diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml
index bb5ef5d624630..5fd048c2ad0c6 100644
--- a/.buildkite/test-amd.yaml
+++ b/.buildkite/test-amd.yaml
@@ -348,6 +348,7 @@ steps:
     - pytest -v -s -m 'not cpu_test' v1/metrics
     - pytest -v -s v1/test_oracle.py
     - pytest -v -s v1/test_request.py
+    - pytest -v -s v1/test_outputs.py
     # Integration test for streaming correctness (requires special branch).
     - pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
     - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml
index 83a7df3b093fc..25f711dd60b37 100644
--- a/.buildkite/test-pipeline.yaml
+++ b/.buildkite/test-pipeline.yaml
@@ -329,6 +329,7 @@ steps:
     - pytest -v -s -m 'not cpu_test' v1/metrics
     - pytest -v -s v1/test_oracle.py
     - pytest -v -s v1/test_request.py
+    - pytest -v -s v1/test_outputs.py
     # Integration test for streaming correctness (requires special branch).
     - pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
     - pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine