diff --git a/docs/my-website/docs/proxy/configs.md b/docs/my-website/docs/proxy/configs.md
index 19c1f7902dd..d08d6324da9 100644
--- a/docs/my-website/docs/proxy/configs.md
+++ b/docs/my-website/docs/proxy/configs.md
@@ -727,6 +727,7 @@ general_settings:
     "completion_model": "string",
     "disable_spend_logs": "boolean", # turn off writing each transaction to the db
     "disable_master_key_return": "boolean", # turn off returning master key on UI (checked on '/user/info' endpoint)
+    "disable_retry_on_max_parallel_request_limit_error": "boolean", # turn off retries when max parallel request limit is reached
     "disable_reset_budget": "boolean", # turn off reset budget scheduled task
     "disable_adding_master_key_hash_to_db": "boolean", # turn off storing master key hash in db, for spend tracking
     "enable_jwt_auth": "boolean", # allow proxy admin to auth in via jwt tokens with 'litellm_proxy_admin' in claims
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 6bd528def82..c793ffbe3ff 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -2672,6 +2672,13 @@ def giveup(e):
         and isinstance(e.message, str)
         and "Max parallel request limit reached" in e.message
     )
+
+    if (
+        general_settings.get("disable_retry_on_max_parallel_request_limit_error")
+        is True
+    ):
+        return True  # giveup if queuing max parallel request limits is disabled
+
     if result:
         verbose_proxy_logger.info(json.dumps({"event": "giveup", "exception": str(e)}))
     return result