diff --git a/llama_stack/templates/remote-vllm/run-with-safety.yaml b/llama_stack/templates/remote-vllm/run-with-safety.yaml
index 3830ffcdb..9ab6d014e 100644
--- a/llama_stack/templates/remote-vllm/run-with-safety.yaml
+++ b/llama_stack/templates/remote-vllm/run-with-safety.yaml
@@ -15,7 +15,7 @@ providers:
   - provider_id: vllm-inference
     provider_type: remote::vllm
     config:
-      url: ${env.VLLM_URL}
+      url: ${env.VLLM_URL:http://localhost:8000/v1}
       max_tokens: ${env.VLLM_MAX_TOKENS:4096}
       api_token: ${env.VLLM_API_TOKEN:fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:true}
diff --git a/llama_stack/templates/remote-vllm/run.yaml b/llama_stack/templates/remote-vllm/run.yaml
index b6bba1252..1f3cdfb39 100644
--- a/llama_stack/templates/remote-vllm/run.yaml
+++ b/llama_stack/templates/remote-vllm/run.yaml
@@ -15,7 +15,7 @@ providers:
   - provider_id: vllm-inference
     provider_type: remote::vllm
     config:
-      url: ${env.VLLM_URL}
+      url: ${env.VLLM_URL:http://localhost:8000/v1}
       max_tokens: ${env.VLLM_MAX_TOKENS:4096}
       api_token: ${env.VLLM_API_TOKEN:fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:true}
diff --git a/llama_stack/templates/remote-vllm/vllm.py b/llama_stack/templates/remote-vllm/vllm.py
index ba0dacae0..0f6c7659e 100644
--- a/llama_stack/templates/remote-vllm/vllm.py
+++ b/llama_stack/templates/remote-vllm/vllm.py
@@ -45,7 +45,7 @@ def get_distribution_template() -> DistributionTemplate:
         provider_id="vllm-inference",
         provider_type="remote::vllm",
         config=VLLMInferenceAdapterConfig.sample_run_config(
-            url="${env.VLLM_URL}",
+            url="${env.VLLM_URL:http://localhost:8000/v1}",
         ),
     )
     embedding_provider = Provider(