diff --git a/llms/mlx_lm/SERVER.md b/llms/mlx_lm/SERVER.md
index 2976a09fc..e544c6fa3 100644
--- a/llms/mlx_lm/SERVER.md
+++ b/llms/mlx_lm/SERVER.md
@@ -92,7 +92,7 @@ curl localhost:8080/v1/chat/completions \
 
 - `system_fingerprint`: A unique identifier for the system.
 
-- `object`: Any of "chat.completions", "chat.completions.chunk" (for
+- `object`: Any of "chat.completion", "chat.completion.chunk" (for
   streaming), or "text.completion".
 
 - `model`: The model repo or path (e.g. `"mlx-community/Llama-3.2-3B-Instruct-4bit"`).
diff --git a/llms/mlx_lm/server.py b/llms/mlx_lm/server.py
index badc6dd37..ce09cf45c 100644
--- a/llms/mlx_lm/server.py
+++ b/llms/mlx_lm/server.py
@@ -589,9 +589,7 @@ def handle_chat_completions(self) -> List[int]:
 
         # Determine response type
         self.request_id = f"chatcmpl-{uuid.uuid4()}"
-        self.object_type = (
-            "chat.completions.chunk" if self.stream else "chat.completions"
-        )
+        self.object_type = "chat.completion.chunk" if self.stream else "chat.completion"
         if (
             hasattr(self.tokenizer, "apply_chat_template")
             and self.tokenizer.chat_template