diff --git a/gpt4all-api/gpt4all_api/app/api_v1/routes/chat.py b/gpt4all-api/gpt4all_api/app/api_v1/routes/chat.py
index aeccbd49..eec597bf 100644
--- a/gpt4all-api/gpt4all_api/app/api_v1/routes/chat.py
+++ b/gpt4all-api/gpt4all_api/app/api_v1/routes/chat.py
@@ -50,7 +50,7 @@ async def chat_completion(request: ChatCompletionRequest):
     # GPU is not implemented yet
     if settings.inference_mode == "gpu":
         raise HTTPException(status_code=400,
-              detail=f"Not implemented yet: Can only infere in CPU mode.")
+              detail=f"Not implemented yet: Can only infer in CPU mode.")
 
     # we only support the configured model
     if request.model != settings.model: