diff --git a/docs/source/distributions/configuration.md b/docs/source/distributions/configuration.md
index b7d910869..2fe9d7c53 100644
--- a/docs/source/distributions/configuration.md
+++ b/docs/source/distributions/configuration.md
@@ -705,7 +705,7 @@ Precedence rules at runtime:
 
 1. If `embedding_model` is explicitly passed in an API call, that value is used.
 2. Otherwise the value in `vector_store_config.default_embedding_model` is used.
-3. If neither is available the server will raise **MissingEmbeddingModelError** at store-creation time so mis-configuration is caught early.
+3. If neither is available the server will raise `MissingEmbeddingModelError` at store-creation time so mis-configuration is caught early.
 
 #### Environment variables
 
diff --git a/llama_stack/apis/common/vector_store_config.py b/llama_stack/apis/common/vector_store_config.py
index 2c396077a..d0508048d 100644
--- a/llama_stack/apis/common/vector_store_config.py
+++ b/llama_stack/apis/common/vector_store_config.py
@@ -29,7 +29,7 @@ class VectorStoreConfig(BaseModel):
     default_embedding_model
         The model *id* the stack should use when an embedding model is
         required but not supplied by the API caller.  When *None* the
-        router will raise a :class:`~llama_stack.errors.MissingEmbeddingModelError`.
+        router will raise a :class:`~llama_stack.apis.common.errors.MissingEmbeddingModelError`.
     default_embedding_dimension
         Optional integer hint for vector dimension.  Routers/providers
         may validate that the chosen model emits vectors of this size.
diff --git a/llama_stack/core/routers/vector_io.py b/llama_stack/core/routers/vector_io.py
index a2f74ba36..bde200c34 100644
--- a/llama_stack/core/routers/vector_io.py
+++ b/llama_stack/core/routers/vector_io.py
@@ -11,6 +11,7 @@ from typing import Any
 from llama_stack.apis.common.content_types import (
     InterleavedContent,
 )
+from llama_stack.apis.common.errors import MissingEmbeddingModelError
 from llama_stack.apis.common.vector_store_config import VectorStoreConfig
 from llama_stack.apis.models import ModelType
 from llama_stack.apis.vector_io import (
@@ -106,9 +107,6 @@ class VectorIORouter(VectorIO):
             return cfg.default_embedding_model, cfg.default_embedding_dimension or 384
 
         # 3. error - no default
-        class MissingEmbeddingModelError(RuntimeError):
-            pass
-
         raise MissingEmbeddingModelError(
             "Failed to create vector store: No embedding model provided. Set vector_store_config.default_embedding_model or supply one in the API call."
         )
diff --git a/tests/unit/router/test_embedding_precedence.py b/tests/unit/router/test_embedding_precedence.py
index 20d26161c..6610ffcbc 100644
--- a/tests/unit/router/test_embedding_precedence.py
+++ b/tests/unit/router/test_embedding_precedence.py
@@ -7,6 +7,7 @@
 
 import pytest
 
+from llama_stack.apis.common.errors import MissingEmbeddingModelError
 from llama_stack.apis.models import ModelType
 from llama_stack.distribution.routers.vector_io import VectorIORouter
 
@@ -76,5 +77,5 @@ async def test_error_when_no_default():
 
     router = VectorIORouter(routing_table=_DummyRoutingTable())
 
-    with pytest.raises(RuntimeError):
+    with pytest.raises(MissingEmbeddingModelError):
         await router._resolve_embedding_model(None)