diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index 271a53dd4..7d639d7a3 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -1501,6 +1501,37 @@ def test_openai_chat_completion_complete_response_call():
 
 
 # test_openai_chat_completion_complete_response_call()
+def test_openai_stream_options_call():
+    litellm.set_verbose = False
+    response = litellm.completion(
+        model="gpt-3.5-turbo",
+        messages=[{"role": "system", "content": "say GM - we're going to make it "}],
+        stream=True,
+        stream_options={"include_usage": True},
+        max_tokens=10,
+    )
+    usage = None
+    chunks = []
+    for chunk in response:
+        print("chunk: ", chunk)
+        chunks.append(chunk)
+
+    last_chunk = chunks[-1]
+    print("last chunk: ", last_chunk)
+
+    """
+    Assert that:
+    - Last Chunk includes Usage
+    - All chunks prior to last chunk have usage=None
+    """
+
+    assert last_chunk.usage is not None
+    assert last_chunk.usage.total_tokens > 0
+    assert last_chunk.usage.prompt_tokens > 0
+    assert last_chunk.usage.completion_tokens > 0
+
+    # assert all non last chunks have usage=None
+    assert all(chunk.usage is None for chunk in chunks[:-1])
 
 
 def test_openai_text_completion_call():