/proxy_unit_tests/test_configs/test_bad_config.yaml +++ b/tests/proxy_unit_tests/test_configs/test_bad_config.yaml @@ -5,12 +5,12 @@ model_list: model: gpt-3.5-turbo - model_name: working-azure-gpt-3.5-turbo litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: os.environ/AZURE_API_BASE api_key: os.environ/AZURE_API_KEY - model_name: azure-gpt-3.5-turbo litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: os.environ/AZURE_API_BASE api_key: bad-key - model_name: azure-embedding diff --git a/tests/proxy_unit_tests/test_configs/test_cloudflare_azure_with_cache_config.yaml b/tests/proxy_unit_tests/test_configs/test_cloudflare_azure_with_cache_config.yaml index acb0785850..9902835618 100644 --- a/tests/proxy_unit_tests/test_configs/test_cloudflare_azure_with_cache_config.yaml +++ b/tests/proxy_unit_tests/test_configs/test_cloudflare_azure_with_cache_config.yaml @@ -1,7 +1,7 @@ model_list: - model_name: azure-cloudflare litellm_params: - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini api_base: https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1 api_key: os.environ/AZURE_API_KEY api_version: 2023-07-01-preview diff --git a/tests/proxy_unit_tests/test_configs/test_config_no_auth.yaml b/tests/proxy_unit_tests/test_configs/test_config_no_auth.yaml index 1ddfee464f..cdc447a5ee 100644 --- a/tests/proxy_unit_tests/test_configs/test_config_no_auth.yaml +++ b/tests/proxy_unit_tests/test_configs/test_config_no_auth.yaml @@ -12,7 +12,7 @@ model_list: - litellm_params: api_base: https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1 api_key: os.environ/AZURE_API_KEY - model: azure/gpt-4.1-nano + model: azure/gpt-4.1-mini model_name: azure-cloudflare-model - litellm_params: api_base: https://openai-france-1234.openai.azure.com diff --git a/tests/proxy_unit_tests/test_proxy_pass_user_config.py b/tests/proxy_unit_tests/test_proxy_pass_user_config.py index 7b05bddd3a..1a74c71ff3 100644 --- a/tests/proxy_unit_tests/test_proxy_pass_user_config.py +++ b/tests/proxy_unit_tests/test_proxy_pass_user_config.py @@ -64,7 +64,7 @@ def test_chat_completion(client_no_auth): ModelConfig( model_name="user-azure-instance", litellm_params=CompletionRequest( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", api_key=os.getenv("AZURE_API_KEY"), api_version=os.getenv("AZURE_API_VERSION"), api_base=os.getenv("AZURE_API_BASE"), diff --git a/tests/proxy_unit_tests/test_proxy_server.py b/tests/proxy_unit_tests/test_proxy_server.py index b5117a3a2a..1f634d7b9a 100644 --- a/tests/proxy_unit_tests/test_proxy_server.py +++ b/tests/proxy_unit_tests/test_proxy_server.py @@ -452,7 +452,7 @@ def test_chat_completion_azure(mock_acompletion, client_no_auth): try: # Your test data test_data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [ {"role": "user", "content": "write 1 sentence poem"}, ], @@ -463,7 +463,7 @@ def test_chat_completion_azure(mock_acompletion, client_no_auth): response = client_no_auth.post("/v1/chat/completions", json=test_data) mock_acompletion.assert_called_once_with( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ {"role": "user", "content": "write 1 sentence poem"}, ], @@ -496,19 +496,19 @@ def test_openai_deployments_model_chat_completions_azure( try: # Your test data test_data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [ {"role": "user", "content": "write 1 sentence poem"}, ], "max_tokens": 10, } - url = "/openai/deployments/azure/gpt-4.1-nano/chat/completions" + url = "/openai/deployments/azure/gpt-4.1-mini/chat/completions" print(f"testing proxy server with Azure Request {url}") response = client_no_auth.post(url, json=test_data) mock_acompletion.assert_called_once_with( - model="azure/gpt-4.1-nano", + model="azure/gpt-4.1-mini", messages=[ {"role": "user", "content": "write 1 sentence poem"}, ], @@ -1322,7 +1322,7 @@ async def test_add_callback_via_key(prisma_client): try: # Your test data test_data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [ {"role": "user", "content": "write 1 sentence poem"}, ], @@ -1416,7 +1416,7 @@ async def test_add_callback_via_key_litellm_pre_call_utils( request._url = URL(url="/chat/completions") test_data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [ {"role": "user", "content": "write 1 sentence poem"}, ], @@ -1431,7 +1431,7 @@ async def test_add_callback_via_key_litellm_pre_call_utils( data = { "data": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [{"role": "user", "content": "write 1 sentence poem"}], "max_tokens": 10, "mock_response": "Hello world", @@ -1531,7 +1531,7 @@ async def test_disable_fallbacks_by_key(disable_fallbacks_set): key_metadata = {"disable_fallbacks": disable_fallbacks_set} existing_data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [{"role": "user", "content": "write 1 sentence poem"}], } data = LiteLLMProxyRequestSetup.add_key_level_controls( @@ -1572,7 +1572,7 @@ async def test_add_callback_via_key_litellm_pre_call_utils_gcs_bucket( request._url = URL(url="/chat/completions") test_data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [ {"role": "user", "content": "write 1 sentence poem"}, ], @@ -1587,7 +1587,7 @@ async def test_add_callback_via_key_litellm_pre_call_utils_gcs_bucket( data = { "data": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [{"role": "user", "content": "write 1 sentence poem"}], "max_tokens": 10, "mock_response": "Hello world", @@ -1705,7 +1705,7 @@ async def test_add_callback_via_key_litellm_pre_call_utils_langsmith( request._url = URL(url="/chat/completions") test_data = { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [ {"role": "user", "content": "write 1 sentence poem"}, ], @@ -1720,7 +1720,7 @@ async def test_add_callback_via_key_litellm_pre_call_utils_langsmith( data = { "data": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "messages": [{"role": "user", "content": "write 1 sentence poem"}], "max_tokens": 10, "mock_response": "Hello world", diff --git a/tests/proxy_unit_tests/test_proxy_server_keys.py b/tests/proxy_unit_tests/test_proxy_server_keys.py index 77c1844839..717eec921b 100644 --- a/tests/proxy_unit_tests/test_proxy_server_keys.py +++ b/tests/proxy_unit_tests/test_proxy_server_keys.py @@ -171,7 +171,7 @@ # model_data = { # "model_name": "azure-model", # "litellm_params": { -# "model": "azure/gpt-4.1-nano", +# "model": "azure/gpt-4.1-mini", # "api_key": os.getenv("AZURE_API_KEY"), # "api_base": os.getenv("AZURE_API_BASE"), # "api_version": os.getenv("AZURE_API_VERSION") diff --git a/tests/test_litellm/test_router.py b/tests/test_litellm/test_router.py index 3e825e935d..a1b18596b3 100644 --- a/tests/test_litellm/test_router.py +++ b/tests/test_litellm/test_router.py @@ -23,7 +23,7 @@ def test_update_kwargs_does_not_mutate_defaults_and_merges_metadata(): { "model_name": "gpt-3.5-turbo", "litellm_params": { - "model": "azure/gpt-4.1-nano", + "model": "azure/gpt-4.1-mini", "api_key": os.getenv("AZURE_API_KEY"), "api_version": os.getenv("AZURE_API_VERSION"), "api_base": os.getenv("AZURE_API_BASE"),