diff --git a/pr_agent/algo/ai_handlers/litellm_ai_handler.py b/pr_agent/algo/ai_handlers/litellm_ai_handler.py
index 7061ca797..e3cbda397 100644
--- a/pr_agent/algo/ai_handlers/litellm_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/litellm_ai_handler.py
@@ -101,11 +101,6 @@ async def chat_completion(self, model: str, system: str, user: str, temperature:
         """
         try:
             deployment_id = self.deployment_id
-            if get_settings().config.verbosity_level >= 2:
-                get_logger().debug(
-                    f"Generating completion with {model}"
-                    f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
-                )
             if self.azure:
                 model = 'azure/' + model
             messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
diff --git a/pr_agent/algo/pr_processing.py b/pr_agent/algo/pr_processing.py
index 4b3805506..ecec30151 100644
--- a/pr_agent/algo/pr_processing.py
+++ b/pr_agent/algo/pr_processing.py
@@ -226,6 +226,11 @@ async def retry_with_fallback_models(f: Callable):
     # try each (model, deployment_id) pair until one is successful, otherwise raise exception
     for i, (model, deployment_id) in enumerate(zip(all_models, all_deployments)):
         try:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().debug(
+                    f"Generating prediction with {model}"
+                    f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
+                )
             get_settings().set("openai.deployment_id", deployment_id)
             return await f(model)
         except Exception as e: