diff --git a/packages/website/src/docs/features/model-integration/page.tsx b/packages/website/src/docs/features/model-integration/page.tsx
index 1d8b691..58f7ae6 100644
--- a/packages/website/src/docs/features/model-integration/page.tsx
+++ b/packages/website/src/docs/features/model-integration/page.tsx
@@ -4,25 +4,19 @@ import CodeEditor from '@/components/CodeEditor'
 
 // Recommended models: lightweight with excellent tool call capabilities
 const MODELS = {
-	recommended: [
-		'gpt-4.1-mini',
-		'claude-haiku-4.5',
-		'gemini-3-flash',
-		'deepseek-3.2',
-		'qwen-3-max',
-		'gpt-5.2',
-	],
+	recommended: ['gpt-4.1-mini', 'claude-haiku-4.5', 'gemini-3-flash', 'deepseek-3.2', 'gpt-5.2'],
 	verified: [
+		'qwen-3-max',
 		'gpt-4.1',
 		'gpt-5',
 		'gpt-5-mini',
 		'gpt-5.1',
 		'grok-4',
 		'grok-code-fast',
-		'qwen3-max',
 		'deepseek-v3.2',
 		'claude-sonnet-3.5',
 		'claude-sonnet-4.5',
+		'claude-opus-4.5',
 		'gemini-2.5',
 		'gemini-3-pro',
 	],
@@ -52,10 +46,10 @@ export default function ModelIntegration() {
 							return (
 								<div
 									key={model}
-									className={`px-3 py-1.5 rounded-md text-sm font-medium transition-colors ${
+									className={`px-3 py-1.5 rounded-md text-sm font-medium font-mono transition-colors ${
 										isRecommended
 											? 'bg-emerald-500 text-white shadow-sm'
-											: 'bg-white/60 dark:bg-gray-800/60 text-gray-700 dark:text-gray-300'
+											: 'bg-white/80 dark:bg-gray-800/80 text-gray-800 dark:text-gray-200 border border-gray-300 dark:border-gray-600'
 									}`}
 								>
 									{model}
@@ -64,6 +58,7 @@ export default function ModelIntegration() {
 							)
 						})}
 					</div>
+					<p className="text-xs text-gray-600 dark:text-gray-400 mt-5">⭐ baseline models</p>
 				</div>
 			</section>
 
diff --git a/packages/website/src/i18n/locales/en-US/docs.ts b/packages/website/src/i18n/locales/en-US/docs.ts
index d008eee..3c81c66 100644
--- a/packages/website/src/i18n/locales/en-US/docs.ts
+++ b/packages/website/src/i18n/locales/en-US/docs.ts
@@ -116,9 +116,9 @@ export default {
 		title: 'Model Integration',
 		subtitle:
 			'Supports models that comply with OpenAI API specification and support tool calls, including public cloud services and private deployments.',
-		recommendation_logic: 'Recommended: Lightweight models with strong ToolCall capabilities',
+		recommendation_logic: 'Recommended: Lightweight models with strong ToolCall capabilities.',
 		recommended: 'Recommended Models',
-		available: 'Available Models',
+		available: 'Tested Models',
 		available_verified: 'Verified Working Models',
 		tips: 'Tips',
 		tip_1: 'Reasoning models (like GPT-5) are slower with no advantage',
@@ -127,7 +127,7 @@ export default {
 		tip_3:
 			'Small models or those unable to handle complex tool definitions typically perform poorly',
 		security: '🔐 Production Authentication',
-		security_warning: '⚠️ Never commit real LLM API Keys to your frontend codebase',
+		security_warning: '⚠️ Never commit real LLM API Keys to your frontend code',
 		security_desc:
 			'In production environments, to hide the real LLM API Keys, we recommend the following architecture:',
 		security_backend_proxy: 'Backend Proxy Pattern',
diff --git a/packages/website/src/i18n/locales/zh-CN/docs.ts b/packages/website/src/i18n/locales/zh-CN/docs.ts
index c031062..92d57dd 100644
--- a/packages/website/src/i18n/locales/zh-CN/docs.ts
+++ b/packages/website/src/i18n/locales/zh-CN/docs.ts
@@ -114,9 +114,9 @@ export default {
 	model_integration: {
 		title: '模型接入',
 		subtitle: '当前支持符合 OpenAI 接口规范且支持 tool call 的模型,包括公有云服务和私有部署方案。',
-		recommendation_logic: '推荐使用 ToolCall 能力强的轻量级模型',
+		recommendation_logic: '推荐使用 ToolCall 能力强的轻量级模型。',
 		recommended: '推荐模型',
-		available: '可用模型',
+		available: '已测试模型',
 		available_verified: '已验证可用模型',
 		tips: '提示',
 		tip_1: 'reasoning 模型(如 GPT-5),速度偏慢,没有必要',
@@ -124,7 +124,7 @@ export default {
 			'ToolCall 能力较弱的模型可能返回错误的格式，常见错误能够自动恢复，建议设置较高的 temperature',
 		tip_3: '小模型或者无法适应复杂 Tool 定义的模型，通常效果不佳',
 		security: '🔐 生产环境鉴权建议',
-		security_warning: '⚠️ 永远不要把真实的 LLM API Key 发布到前端代码库',
+		security_warning: '⚠️ 永远不要把真实的 LLM API Key 发布到前端代码',
 		security_desc: '在实际应用中,为了隐藏真实的 LLM API Key，建议采用以下架构:',
 		security_backend_proxy: '后端代理转发',
 		security_backend_desc: