diff --git a/examples/server/public/completion.js b/examples/server/public/completion.js
index 987b9a3b8..36818f764 100644
--- a/examples/server/public/completion.js
+++ b/examples/server/public/completion.js
@@ -21,7 +21,7 @@ let generation_settings = null;
 //
 export async function* llama(prompt, params = {}, config = {}) {
   let controller = config.controller;
-  const api_url = config.api_url || "";
+  const api_url = config.api_url?.replace(/\/+$/, '') || "";
 
   if (!controller) {
     controller = new AbortController();
@@ -196,7 +196,7 @@ export const llamaComplete = async (params, controller, callback) => {
 // Get the model info from the server. This is useful for getting the context window and so on.
 export const llamaModelInfo = async (config = {}) => {
   if (!generation_settings) {
-    const api_url = config.api_url || "";
+    const api_url = config.api_url?.replace(/\/+$/, '') || "";
     const props = await fetch(`${api_url}/props`).then(r => r.json());
     generation_settings = props.default_generation_settings;
   }
diff --git a/examples/server/public/index.html b/examples/server/public/index.html
index 2f60a76e8..a15424613 100644
--- a/examples/server/public/index.html
+++ b/examples/server/public/index.html
@@ -479,7 +479,7 @@
         throw new Error("already running");
       }
       controller.value = new AbortController();
-      for await (const chunk of llama(prompt, llamaParams, { controller: controller.value, api_url: location.pathname.replace(/\/+$/, '') })) {
+      for await (const chunk of llama(prompt, llamaParams, { controller: controller.value, api_url: URL.parse('.', document.baseURI).href })) {
         const data = chunk.data;
 
         if (data.stop) {