diff --git a/docs/my-website/docs/completion/usage.md b/docs/my-website/docs/completion/usage.md
index d65fc1e655f..ea41c166bb3 100644
--- a/docs/my-website/docs/completion/usage.md
+++ b/docs/my-website/docs/completion/usage.md
@@ -70,6 +70,8 @@ Or set the environment variable (no config file change needed):
 LITELLM_ENFORCE_STREAMED_USAGE=true
 ```
 
+> **Note:** This value is read once at server startup. Changing it at runtime has no effect — a server restart is required.
+
 Alternatively, configure it through the UI:
 
 1. Navigate to the LiteLLM Proxy UI
diff --git a/litellm/proxy/common_request_processing.py b/litellm/proxy/common_request_processing.py
index 55182cafe61..6331db18f5c 100644
--- a/litellm/proxy/common_request_processing.py
+++ b/litellm/proxy/common_request_processing.py
@@ -53,7 +53,8 @@ StreamChunkSerializer = Callable[[Any], str]
 # Type alias for streaming error serializer (ProxyException -> wire format)
 StreamErrorSerializer = Callable[[ProxyException], str]
 
-# Cached at module load time to avoid repeated env var lookups on every request
+# Cached at module load time to avoid repeated env var lookups on every request.
+# NOTE: changing this env var at runtime has no effect; a server restart is required.
 _ENFORCE_STREAMED_USAGE = (
     os.environ.get("LITELLM_ENFORCE_STREAMED_USAGE", "false").lower() == "true"
 )