litellm - 💡(How to fix) Fix [Bug]: Azure OAI Models Auth Broken in 1.84.0

{"message": "\nLiteLLM completion() model= gpt-5-4-mini; provider = azure", "level": "INFO", "timestamp": "2026-05-14T17:35:00.087708", "component": "LiteLLM", "logger": "utils.py:4051"}
{"message": "For Azure AD Token Provider, choosing credential type: AzureCredentialType.DefaultAzureCredential", "level": "INFO", "timestamp": "2026-05-14T17:35:00.088509", "component": "LiteLLM", "logger": "get_azure_ad_token_provider.py:76"}
{"message": "litellm.acompletion(model=azure/gpt-5-4-mini)\u001b[31m Exception litellm.AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable\u001b[0m", "level": "INFO", "timestamp": "2026-05-14T17:35:00.105306", "component": "LiteLLM Router", "logger": "router.py:2521"}
{"message": "Trying to fallback b/w models", "level": "INFO", "timestamp": "2026-05-14T17:35:00.109130", "component": "LiteLLM Router", "logger": "router.py:5738"}
{"message": "litellm.proxy.proxy_server._handle_llm_api_exception(): Exception occured - litellm.AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable. Received Model Group=gpt-5-4-mini\nAvailable Model Group Fallbacks=None", "level": "ERROR", "timestamp": "2026-05-14T17:35:00.113142", "component": "LiteLLM Proxy", "logger": "common_request_processing.py:1730", "stacktrace": "Traceback (most recent call last):\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/llms/azure/azure.py\", line 592, in async_streaming\n    azure_client = self.get_azure_openai_client(\n        api_version=api_version,\n    ...<5 lines>...\n        litellm_params=litellm_params,\n    )\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/llms/azure/common_utils.py\", line 493, in get_azure_openai_client\n    openai_client = AsyncOpenAI(**v1_params)  # type: ignore\n  File \"/app/.venv/lib/python3.13/site-packages/openai/_client.py\", line 587, in __init__\n    raise OpenAIError(\n        \"The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable\"\n    )\nopenai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/main.py\", line 622, in acompletion\n    response = await init_response\n               ^^^^^^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/llms/azure/azure.py\", line 647, in async_streaming\n    raise AzureOpenAIError(\n    ...<4 lines>...\n    )\nlitellm.llms.azure.common_utils.AzureOpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/proxy/proxy_server.py\", line 8069, in chat_completion\n    result = await base_llm_response_processor.base_process_llm_request(\n             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    ...<16 lines>...\n    )\n    ^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/proxy/common_request_processing.py\", line 1193, in base_process_llm_request\n    responses = await llm_responses\n                ^^^^^^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 2029, in acompletion\n    raise e\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 2005, in acompletion\n    response = await self.async_function_with_fallbacks(**kwargs)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 5935, in async_function_with_fallbacks\n    return await self.async_function_with_fallbacks_common_utils(\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    ...<8 lines>...\n    )\n    ^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 5892, in async_function_with_fallbacks_common_utils\n    raise original_exception\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 5926, in async_function_with_fallbacks\n    response = await self.async_function_with_retries(*args, **kwargs)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 6081, in async_function_with_retries\n    self.should_retry_this_error(\n    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^\n        error=e,\n        ^^^^^^^^\n    ...<4 lines>...\n        content_policy_fallbacks=content_policy_fallbacks,\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 6306, in should_retry_this_error\n    raise error  # then raise error\n    ^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 6032, in async_function_with_retries\n    response = await self.make_call(original_function, *args, **kwargs)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 6200, in make_call\n    response = await response\n               ^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 2529, in _acompletion\n    raise e\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/router.py\", line 2475, in _acompletion\n    response = await _response\n               ^^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/utils.py\", line 2097, in wrapper_async\n    raise e\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/utils.py\", line 1896, in wrapper_async\n    result = await original_function(*args, **kwargs)\n             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/main.py\", line 641, in acompletion\n    raise exception_type(\n          ~~~~~~~~~~~~~~^\n        model=model,\n        ^^^^^^^^^^^^\n    ...<3 lines>...\n        extra_kwargs=kwargs,\n        ^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py\", line 2466, in exception_type\n    raise e\n  File \"/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py\", line 2212, in exception_type\n    raise AuthenticationError(\n    ...<5 lines>...\n    )\nlitellm.exceptions.AuthenticationError: litellm.AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable. Received Model Group=gpt-5-4-mini\nAvailable Model Group Fallbacks=None"}