diff --git a/docs/changelog/139966.yaml b/docs/changelog/139966.yaml
new file mode 100644
index 0000000000000..1f52cd6cd8ad6
--- /dev/null
+++ b/docs/changelog/139966.yaml
@@ -0,0 +1,5 @@
+pr: 139966
+summary: "[Inference API] Fix auth exception listener not called bug"
+area: Inference
+type: bug
+issues: []
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandler.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandler.java
index c1e888d3ecf1c..6f8c8acff7ee6 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandler.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandler.java
@@ -116,6 +116,7 @@ public void getAuthorization(ActionListener<ElasticInferenceServiceAuthorization
         } catch (Exception e) {
             logger.warn(Strings.format("Retrieving the authorization information encountered an exception: %s", e));
             requestCompleteLatch.countDown();
+            listener.onFailure(e);
         }
     }
 
diff --git a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandlerTests.java b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandlerTests.java
index 570e34370fc8a..1d34a982e0108 100644
--- a/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandlerTests.java
+++ b/x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elastic/authorization/ElasticInferenceServiceAuthorizationRequestHandlerTests.java
@@ -44,7 +44,9 @@
 import static org.hamcrest.Matchers.instanceOf;
 import static org.hamcrest.Matchers.is;
 import static org.mockito.ArgumentMatchers.any;
+import static org.mockito.ArgumentMatchers.anyString;
 import static org.mockito.Mockito.doAnswer;
+import static org.mockito.Mockito.doThrow;
 import static org.mockito.Mockito.mock;
 import static org.mockito.Mockito.times;
 import static org.mockito.Mockito.verify;
@@ -161,6 +163,44 @@ private void queueWebServerResponsesForRetries(String responseJson) {
         }
     }
 
+    public void testGetAuthorization_ReturnsFailure_WhenExceptionOccurs() throws IOException {
+        var senderFactory = HttpRequestSenderTests.createSenderFactory(threadPool, clientManager);
+        var eisGatewayUrl = getUrl(webServer);
+
+        var exceptionToThrow = new IllegalStateException("exception");
+        var logger = mock(Logger.class);
+        doThrow(exceptionToThrow).when(logger).debug(anyString());
+
+        var authHandler = new ElasticInferenceServiceAuthorizationRequestHandler(eisGatewayUrl, threadPool, logger);
+
+        try (var sender = senderFactory.createSender()) {
+            String responseJson = """
+                {
+                    "models": [
+                        {
+                          "model_name": "model-a",
+                          "task_types": ["embed/text/sparse", "chat"]
+                        },
+                        {
+                          "model_name": "model-b",
+                          "task_types": ["embed/text/dense"]
+                        }
+                    ]
+                }
+                """;
+
+            webServer.enqueue(new MockResponse().setResponseCode(200).setBody(responseJson));
+
+            PlainActionFuture<ElasticInferenceServiceAuthorizationModel> listener = new PlainActionFuture<>();
+            authHandler.getAuthorization(listener, sender);
+
+            var exception = expectThrows(IllegalStateException.class, () -> listener.actionGet(TIMEOUT));
+            assertThat(exception, is(exceptionToThrow));
+
+            assertThat(webServer.requests().size(), is(0));
+        }
+    }
+
     public void testGetAuthorization_ReturnsAValidResponse() throws IOException {
         var senderFactory = HttpRequestSenderTests.createSenderFactory(threadPool, clientManager);
         var eisGatewayUrl = getUrl(webServer);