diff --git a/litellm/proxy/common_utils/swagger_utils.py b/litellm/proxy/common_utils/swagger_utils.py
new file mode 100644
index 0000000000..75a64707cd
--- /dev/null
+++ b/litellm/proxy/common_utils/swagger_utils.py
@@ -0,0 +1,48 @@
+from typing import Any, Dict
+
+from pydantic import BaseModel, Field
+
+from litellm.exceptions import LITELLM_EXCEPTION_TYPES
+
+
+class ErrorResponse(BaseModel):
+    detail: Dict[str, Any] = Field(
+        ...,
+        example={  # type: ignore
+            "error": {
+                "message": "Error message",
+                "type": "error_type",
+                "param": "error_param",
+                "code": "error_code",
+            }
+        },
+    )
+
+
+# Define a function to get the status code
+def get_status_code(exception):
+    if hasattr(exception, "status_code"):
+        return exception.status_code
+    # Default status codes for exceptions without a status_code attribute
+    if exception.__name__ == "Timeout":
+        return 408  # Request Timeout
+    if exception.__name__ == "APIConnectionError":
+        return 503  # Service Unavailable
+    return 500  # Internal Server Error as default
+
+
+# Create error responses
+ERROR_RESPONSES = {
+    get_status_code(exception): {
+        "model": ErrorResponse,
+        "description": exception.__doc__ or exception.__name__,
+    }
+    for exception in LITELLM_EXCEPTION_TYPES
+}
+
+# Ensure we have a 500 error response
+if 500 not in ERROR_RESPONSES:
+    ERROR_RESPONSES[500] = {
+        "model": ErrorResponse,
+        "description": "Internal Server Error",
+    }
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 9d8d3fa2df..e0dbcebfc9 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -167,6 +167,7 @@ from litellm.proxy.common_utils.load_config_utils import get_file_contents_from_
 from litellm.proxy.common_utils.openai_endpoint_utils import (
     remove_sensitive_info_from_deployment,
 )
+from litellm.proxy.common_utils.swagger_utils import ERROR_RESPONSES
 from litellm.proxy.fine_tuning_endpoints.endpoints import router as fine_tuning_router
 from litellm.proxy.fine_tuning_endpoints.endpoints import set_fine_tuning_config
 from litellm.proxy.guardrails.init_guardrails import (
@@ -3036,6 +3037,7 @@ def model_list(
     "/openai/deployments/{model:path}/chat/completions",
     dependencies=[Depends(user_api_key_auth)],
     tags=["chat/completions"],
+    responses={200: {"description": "Successful response"}, **ERROR_RESPONSES},
 )  # azure compatible endpoint
 @backoff.on_exception(
     backoff.expo,