diff --git a/docs/resources/llama-stack-spec.html b/docs/resources/llama-stack-spec.html
index 838633a4f..cf4bf5125 100644
--- a/docs/resources/llama-stack-spec.html
+++ b/docs/resources/llama-stack-spec.html
@@ -21,7 +21,7 @@
     "info": {
         "title": "[DRAFT] Llama Stack Specification",
         "version": "alpha",
-        "description": "This is the specification of the llama stack that provides\n                a set of endpoints and their corresponding interfaces that are tailored to\n                best leverage Llama Models. The specification is still in draft and subject to change.\n                Generated at 2024-11-18 23:37:24.867143"
+        "description": "This is the specification of the llama stack that provides\n                a set of endpoints and their corresponding interfaces that are tailored to\n                best leverage Llama Models. The specification is still in draft and subject to change.\n                Generated at 2024-11-19 09:14:01.145131"
     },
     "servers": [
         {
diff --git a/docs/resources/llama-stack-spec.yaml b/docs/resources/llama-stack-spec.yaml
index 994e3aac4..e84f11bdd 100644
--- a/docs/resources/llama-stack-spec.yaml
+++ b/docs/resources/llama-stack-spec.yaml
@@ -3400,7 +3400,7 @@ info:
   description: "This is the specification of the llama stack that provides\n     \
     \           a set of endpoints and their corresponding interfaces that are tailored\
     \ to\n                best leverage Llama Models. The specification is still in\
-    \ draft and subject to change.\n                Generated at 2024-11-18 23:37:24.867143"
+    \ draft and subject to change.\n                Generated at 2024-11-19 09:14:01.145131"
   title: '[DRAFT] Llama Stack Specification'
   version: alpha
 jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
diff --git a/llama_stack/distribution/server/endpoints.py b/llama_stack/distribution/server/endpoints.py
index 93432abe1..af429e020 100644
--- a/llama_stack/distribution/server/endpoints.py
+++ b/llama_stack/distribution/server/endpoints.py
@@ -9,6 +9,8 @@ from typing import Dict, List
 
 from pydantic import BaseModel
 
+from llama_stack.apis.version import LLAMA_STACK_API_VERSION
+
 from llama_stack.distribution.resolver import api_protocol_map
 
 from llama_stack.providers.datatypes import Api
@@ -33,7 +35,7 @@ def get_all_api_endpoints() -> Dict[Api, List[ApiEndpoint]]:
                 continue
 
             webmethod = method.__webmethod__
-            route = webmethod.route
+            route = f"/{LLAMA_STACK_API_VERSION}/{webmethod.route.lstrip('/')}"
 
             if webmethod.method == "GET":
                 method = "get"