diff --git a/litellm/router.py b/litellm/router.py
index 5d0cde44f..ba3f13b8e 100644
--- a/litellm/router.py
+++ b/litellm/router.py
@@ -3998,8 +3998,8 @@ class Router:
             verbose_router_logger.error(
                 "Could not identify azure model. Set azure 'base_model' for accurate max tokens, cost tracking, etc.- https://docs.litellm.ai/docs/proxy/cost_tracking#spend-tracking-for-azure-openai-models"
             )
-        else:
-            model = deployment.get("litellm_params", {}).get("model", None)
+        elif custom_llm_provider != "azure":
+            model = _model
 
         ## GET LITELLM MODEL INFO - raises exception, if model is not mapped
         model_info = litellm.get_model_info(model=model)
diff --git a/litellm/tests/test_router.py b/litellm/tests/test_router.py
index db240e358..7c59611d7 100644
--- a/litellm/tests/test_router.py
+++ b/litellm/tests/test_router.py
@@ -812,6 +812,7 @@ def test_router_context_window_check_pre_call_check():
                     "base_model": "azure/gpt-35-turbo",
                     "mock_response": "Hello world 1!",
                 },
+                "model_info": {"base_model": "azure/gpt-35-turbo"},
             },
             {
                 "model_name": "gpt-3.5-turbo",  # openai model name
diff --git a/pyproject.toml b/pyproject.toml
index 9084f5778..a3267dfa8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "1.40.32"
+version = "1.41.0"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT"
@@ -90,7 +90,7 @@ requires = ["poetry-core", "wheel"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.commitizen]
-version = "1.40.32"
+version = "1.41.0"
 version_files = [
     "pyproject.toml:^version"
 ]