diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 9918743bc9..d30a4d863b 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -1471,6 +1471,64 @@
         "litellm_provider": "openai",
         "supported_endpoints": ["/v1/audio/speech"]
     },
+    "azure/gpt-4.1": {
+        "max_tokens": 32768,
+        "max_input_tokens": 1047576,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 2e-6,
+        "output_cost_per_token": 8e-6,
+        "input_cost_per_token_batches": 1e-6,
+        "output_cost_per_token_batches": 4e-6,
+        "cache_read_input_token_cost": 0.5e-6,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+        "supported_modalities": ["text", "image"],
+        "supported_output_modalities": ["text"],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_native_streaming": true,
+        "supports_web_search": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 30e-3,
+            "search_context_size_medium": 35e-3,
+            "search_context_size_high": 50e-3
+        }
+    },
+    "azure/gpt-4.1-2025-04-14": {
+        "max_tokens": 32768,
+        "max_input_tokens": 1047576,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 2e-6,
+        "output_cost_per_token": 8e-6,
+        "input_cost_per_token_batches": 1e-6,
+        "output_cost_per_token_batches": 4e-6,
+        "cache_read_input_token_cost": 0.5e-6,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+        "supported_modalities": ["text", "image"],
+        "supported_output_modalities": ["text"],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_native_streaming": true,
+        "supports_web_search": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 30e-3,
+            "search_context_size_medium": 35e-3,
+            "search_context_size_high": 50e-3
+        }
+    },
     "azure/gpt-4o-mini-realtime-preview-2024-12-17": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,
diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml
index e166133cec..b1c4959e0b 100644
--- a/litellm/proxy/_new_secret_config.yaml
+++ b/litellm/proxy/_new_secret_config.yaml
@@ -21,13 +21,12 @@ model_list:
       model: databricks/databricks-claude-3-7-sonnet
       api_key: os.environ/DATABRICKS_API_KEY
       api_base: os.environ/DATABRICKS_API_BASE
-  - model_name: "gpt-4o-realtime-preview"
+  - model_name: "gpt-4.1"
     litellm_params:
-      model: azure/gpt-4o-realtime-preview-2
+      model: azure/gpt-4.1
       api_key: os.environ/AZURE_API_KEY_REALTIME
       api_base: https://krris-m2f9a9i7-eastus2.openai.azure.com/
-    model_info:
-      base_model: azure/gpt-4o-realtime-preview-2024-10-01
+
 
 
 litellm_settings:
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 9918743bc9..d30a4d863b 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -1471,6 +1471,64 @@
         "litellm_provider": "openai",
         "supported_endpoints": ["/v1/audio/speech"]
     },
+    "azure/gpt-4.1": {
+        "max_tokens": 32768,
+        "max_input_tokens": 1047576,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 2e-6,
+        "output_cost_per_token": 8e-6,
+        "input_cost_per_token_batches": 1e-6,
+        "output_cost_per_token_batches": 4e-6,
+        "cache_read_input_token_cost": 0.5e-6,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+        "supported_modalities": ["text", "image"],
+        "supported_output_modalities": ["text"],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_native_streaming": true,
+        "supports_web_search": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 30e-3,
+            "search_context_size_medium": 35e-3,
+            "search_context_size_high": 50e-3
+        }
+    },
+    "azure/gpt-4.1-2025-04-14": {
+        "max_tokens": 32768,
+        "max_input_tokens": 1047576,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 2e-6,
+        "output_cost_per_token": 8e-6,
+        "input_cost_per_token_batches": 1e-6,
+        "output_cost_per_token_batches": 4e-6,
+        "cache_read_input_token_cost": 0.5e-6,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
+        "supported_modalities": ["text", "image"],
+        "supported_output_modalities": ["text"],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_prompt_caching": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_native_streaming": true,
+        "supports_web_search": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 30e-3,
+            "search_context_size_medium": 35e-3,
+            "search_context_size_high": 50e-3
+        }
+    },
     "azure/gpt-4o-mini-realtime-preview-2024-12-17": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,