From 21c126464b8d4a6e21a0008a6d73c3cdf0a4f767 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Mon, 6 Jul 2026 17:03:18 +0000
Subject: [PATCH] fix(streaming): include ModelResponseStream in
 _extract_usage_chunk annotation

---
 litellm/litellm_core_utils/streaming_chunk_builder_utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/litellm/litellm_core_utils/streaming_chunk_builder_utils.py b/litellm/litellm_core_utils/streaming_chunk_builder_utils.py
index fbb11fa7a1f..d52d9849310 100644
--- a/litellm/litellm_core_utils/streaming_chunk_builder_utils.py
+++ b/litellm/litellm_core_utils/streaming_chunk_builder_utils.py
@@ -517,7 +517,7 @@ class ChunkProcessor:
         return reasoning_tokens
 
     @staticmethod
-    def _extract_usage_chunk(chunk: dict[str, Any] | ModelResponse) -> Usage | None:
+    def _extract_usage_chunk(chunk: dict[str, Any] | ModelResponse | ModelResponseStream) -> Usage | None:
         usage_chunk: Usage | dict[str, Any] | None = None
         if hasattr(chunk, "usage") and chunk.usage is not None:
             usage_chunk = chunk.usage