diff --git a/litellm/llms/vertex_ai/common_utils.py b/litellm/llms/vertex_ai/common_utils.py
index 5895a91f3aa..71b3b2babcd 100644
--- a/litellm/llms/vertex_ai/common_utils.py
+++ b/litellm/llms/vertex_ai/common_utils.py
@@ -263,6 +263,11 @@ def _get_embedding_url(
     except Exception:
         uses_embed_content = False
 
+    # Fallback: all gemini-embedding-* models require the
+    # embedContent endpoint, not the legacy :predict endpoint.
+    if not uses_embed_content and model.startswith("gemini-embedding"):
+        uses_embed_content = True
+
     endpoint = "embedContent" if uses_embed_content else "predict"
 
     base_url = get_vertex_base_url(vertex_location)
diff --git a/litellm/main.py b/litellm/main.py
index f2ce894ba38..ac7499ea415 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -5204,6 +5204,11 @@ def embedding(  # noqa: PLR0915
             except Exception:
                 uses_embed_content = False
 
+            # Fallback: all gemini-embedding-* models require the
+            # embedContent endpoint, not the legacy :predict endpoint.
+            if not uses_embed_content and model.startswith("gemini-embedding"):
+                uses_embed_content = True
+
             if uses_embed_content:
                 response = google_batch_embeddings.batch_embeddings(  # type: ignore
                     model=model,