diff --git a/src/providers/anthropic.rs b/src/providers/anthropic.rs
index 726503e..e595820 100644
--- a/src/providers/anthropic.rs
+++ b/src/providers/anthropic.rs
@@ -261,7 +261,7 @@ impl LLMProvider for AnthropicProvider {
         request: ChatCompletionRequest,
     ) -> Result<ChatCompletionResponse, Box<dyn std::error::Error + Send + Sync>> {
         let url = format!("{}/v1/messages", self.base_url);
-        let max_tokens = request.max_tokens.or(self.max_tokens).unwrap_or(1024);
+        let max_tokens = request.max_tokens.or(self.max_tokens).unwrap_or(8192);
 
         tracing::info!(
             provider = %self.name,
diff --git a/web/src/components/Settings/tabs/ModelsTab.tsx b/web/src/components/Settings/tabs/ModelsTab.tsx
index 30342a0..49a0513 100644
--- a/web/src/components/Settings/tabs/ModelsTab.tsx
+++ b/web/src/components/Settings/tabs/ModelsTab.tsx
@@ -47,12 +47,11 @@ export function ModelsTab({ config, update }: TabProps) {
                   editors.patch(name, { temperature: e.target.value ? +e.target.value : undefined })
                 }
                 className={inputCls}
-                placeholder="0.7"
               />
             </Field>
             <Field
               label="Max Tokens"
-              hint="模型单次回复最大生成 token 数，超出会被截断。留空则不传该字段（Anthropic 型 provider 会回退为 1024）"
+              hint="模型单次回复最大生成 token 数，超出会被截断。留空则不传该字段（Anthropic 型 provider 会回退为 8192）"
             >
               <input
                 type="number"