diff --git a/llama_stack/apis/inspect/inspect.py b/llama_stack/apis/inspect/inspect.py
index 1dbe80a02..699bce7b7 100644
--- a/llama_stack/apis/inspect/inspect.py
+++ b/llama_stack/apis/inspect/inspect.py
@@ -29,6 +29,11 @@ class HealthInfo(BaseModel):
     # TODO: add a provider level status
 
 
+@json_schema_type
+class VersionInfo(BaseModel):
+    version: str
+
+
 @runtime_checkable
 class Inspect(Protocol):
     @webmethod(route="/providers/list", method="GET")
@@ -39,3 +44,6 @@ class Inspect(Protocol):
 
     @webmethod(route="/health", method="GET")
     async def health(self) -> HealthInfo: ...
+
+    @webmethod(route="/version", method="GET")
+    async def version(self) -> VersionInfo: ...
diff --git a/llama_stack/distribution/inspect.py b/llama_stack/distribution/inspect.py
index dbb16d8ce..d275a5c2f 100644
--- a/llama_stack/distribution/inspect.py
+++ b/llama_stack/distribution/inspect.py
@@ -4,11 +4,18 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from importlib.metadata import version
 from typing import Dict, List
 
 from pydantic import BaseModel
 
-from llama_stack.apis.inspect import HealthInfo, Inspect, ProviderInfo, RouteInfo
+from llama_stack.apis.inspect import (
+    HealthInfo,
+    Inspect,
+    ProviderInfo,
+    RouteInfo,
+    VersionInfo,
+)
 from llama_stack.distribution.datatypes import StackRunConfig
 from llama_stack.distribution.server.endpoints import get_all_api_endpoints
 
@@ -65,3 +72,6 @@ class DistributionInspectImpl(Inspect):
 
     async def health(self) -> HealthInfo:
         return HealthInfo(status="OK")
+
+    async def version(self) -> VersionInfo:
+        return VersionInfo(version=version("llama-stack"))