diff --git a/docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb b/docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb
index 561e3bd7ec..d346d035f1 100644
--- a/docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb
+++ b/docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb
@@ -134,7 +134,7 @@
     "from langchain_nvidia_ai_endpoints import ChatNVIDIA\n",
     "\n",
     "# connect to an embedding NIM running at localhost:8000, specifying a specific model\n",
-    "llm = ChatNVIDIA(base_url=\"http://localhost:8000/v1\", model=\"meta-llama3-8b-instruct\")"
+    "llm = ChatNVIDIA(base_url=\"http://localhost:8000/v1\", model=\"meta/llama3-8b-instruct\")"
    ]
   },
   {
@@ -658,7 +658,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.2"
   }
  },
  "nbformat": 4,
diff --git a/docs/docs/integrations/providers/nvidia.mdx b/docs/docs/integrations/providers/nvidia.mdx
index 0e9fa2e9dd..70f1123c41 100644
--- a/docs/docs/integrations/providers/nvidia.mdx
+++ b/docs/docs/integrations/providers/nvidia.mdx
@@ -62,7 +62,7 @@ When ready to deploy, you can self-host models with NVIDIA NIM—which is includ
 from langchain_nvidia_ai_endpoints import ChatNVIDIA, NVIDIAEmbeddings, NVIDIARerank
 
 # connect to an chat NIM running at localhost:8000, specifyig a specific model
-llm = ChatNVIDIA(base_url="http://localhost:8000/v1", model="meta-llama3-8b-instruct")
+llm = ChatNVIDIA(base_url="http://localhost:8000/v1", model="meta/llama3-8b-instruct")
 
 # connect to an embedding NIM running at localhost:8080
 embedder = NVIDIAEmbeddings(base_url="http://localhost:8080/v1")