[Bug]: Error when attempting to use /chat/completions when using Azure's `v1-preview` API Version

[aidankovacic-8451]

What happened?

Problem
When attempting to use Azure AI Foundry's v1-preview API Version, an error occurs when attempting to call /chat/completions, but not /responses when using OpenAI models.

Steps to Recreate

1. Create a model config like such:

- model_name: gpt-4.1
    litellm_params:
      model: "azure/gpt-4-1"
      api_base: <base_url>
      api_key: <api_key>
      api_version: preview # IMPORTANT
      timeout: 60
      stream_timeout: 30
      rpm: 2000
      tpm: 2000000

2. Load LiteLLM
3. Send a request like such

_Optional:_ Verify that Responses API is working.

Relevant log output

{
  "error": {
    "message": "litellm.APIConnectionError: AzureException APIConnectionError - list index out of range\nTraceback (most recent call last):\n  File \"/usr/local/lib/python3.13/site-packages/litellm/main.py\", line 1194, in completion\n    optional_params = get_optional_params(\n        **optional_param_args, **non_default_params\n    )\n  File \"/usr/local/lib/python3.13/site-packages/litellm/utils.py\", line 3819, in get_optional_params\n    optional_params = litellm.AzureOpenAIConfig().map_openai_params(\n        non_default_params=non_default_params,\n    ...<7 lines>...\n        ),\n    )\n  File \"/usr/local/lib/python3.13/site-packages/litellm/llms/azure/chat/gpt_transformation.py\", line 165, in map_openai_params\n    api_version_month = api_version_times[1]\n                        ~~~~~~~~~~~~~~~~~^^^\nIndexError: list index out of range\n. Received Model Group=gpt-4.1\nAvailable Model Group Fallbacks=None",
    "type": null,
    "param": null,
    "code": "500"
  }
}

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

v1.73.6

Twitter / LinkedIn details

No response