Merge branch 'main' into litellm_embedding_caching_updates

litellm/main.py

@@ -202,6 +202,7 @@ async def acompletion(
         - If `stream` is True, the function returns an async generator that yields completion lines.
     """
     loop = asyncio.get_event_loop()
+    custom_llm_provider = None
     # Adjusted to use explicit arguments instead of *args and **kwargs
     completion_kwargs = {
         "model": model,
@@ -243,6 +244,9 @@ async def acompletion(
         ctx = contextvars.copy_context()
         func_with_context = partial(ctx.run, func)
 
+        _, custom_llm_provider, _, _ = get_llm_provider(
+            model=model, api_base=kwargs.get("api_base", None)
+        )
         if (
             custom_llm_provider == "openai"
             or custom_llm_provider == "azure"