diff --git a/docs/providers/nvidia.md b/docs/providers/nvidia.md
index 2a590f024c2..693a51db9b3 100644
--- a/docs/providers/nvidia.md
+++ b/docs/providers/nvidia.md
@@ -12,11 +12,12 @@ NVIDIA provides an OpenAI-compatible API at `https://integrate.api.nvidia.com/v1
 
 ## CLI setup
 
-Export the key once, then run onboarding without an inline secret:
+Export the key once, then run onboarding and set an NVIDIA model:
 
 ```bash
 export NVIDIA_API_KEY="nvapi-..."
-openclaw onboard --auth-choice apiKey --token-provider nvidia
+openclaw onboard --auth-choice skip
+openclaw models set nvidia/nvidia/llama-3.1-nemotron-70b-instruct
 ```
 
 If you still pass `--token`, remember it lands in shell history and `ps` output; prefer the env var when possible.
@@ -36,7 +37,7 @@ If you still pass `--token`, remember it lands in shell history and `ps` output;
   },
   agents: {
     defaults: {
-      model: { primary: "nvidia/llama-3.1-nemotron-70b-instruct" },
+      model: { primary: "nvidia/nvidia/llama-3.1-nemotron-70b-instruct" },
     },
   },
 }
@@ -45,7 +46,7 @@ If you still pass `--token`, remember it lands in shell history and `ps` output;
 ## Model IDs
 
 - `nvidia/llama-3.1-nemotron-70b-instruct` (default)
-- `nvidia/llama-3.3-70b-instruct`
+- `meta/llama-3.3-70b-instruct`
 - `nvidia/mistral-nemo-minitron-8b-8k-instruct`
 
 ## Notes
diff --git a/src/agents/models-config.providers.nvidia.test.ts b/src/agents/models-config.providers.nvidia.test.ts
index fcb9885e6e5..42a46ebe4a1 100644
--- a/src/agents/models-config.providers.nvidia.test.ts
+++ b/src/agents/models-config.providers.nvidia.test.ts
@@ -59,7 +59,7 @@ describe("NVIDIA provider", () => {
     const provider = buildNvidiaProvider();
     const modelIds = provider.models.map((m) => m.id);
     expect(modelIds).toContain("nvidia/llama-3.1-nemotron-70b-instruct");
-    expect(modelIds).toContain("nvidia/llama-3.3-70b-instruct");
+    expect(modelIds).toContain("meta/llama-3.3-70b-instruct");
     expect(modelIds).toContain("nvidia/mistral-nemo-minitron-8b-8k-instruct");
   });
 });
diff --git a/src/agents/models-config.providers.ts b/src/agents/models-config.providers.ts
index 717726117c3..393b333e250 100644
--- a/src/agents/models-config.providers.ts
+++ b/src/agents/models-config.providers.ts
@@ -635,8 +635,8 @@ export function buildNvidiaProvider(): ProviderConfig {
         maxTokens: NVIDIA_DEFAULT_MAX_TOKENS,
       },
       {
-        id: "nvidia/llama-3.3-70b-instruct",
-        name: "NVIDIA Llama 3.3 70B Instruct",
+        id: "meta/llama-3.3-70b-instruct",
+        name: "Meta Llama 3.3 70B Instruct",
         reasoning: false,
         input: ["text"],
         cost: NVIDIA_DEFAULT_COST,