diff --git a/llama_stack/distribution/server/server.py b/llama_stack/distribution/server/server.py
index 84c369364..185c89e7e 100644
--- a/llama_stack/distribution/server/server.py
+++ b/llama_stack/distribution/server/server.py
@@ -288,6 +288,9 @@ def main(
         apis_to_serve = set(impls.keys())
 
     for inf in builtin_automatically_routed_apis():
+        # if we do not serve the corresponding router API, we should not serve the routing table API
+        if inf.router_api.value not in apis_to_serve:
+            continue
         apis_to_serve.add(inf.routing_table_api.value)
 
     apis_to_serve.add("inspect")
diff --git a/tests/examples/inference-run.yaml b/tests/examples/inference-run.yaml
new file mode 100644
index 000000000..87ab5146b
--- /dev/null
+++ b/tests/examples/inference-run.yaml
@@ -0,0 +1,14 @@
+version: '2'
+built_at: '2024-10-08T17:40:45.325529'
+image_name: local
+docker_image: null
+conda_env: local
+apis:
+- models
+- inference
+providers:
+  inference:
+  - provider_id: tgi0
+    provider_type: remote::tgi
+    config:
+      url: http://127.0.0.1:5009