diff --git a/libs/partners/groq/langchain_groq/chat_models.py b/libs/partners/groq/langchain_groq/chat_models.py
index 9cfaa31042a..d98eb734610 100644
--- a/libs/partners/groq/langchain_groq/chat_models.py
+++ b/libs/partners/groq/langchain_groq/chat_models.py
@@ -430,7 +430,9 @@ class ChatGroq(BaseChatModel):
     max_tokens: int | None = None
     """Maximum number of tokens to generate."""
 
-    service_tier: Literal["on_demand", "flex", "auto"] = Field(default="on_demand")
+    service_tier: Literal["on_demand", "flex", "auto", "performance"] = Field(
+        default="on_demand"
+    )
     """Optional parameter that you can include to specify the service tier you'd like to
     use for requests.
 
@@ -440,6 +442,8 @@ class ChatGroq(BaseChatModel):
         reliability for workloads that don't require guaranteed processing.
     - `'auto'`: Uses on-demand rate limits, then falls back to `'flex'` if those
         limits are exceeded
+    - `'performance'`: Highest tier, providing reliable low latency for the most
+        critical production applications.
 
     See the [Groq documentation](https://console.groq.com/docs/flex-processing) for more
     details and a list of service tiers and descriptions.
diff --git a/libs/partners/groq/tests/integration_tests/test_chat_models.py b/libs/partners/groq/tests/integration_tests/test_chat_models.py
index bd43972b1f3..e1cba270728 100644
--- a/libs/partners/groq/tests/integration_tests/test_chat_models.py
+++ b/libs/partners/groq/tests/integration_tests/test_chat_models.py
@@ -574,6 +574,9 @@ def test_setting_service_tier_class() -> None:
     response = chat.invoke([message])
     assert response.response_metadata.get("service_tier") == "on_demand"
 
+    chat = ChatGroq(model=DEFAULT_MODEL_NAME, service_tier="performance")
+    assert chat.service_tier == "performance"
+
     chat = ChatGroq(model=DEFAULT_MODEL_NAME)
     assert chat.service_tier == "on_demand"
     response = chat.invoke([message])