diff --git a/config/envoy.template.yaml b/config/envoy.template.yaml
index 40980167..7415bba5 100644
--- a/config/envoy.template.yaml
+++ b/config/envoy.template.yaml
@@ -257,7 +257,7 @@ static_resources:
                           route:
                             auto_host_rewrite: true
                             cluster: bright_staff
-                            timeout: 300s
+                            timeout: {{ listener.timeout | default('300s') }}
                         {% for cluster_name, cluster in plano_clusters.items() %}
                         - match:
                             prefix: "/"
@@ -268,7 +268,7 @@ static_resources:
                           route:
                             auto_host_rewrite: true
                             cluster: {{ cluster_name }}
-                            timeout: 300s
+                            timeout: {{ listener.timeout | default('300s') }}
                         {% endfor %}
                 http_filters:
                   - name: envoy.filters.http.router
diff --git a/crates/prompt_gateway/src/http_context.rs b/crates/prompt_gateway/src/http_context.rs
index e33b2a4c..2b0ca433 100644
--- a/crates/prompt_gateway/src/http_context.rs
+++ b/crates/prompt_gateway/src/http_context.rs
@@ -205,11 +205,7 @@ impl HttpContext for StreamContext {
         info!("on_http_request_body: sending request to model server");
         debug!("request body: {}", json_data);
 
-        let timeout_ms = if let Some(overrides) = self.overrides.as_ref() {
-            overrides.upstream_timeout_ms.unwrap_or(MODEL_SERVER_REQUEST_TIMEOUT_MS)
-        } else {
-            MODEL_SERVER_REQUEST_TIMEOUT_MS
-        };
+        let timeout_ms = MODEL_SERVER_REQUEST_TIMEOUT_MS;
         let timeout_str = timeout_ms.to_string();
 
         let mut headers = vec![
diff --git a/crates/prompt_gateway/src/stream_context.rs b/crates/prompt_gateway/src/stream_context.rs
index 173fcaf5..6166e09b 100644
--- a/crates/prompt_gateway/src/stream_context.rs
+++ b/crates/prompt_gateway/src/stream_context.rs
@@ -171,13 +171,7 @@ impl StreamContext {
                     callout_context.request_body.messages.clone(),
                 );
                 let arch_messages_json = serde_json::to_string(&params).unwrap();
-                let timeout_ms = if let Some(overrides) = self.overrides.as_ref() {
-                    overrides
-                        .upstream_timeout_ms
-                        .unwrap_or(DEFAULT_TARGET_REQUEST_TIMEOUT_MS)
-                } else {
-                    DEFAULT_TARGET_REQUEST_TIMEOUT_MS
-                };
+                let timeout_ms = DEFAULT_TARGET_REQUEST_TIMEOUT_MS;
                 let timeout_str = timeout_ms.to_string();
 
                 let mut headers = vec![
@@ -429,11 +423,7 @@ impl StreamContext {
 
         debug!("on_http_call_response: api call body {:?}", api_call_body);
 
-        let timeout_ms = if let Some(overrides) = self.overrides.as_ref() {
-            overrides.upstream_timeout_ms.unwrap_or(API_REQUEST_TIMEOUT_MS)
-        } else {
-            API_REQUEST_TIMEOUT_MS
-        };
+        let timeout_ms = API_REQUEST_TIMEOUT_MS;
         let timeout_str = timeout_ms.to_string();
 
         let http_method_str = http_method.to_string();