diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index d4f986edd9b..d2be523e59a 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -2724,7 +2724,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": false
+        "supports_web_search": false,
+        "supports_service_tier": true
     },
     "azure/gpt-4.1-2025-04-14": {
         "deprecation_date": "2026-11-04",
@@ -2758,7 +2759,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": false
+        "supports_web_search": false,
+        "supports_service_tier": true
     },
     "azure/gpt-4.1-mini": {
         "cache_read_input_token_cost": 1e-07,
@@ -4190,7 +4192,6 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_service_tier": true,
         "supports_vision": true
     },
     "azure/gpt-5.3-codex": {
@@ -4469,7 +4470,6 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_service_tier": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -4505,7 +4505,6 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_service_tier": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index d4f986edd9b..d2be523e59a 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -2724,7 +2724,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": false
+        "supports_web_search": false,
+        "supports_service_tier": true
     },
     "azure/gpt-4.1-2025-04-14": {
         "deprecation_date": "2026-11-04",
@@ -2758,7 +2759,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": false
+        "supports_web_search": false,
+        "supports_service_tier": true
     },
     "azure/gpt-4.1-mini": {
         "cache_read_input_token_cost": 1e-07,
@@ -4190,7 +4192,6 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_service_tier": true,
         "supports_vision": true
     },
     "azure/gpt-5.3-codex": {
@@ -4469,7 +4470,6 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_service_tier": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
@@ -4505,7 +4505,6 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_service_tier": true,
         "supports_vision": true,
         "supports_web_search": true,
         "supports_none_reasoning_effort": false,
diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py
index e984403a05b..5875ca07766 100644
--- a/tests/test_litellm/test_utils.py
+++ b/tests/test_litellm/test_utils.py
@@ -892,6 +892,47 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
         raise AssertionError(error_message)
 
 
+def test_azure_supports_service_tier_flags():
+    """
+    Verify that supports_service_tier is set correctly for Azure models
+    based on Azure's priority processing documentation.
+
+    Ref: https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing
+    """
+    import json
+    from pathlib import Path
+
+    config_path = (
+        Path(__file__).parent.parent.parent / "model_prices_and_context_window.json"
+    )
+    with open(config_path, "r") as f:
+        models = json.load(f)
+
+    # Models that Azure officially supports for priority processing
+    should_have = [
+        "azure/gpt-4.1",
+        "azure/gpt-4.1-2025-04-14",
+    ]
+    # Models that should NOT have the flag
+    should_not_have = [
+        "azure/gpt-5.3-chat",
+        "azure/gpt-5.4-mini",
+        "azure/gpt-5.4-nano",
+    ]
+
+    for model in should_have:
+        assert model in models, f"{model} not found in model config"
+        assert models[model].get("supports_service_tier") is True, (
+            f"{model} should have supports_service_tier=true"
+        )
+
+    for model in should_not_have:
+        assert model in models, f"{model} not found in model config"
+        assert "supports_service_tier" not in models[model], (
+            f"{model} should not have supports_service_tier"
+        )
+
+
 def test_max_tokens_consistency():
     """
     Test that max_tokens == max_output_tokens for all models.