diff --git a/docs/source/getting_started/distributions/self_hosted_distro/remote-vllm.md b/docs/source/getting_started/distributions/self_hosted_distro/remote-vllm.md
index db067c196..884e9a13c 100644
--- a/docs/source/getting_started/distributions/self_hosted_distro/remote-vllm.md
+++ b/docs/source/getting_started/distributions/self_hosted_distro/remote-vllm.md
@@ -107,7 +107,7 @@ docker run \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1 \
   --env SAFETY_MODEL=$SAFETY_MODEL \
-  --env VLLM_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT/v1
+  --env SAFETY_VLLM_URL=http://host.docker.internal:$SAFETY_PORT/v1
 ```
 
 
@@ -126,7 +126,7 @@ llama stack build --template remote-vllm --image-type conda
 llama stack run ./run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1
+  --env VLLM_URL=http://localhost:$INFERENCE_PORT/v1
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -138,7 +138,7 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 llama stack run ./run-with-safety.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1 \
+  --env VLLM_URL=http://localhost:$INFERENCE_PORT/v1 \
   --env SAFETY_MODEL=$SAFETY_MODEL \
-  --env VLLM_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT/v1
+  --env SAFETY_VLLM_URL=http://localhost:$SAFETY_PORT/v1
 ```
diff --git a/llama_stack/templates/remote-vllm/doc_template.md b/llama_stack/templates/remote-vllm/doc_template.md
index 88f5a6e2e..aca4fc643 100644
--- a/llama_stack/templates/remote-vllm/doc_template.md
+++ b/llama_stack/templates/remote-vllm/doc_template.md
@@ -99,7 +99,7 @@ docker run \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
   --env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1 \
   --env SAFETY_MODEL=$SAFETY_MODEL \
-  --env VLLM_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT/v1
+  --env SAFETY_VLLM_URL=http://host.docker.internal:$SAFETY_PORT/v1
 ```
 
 
@@ -118,7 +118,7 @@ llama stack build --template remote-vllm --image-type conda
 llama stack run ./run.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1
+  --env VLLM_URL=http://localhost:$INFERENCE_PORT/v1
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -130,7 +130,7 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 llama stack run ./run-with-safety.yaml \
   --port $LLAMA_STACK_PORT \
   --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1 \
+  --env VLLM_URL=http://localhost:$INFERENCE_PORT/v1 \
   --env SAFETY_MODEL=$SAFETY_MODEL \
-  --env VLLM_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT/v1
+  --env SAFETY_VLLM_URL=http://localhost:$SAFETY_PORT/v1
 ```