diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 66b9efe5325..da09346503d 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -5313,7 +5313,7 @@ async def embeddings(  # noqa: PLR0915
             # check if provider accept list of tokens as input - e.g. for langchain integration
             if llm_router is not None and data.get("model") in router_model_names:
                 # Use router's O(1) lookup instead of O(N) iteration through llm_model_list
-                deployment = llm_router.get_deployment(model_id=data["model"])
+                deployment = llm_router.get_deployment_by_model_group_name(model_group_name=data["model"])
                 if deployment is not None:
                     litellm_params = deployment.get("litellm_params", {}) or {}
                     litellm_model = litellm_params.get("model", "")