diff --git a/README.md b/README.md
index 6db724999a..42013bc650 100644
--- a/README.md
+++ b/README.md
@@ -183,7 +183,7 @@ const { generated_text } = await gpt2.textGeneration({inputs: 'The answer to the
 
 // Chat Completion
 const llamaEndpoint = inference.endpoint(
-  "https://router.huggingface.co/together/models/meta-llama/Llama-3.1-8B-Instruct"
+  "https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.1-8B-Instruct"
 );
 const out = await llamaEndpoint.chatCompletion({
   model: "meta-llama/Llama-3.1-8B-Instruct",
diff --git a/packages/inference/README.md b/packages/inference/README.md
index 5b16832bcc..b43db15982 100644
--- a/packages/inference/README.md
+++ b/packages/inference/README.md
@@ -611,7 +611,7 @@ const { generated_text } = await gpt2.textGeneration({inputs: 'The answer to the
 
 // Chat Completion Example
 const ep = hf.endpoint(
-  "https://router.huggingface.co/together/models/meta-llama/Llama-3.1-8B-Instruct"
+  "https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.1-8B-Instruct"
 );
 const stream = ep.chatCompletionStream({
   model: "tgi",