diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTask.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTask.java
index 9ccb93a0858ae..e5c29adeb9176 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTask.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTask.java
@@ -7,13 +7,14 @@
 
 package org.elasticsearch.xpack.inference.external.http.sender;
 
-import org.elasticsearch.ElasticsearchTimeoutException;
+import org.elasticsearch.ElasticsearchStatusException;
 import org.elasticsearch.action.ActionListener;
 import org.elasticsearch.action.support.ListenerTimeouts;
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.core.Nullable;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.InferenceServiceResults;
+import org.elasticsearch.rest.RestStatus;
 import org.elasticsearch.threadpool.ThreadPool;
 
 import java.util.Objects;
@@ -64,7 +65,10 @@ private ActionListener<InferenceServiceResults> getListener(
             threadPool.executor(UTILITY_THREAD_POOL_NAME),
             notificationListener,
             (ignored) -> notificationListener.onFailure(
-                new ElasticsearchTimeoutException(Strings.format("Request timed out waiting to be sent after [%s]", timeout))
+                new ElasticsearchStatusException(
+                    Strings.format("Request timed out waiting to be sent after [%s]", timeout),
+                    RestStatus.REQUEST_TIMEOUT
+                )
             )
         );
     }
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java
index 79f6aa8164b75..b3e7db6009204 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/HttpRequestSenderTests.java
@@ -8,7 +8,7 @@
 package org.elasticsearch.xpack.inference.external.http.sender;
 
 import org.apache.http.HttpHeaders;
-import org.elasticsearch.ElasticsearchTimeoutException;
+import org.elasticsearch.ElasticsearchStatusException;
 import org.elasticsearch.action.support.PlainActionFuture;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.common.util.concurrent.ThreadContext;
@@ -162,12 +162,13 @@ public void testHttpRequestSender_Throws_WhenATimeoutOccurs() throws Exception {
             PlainActionFuture<InferenceServiceResults> listener = new PlainActionFuture<>();
             sender.send(RequestManagerTests.createMock(), new DocumentsOnlyInput(List.of()), TimeValue.timeValueNanos(1), listener);
 
-            var thrownException = expectThrows(ElasticsearchTimeoutException.class, () -> listener.actionGet(TIMEOUT));
+            var thrownException = expectThrows(ElasticsearchStatusException.class, () -> listener.actionGet(TIMEOUT));
 
             assertThat(
                 thrownException.getMessage(),
                 is(format("Request timed out waiting to be sent after [%s]", TimeValue.timeValueNanos(1)))
             );
+            assertThat(thrownException.status().getStatus(), is(408));
         }
     }
 
@@ -187,12 +188,13 @@ public void testHttpRequestSenderWithTimeout_Throws_WhenATimeoutOccurs() throws
             PlainActionFuture<InferenceServiceResults> listener = new PlainActionFuture<>();
             sender.send(RequestManagerTests.createMock(), new DocumentsOnlyInput(List.of()), TimeValue.timeValueNanos(1), listener);
 
-            var thrownException = expectThrows(ElasticsearchTimeoutException.class, () -> listener.actionGet(TIMEOUT));
+            var thrownException = expectThrows(ElasticsearchStatusException.class, () -> listener.actionGet(TIMEOUT));
 
             assertThat(
                 thrownException.getMessage(),
                 is(format("Request timed out waiting to be sent after [%s]", TimeValue.timeValueNanos(1)))
             );
+            assertThat(thrownException.status().getStatus(), is(408));
         }
     }
 
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestExecutorServiceTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestExecutorServiceTests.java
index e09e4968571e5..7e29fad56812d 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestExecutorServiceTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestExecutorServiceTests.java
@@ -8,7 +8,7 @@
 package org.elasticsearch.xpack.inference.external.http.sender;
 
 import org.elasticsearch.ElasticsearchException;
-import org.elasticsearch.ElasticsearchTimeoutException;
+import org.elasticsearch.ElasticsearchStatusException;
 import org.elasticsearch.action.ActionListener;
 import org.elasticsearch.action.support.PlainActionFuture;
 import org.elasticsearch.common.Strings;
@@ -238,12 +238,13 @@ public void testExecute_CallsOnFailure_WhenRequestTimesOut() {
         var listener = new PlainActionFuture<InferenceServiceResults>();
         service.execute(RequestManagerTests.createMock(), new DocumentsOnlyInput(List.of()), TimeValue.timeValueNanos(1), listener);
 
-        var thrownException = expectThrows(ElasticsearchTimeoutException.class, () -> listener.actionGet(TIMEOUT));
+        var thrownException = expectThrows(ElasticsearchStatusException.class, () -> listener.actionGet(TIMEOUT));
 
         assertThat(
             thrownException.getMessage(),
             is(format("Request timed out waiting to be sent after [%s]", TimeValue.timeValueNanos(1)))
         );
+        assertThat(thrownException.status().getStatus(), is(408));
     }
 
     public void testExecute_PreservesThreadContext() throws InterruptedException, ExecutionException, TimeoutException {
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTaskTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTaskTests.java
index c839c266e9320..e37a1a213569e 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTaskTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/external/http/sender/RequestTaskTests.java
@@ -7,7 +7,7 @@
 
 package org.elasticsearch.xpack.inference.external.http.sender;
 
-import org.elasticsearch.ElasticsearchTimeoutException;
+import org.elasticsearch.ElasticsearchStatusException;
 import org.elasticsearch.action.ActionListener;
 import org.elasticsearch.action.support.PlainActionFuture;
 import org.elasticsearch.core.TimeValue;
@@ -86,13 +86,14 @@ public void testRequest_ReturnsTimeoutException() {
             listener
         );
 
-        var thrownException = expectThrows(ElasticsearchTimeoutException.class, () -> listener.actionGet(TIMEOUT));
+        var thrownException = expectThrows(ElasticsearchStatusException.class, () -> listener.actionGet(TIMEOUT));
         assertThat(
             thrownException.getMessage(),
             is(format("Request timed out waiting to be sent after [%s]", TimeValue.timeValueMillis(1)))
         );
         assertTrue(requestTask.hasCompleted());
         assertTrue(requestTask.getRequestCompletedFunction().get());
+        assertThat(thrownException.status().getStatus(), is(408));
     }
 
     public void testRequest_DoesNotCallOnFailureTwiceWhenTimingOut() throws Exception {