diff --git a/CHANGELOG.md b/CHANGELOG.md
index eb9bb4373e8..7ce3515f7cc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -289,7 +289,6 @@ Docs: https://docs.openclaw.ai
 - Models: support Anthropic Opus 4.6 and OpenAI Codex gpt-5.3-codex (forward-compat fallbacks). (#9853, #10720, #9995) Thanks @TinyTb, @calvin-hpnet, @tyler6204.
 - Providers: add xAI (Grok) support. (#9885) Thanks @grp06.
 - Providers: add Baidu Qianfan support. (#8868) Thanks @ide-rea.
-- Providers: add NVIDIA API support with models including Llama 3.1 Nemotron 70B, Llama 3.3 70B, and Mistral NeMo Minitron 8B.
 - Web UI: add token usage dashboard. (#10072) Thanks @Takhoffman.
 - Web UI: add RTL auto-direction support for Hebrew/Arabic text in chat composer and rendered messages. (#11498) Thanks @dirbalak.
 - Memory: native Voyage AI support. (#7078) Thanks @mcinteerj.
diff --git a/docs/nvidia.md b/docs/nvidia.md
deleted file mode 100644
index 2e988c050c9..00000000000
--- a/docs/nvidia.md
+++ /dev/null
@@ -1,107 +0,0 @@
----
-summary: "NVIDIA API setup for AI model access"
-read_when:
-  - You want to use NVIDIA's AI models
-  - You need NVIDIA_API_KEY setup
-title: "NVIDIA API"
----
-
-# NVIDIA API
-
-OpenClaw can use NVIDIA's API (https://integrate.api.nvidia.com/v1) for accessing various AI models. NVIDIA provides access to state-of-the-art language models through their integration endpoint.
-
-## API Setup
-
-### NVIDIA (direct)
-
-- Base URL: [https://integrate.api.nvidia.com/v1](https://integrate.api.nvidia.com/v1)
-- Environment variable: `NVIDIA_API_KEY`
-- Get your API key from: [NVIDIA NGC](https://catalog.ngc.nvidia.com/)
-
-## Config example
-
-```json5
-{
-  models: {
-    providers: {
-      nvidia: {
-        apiKey: "nvapi-...",
-        baseUrl: "https://integrate.api.nvidia.com/v1",
-      },
-    },
-  },
-  agents: {
-    default: {
-      provider: "nvidia",
-      model: "nvidia/llama-3.1-nemotron-70b-instruct",
-    },
-  },
-}
-```
-
-## Available Models
-
-OpenClaw includes support for several NVIDIA models:
-
-- `nvidia/llama-3.1-nemotron-70b-instruct` (default) — High-performance instruction-following model
-- `nvidia/llama-3.3-70b-instruct` — Latest Llama 3.3 variant
-- `nvidia/mistral-nemo-minitron-8b-8k-instruct` — Smaller, efficient model
-
-## Environment Variable Setup
-
-Set your NVIDIA API key as an environment variable:
-
-```bash
-export NVIDIA_API_KEY="nvapi-your-key-here"
-```
-
-Or add it to your `.env` file:
-
-```bash
-NVIDIA_API_KEY=nvapi-your-key-here
-```
-
-## Usage in Config
-
-Minimal configuration (uses environment variable):
-
-```json5
-{
-  agents: {
-    default: {
-      provider: "nvidia",
-      model: "nvidia/llama-3.1-nemotron-70b-instruct",
-    },
-  },
-}
-```
-
-Explicit API key configuration:
-
-```json5
-{
-  models: {
-    providers: {
-      nvidia: {
-        apiKey: "NVIDIA_API_KEY",
-        baseUrl: "https://integrate.api.nvidia.com/v1",
-        api: "openai-completions",
-      },
-    },
-  },
-}
-```
-
-## Professional and Personal Use
-
-NVIDIA's API is suitable for both professional and personal applications:
-
-- **Professional**: Enterprise-grade models for business applications, research, and development
-- **Personal**: Access to powerful AI models for learning, experimentation, and personal projects
-
-## Notes
-
-- NVIDIA API uses OpenAI-compatible endpoints
-- Models are automatically discovered if `NVIDIA_API_KEY` is set
-- Default context window: 131,072 tokens
-- Default max tokens: 4,096 tokens
diff --git a/docs/providers/index.md b/docs/providers/index.md
index 1b0ddcc2134..dbaeaeadf29 100644
--- a/docs/providers/index.md
+++ b/docs/providers/index.md
@@ -1,9 +1,9 @@
 ---
-summary: "Model providers (LLMs) supported by OpenClaw"
+summary: 'Model providers (LLMs) supported by OpenClaw'
 read_when:
   - You want to choose a model provider
   - You need a quick overview of supported LLM backends
-title: "Model Providers"
+title: 'Model Providers'
 ---
 
 # Model Providers
@@ -29,7 +29,7 @@ See [Venice AI](/providers/venice).
 
 ```json5
 {
-  agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
+  agents: { defaults: { model: { primary: 'anthropic/claude-opus-4-6' } } },
 }
 ```
 
@@ -55,6 +55,7 @@ See [Venice AI](/providers/venice).
 - [Ollama (local models)](/providers/ollama)
 - [vLLM (local models)](/providers/vllm)
 - [Qianfan](/providers/qianfan)
+- [NVIDIA](/providers/nvidia)
 
 ## Transcription providers
 
diff --git a/docs/providers/nvidia.md b/docs/providers/nvidia.md
new file mode 100644
index 00000000000..1faea0d8cd5
--- /dev/null
+++ b/docs/providers/nvidia.md
@@ -0,0 +1,51 @@
+---
+summary: "Use NVIDIA's OpenAI-compatible API in OpenClaw"
+read_when:
+  - You want to use NVIDIA models in OpenClaw
+  - You need NVIDIA_API_KEY setup
+title: 'NVIDIA'
+---
+
+# NVIDIA
+
+NVIDIA provides an OpenAI-compatible API at `https://integrate.api.nvidia.com/v1` for Nemotron and NeMo models. Authenticate with an API key from [NVIDIA NGC](https://catalog.ngc.nvidia.com/).
+
+## CLI setup
+
+```bash
+openclaw onboard --auth-choice apiKey --token-provider nvidia --token "$NVIDIA_API_KEY"
+```
+
+If `NVIDIA_API_KEY` is already exported, you can omit `--token`.
+
+## Config snippet
+
+```json5
+{
+  env: { NVIDIA_API_KEY: 'nvapi-...' },
+  models: {
+    providers: {
+      nvidia: {
+        baseUrl: 'https://integrate.api.nvidia.com/v1',
+        api: 'openai-completions',
+      },
+    },
+  },
+  agents: {
+    defaults: {
+      model: { primary: 'nvidia/llama-3.1-nemotron-70b-instruct' },
+    },
+  },
+}
+```
+
+## Model IDs
+
+- `nvidia/llama-3.1-nemotron-70b-instruct` (default)
+- `nvidia/llama-3.3-70b-instruct`
+- `nvidia/mistral-nemo-minitron-8b-8k-instruct`
+
+## Notes
+
+- OpenAI-compatible `/v1` endpoint; use an API key from NVIDIA NGC.
+- Provider auto-enables when `NVIDIA_API_KEY` is set; uses static defaults (131,072-token context window, 4,096 max tokens).
diff --git a/src/agents/model-auth.ts b/src/agents/model-auth.ts
index 045f7c6c3f6..187d3df6788 100644
--- a/src/agents/model-auth.ts
+++ b/src/agents/model-auth.ts
@@ -305,6 +305,7 @@ export function resolveEnvApiKey(provider: string): EnvApiKeyResult | null {
     "cloudflare-ai-gateway": "CLOUDFLARE_AI_GATEWAY_API_KEY",
     moonshot: "MOONSHOT_API_KEY",
     minimax: "MINIMAX_API_KEY",
+    nvidia: "NVIDIA_API_KEY",
     xiaomi: "XIAOMI_API_KEY",
     synthetic: "SYNTHETIC_API_KEY",
     venice: "VENICE_API_KEY",
diff --git a/src/agents/models-config.providers.nvidia.test.ts b/src/agents/models-config.providers.nvidia.test.ts
index e33e7212a6a..bbd655fe09f 100644
--- a/src/agents/models-config.providers.nvidia.test.ts
+++ b/src/agents/models-config.providers.nvidia.test.ts
@@ -2,7 +2,7 @@ import { mkdtempSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
 import { describe, expect, it } from "vitest";
-import { resolveImplicitProviders, buildNvidiaProvider } from "./models-config.providers.js";
+import { buildNvidiaProvider, resolveImplicitProviders } from "./models-config.providers.js";
 
 describe("NVIDIA provider", () => {
   it("should include nvidia when NVIDIA_API_KEY is configured", async () => {