diff --git a/app.py b/app.py
index a38f0d8..f0d2e5d 100644
--- a/app.py
+++ b/app.py
@@ -165,3 +165,12 @@ class EmbeddingResponse(BaseModel):
 )
 async def embedding(embedding: EmbeddingModel, user=Depends(verify_api_key)):
     return LLM(model=embedding.model).embedding(input=embedding.input)
+
+
+@app.post(
+    "/v1/engines/{model_name}/embeddings",
+    tags=["Embeddings"],
+    dependencies=[Depends(verify_api_key)],
+)
+async def embedding(embedding: EmbeddingModel, user=Depends(verify_api_key)):
+    return LLM(model=embedding.model).embedding(input=embedding.input)
diff --git a/setup.py b/setup.py
index a7d2fda..0a4f94a 100644
--- a/setup.py
+++ b/setup.py
@@ -10,7 +10,7 @@
 
 setup(
     name="local-llm",
-    version="0.0.20",
+    version="0.0.21",
     description="Local-LLM is a llama.cpp server in Docker with OpenAI Style Endpoints.",
     long_description=long_description,
     long_description_content_type="text/markdown",