diff --git a/libs/community/langchain_community/embeddings/huggingface_hub.py b/libs/community/langchain_community/embeddings/huggingface_hub.py
index 0ee0881d2e7..df95a2d2720 100644
--- a/libs/community/langchain_community/embeddings/huggingface_hub.py
+++ b/libs/community/langchain_community/embeddings/huggingface_hub.py
@@ -112,8 +112,9 @@ class HuggingFaceHubEmbeddings(BaseModel, Embeddings):
         # replace newlines, which can negatively affect performance.
         texts = [text.replace("\n", " ") for text in texts]
         _model_kwargs = self.model_kwargs or {}
+        #  api doc: https://huggingface.github.io/text-embeddings-inference/#/Text%20Embeddings%20Inference/embed
         responses = self.client.post(
-            json={"inputs": texts, "parameters": _model_kwargs}, task=self.task
+            json={"inputs": texts, **_model_kwargs}, task=self.task
         )
         return json.loads(responses.decode())
 
diff --git a/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface_endpoint.py b/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface_endpoint.py
index 519a42ae393..20df972cb26 100644
--- a/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface_endpoint.py
+++ b/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface_endpoint.py
@@ -108,8 +108,9 @@ class HuggingFaceEndpointEmbeddings(BaseModel, Embeddings):
         # replace newlines, which can negatively affect performance.
         texts = [text.replace("\n", " ") for text in texts]
         _model_kwargs = self.model_kwargs or {}
+        #  api doc: https://huggingface.github.io/text-embeddings-inference/#/Text%20Embeddings%20Inference/embed
         responses = self.client.post(
-            json={"inputs": texts, "parameters": _model_kwargs}, task=self.task
+            json={"inputs": texts, **_model_kwargs}, task=self.task
         )
         return json.loads(responses.decode())