diff --git a/backends/v3/src/lib.rs b/backends/v3/src/lib.rs
index f3372923..8913e40b 100644
--- a/backends/v3/src/lib.rs
+++ b/backends/v3/src/lib.rs
@@ -101,6 +101,7 @@ pub async fn connect_backend(
             .map_err(V3Error::Warmup)?,
     )?;
     tracing::info!("Setting max batch total tokens to {max_batch_total_tokens}");
+    metrics::gauge!("tgi_batch_max_total_tokens").set(max_batch_total_tokens);
 
     let backend_info = BackendInfo {
         waiting_served_ratio,
diff --git a/router/src/server.rs b/router/src/server.rs
index cc896f99..73b54321 100644
--- a/router/src/server.rs
+++ b/router/src/server.rs
@@ -1937,6 +1937,11 @@ async fn start(
         metrics::Unit::Count,
         "Maximum tokens for the current batch"
     );
+    metrics::describe_gauge!(
+        "tgi_batch_total_tokens",
+        metrics::Unit::Count,
+        "Maximum amount of tokens in total."
+    );
     metrics::describe_histogram!(
         "tgi_request_max_new_tokens",
         metrics::Unit::Count,