diff --git a/litellm/__init__.py b/litellm/__init__.py
index cb07c6a389..2ed12e7f02 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -260,6 +260,7 @@ open_ai_chat_completion_models: List = []
 open_ai_text_completion_models: List = []
 cohere_models: List = []
 cohere_chat_models: List = []
+mistral_chat_models: List = []
 anthropic_models: List = []
 openrouter_models: List = []
 vertex_language_models: List = []
@@ -284,6 +285,8 @@ for key, value in model_cost.items():
         cohere_models.append(key)
     elif value.get("litellm_provider") == "cohere_chat":
         cohere_chat_models.append(key)
+    elif value.get("litellm_provider") == "mistral":
+        mistral_chat_models.append(key)
     elif value.get("litellm_provider") == "anthropic":
         anthropic_models.append(key)
     elif value.get("litellm_provider") == "openrouter":
diff --git a/litellm/utils.py b/litellm/utils.py
index d642fbbb95..9da560947a 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -5575,13 +5575,15 @@ def get_llm_provider(
 
         # AZURE AI-Studio Logic - Azure AI Studio supports AZURE/Cohere
         # If User passes azure/command-r-plus -> we should send it to cohere_chat/command-r-plus
-        if (
-            model.split("/", 1)[0] == "azure"
-            and model.split("/", 1)[1] in litellm.cohere_chat_models
-        ):
-            custom_llm_provider = "openai"
-            model = model.split("/", 1)[1]
-            return model, custom_llm_provider, dynamic_api_key, api_base
+        if model.split("/", 1)[0] == "azure":
+            model_name = model.split("/", 1)[1]
+            if (
+                model_name in litellm.cohere_chat_models
+                or model_name in litellm.mistral_chat_models
+            ):
+                custom_llm_provider = "openai"
+                model = model_name
+                return model, custom_llm_provider, dynamic_api_key, api_base
 
         if custom_llm_provider:
             return model, custom_llm_provider, dynamic_api_key, api_base