diff --git a/libs/core/langchain_core/language_models/chat_models.py b/libs/core/langchain_core/language_models/chat_models.py
index 6336dfbab8316..57a0cd37c13b4 100644
--- a/libs/core/langchain_core/language_models/chat_models.py
+++ b/libs/core/langchain_core/language_models/chat_models.py
@@ -463,7 +463,7 @@ async def astream(
         )
 
         if self.rate_limiter:
-            self.rate_limiter.acquire(blocking=True)
+            await self.rate_limiter.aacquire(blocking=True)
 
         generation: Optional[ChatGenerationChunk] = None
         try:
@@ -905,7 +905,7 @@ async def _agenerate_with_cache(
         # we usually don't want to rate limit cache lookups, but
         # we do want to rate limit API requests.
         if self.rate_limiter:
-            self.rate_limiter.acquire(blocking=True)
+            await self.rate_limiter.aacquire(blocking=True)
 
         # If stream is not explicitly set, check if implicitly requested by
         # astream_events() or astream_log(). Bail out if _astream not implemented