diff --git a/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/__tests__/index.spec.tsx b/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/__tests__/index.spec.tsx
index 58765f81404..dbcda3cd91e 100644
--- a/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/__tests__/index.spec.tsx
+++ b/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/__tests__/index.spec.tsx
@@ -388,16 +388,26 @@ describe('ModelParameterModal', () => {
     expect(screen.getByText(/debugAsSingleModel/i)).toBeInTheDocument()
   })
 
-  it('should append the first token timeout parameter only in workflow advanced mode', () => {
-    render(<ModelParameterModal {...defaultProps} isAdvancedMode isInWorkflow />)
+  it('should append the first token timeout parameter when the panel supports it', () => {
+    render(
+      <ModelParameterModal
+        {...defaultProps}
+        isAdvancedMode
+        isInWorkflow
+        supportFirstTokenTimeout
+      />,
+    )
 
     openSettings()
 
     expect(screen.getByTestId('param-first_token_timeout_ms')).toBeInTheDocument()
   })
 
-  it('should not append the first token timeout parameter outside workflow', () => {
-    render(<ModelParameterModal {...defaultProps} isAdvancedMode />)
+  it('should not append the first token timeout parameter for workflow panels that do not support it', () => {
+    // Being in a workflow is not enough: panels whose model config is not consumed
+    // by fetch_model_config (knowledge retrieval, tool/trigger model params) must
+    // not render a dead setting.
+    render(<ModelParameterModal {...defaultProps} isAdvancedMode isInWorkflow />)
 
     openSettings()
 
diff --git a/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/index.tsx b/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/index.tsx
index 1d30756a1f9..69f583df234 100644
--- a/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/index.tsx
+++ b/web/app/components/header/account-setting/model-provider-page/model-parameter-modal/index.tsx
@@ -40,6 +40,10 @@ export type ModelParameterModalProps = {
   renderTrigger?: (v: TriggerProps) => ReactNode
   readonly?: boolean
   isInWorkflow?: boolean
+  // Only LLM-compatible node panels (LLM / question classifier / parameter
+  // extractor) should pass this: the backend consumes the value solely on
+  // their model-config path, so rendering it elsewhere yields dead config.
+  supportFirstTokenTimeout?: boolean
   scope?: string
   nodesOutputVars?: NodeOutPutVar[]
   availableNodes?: Node[]
@@ -59,6 +63,7 @@ const ModelParameterModal: FC<ModelParameterModalProps> = ({
   renderTrigger,
   readonly,
   isInWorkflow,
+  supportFirstTokenTimeout,
   nodesOutputVars,
   availableNodes,
 }) => {
@@ -223,7 +228,9 @@ const ModelParameterModal: FC<ModelParameterModalProps> = ({
                 [
                   ...parameterRules,
                   ...(isAdvancedMode ? [STOP_PARAMETER_RULE] : []),
-                  ...(isAdvancedMode && isInWorkflow ? [FIRST_TOKEN_TIMEOUT_PARAMETER_RULE] : []),
+                  ...(isAdvancedMode && supportFirstTokenTimeout
+                    ? [FIRST_TOKEN_TIMEOUT_PARAMETER_RULE]
+                    : []),
                 ].map((parameter) => (
                   <ParameterItem
                     key={`${modelId}-${parameter.name}`}
diff --git a/web/app/components/workflow/nodes/llm/panel.tsx b/web/app/components/workflow/nodes/llm/panel.tsx
index 528bd928694..659ccaf2175 100644
--- a/web/app/components/workflow/nodes/llm/panel.tsx
+++ b/web/app/components/workflow/nodes/llm/panel.tsx
@@ -117,6 +117,7 @@ const Panel: FC<NodePanelProps<LLMNodeType>> = ({ id, data }) => {
             popupClassName="w-[387px]!"
             isInWorkflow
             isAdvancedMode={true}
+            supportFirstTokenTimeout
             provider={model?.provider}
             completionParams={model?.completion_params}
             modelId={model?.name}
diff --git a/web/app/components/workflow/nodes/parameter-extractor/panel.tsx b/web/app/components/workflow/nodes/parameter-extractor/panel.tsx
index 8453b8b0188..11b43212775 100644
--- a/web/app/components/workflow/nodes/parameter-extractor/panel.tsx
+++ b/web/app/components/workflow/nodes/parameter-extractor/panel.tsx
@@ -61,6 +61,7 @@ const Panel: FC<NodePanelProps<ParameterExtractorNodeType>> = ({ id, data }) =>
             popupClassName="w-[387px]!"
             isInWorkflow
             isAdvancedMode={true}
+            supportFirstTokenTimeout
             provider={model?.provider}
             completionParams={model?.completion_params}
             modelId={model?.name}
diff --git a/web/app/components/workflow/nodes/question-classifier/panel.tsx b/web/app/components/workflow/nodes/question-classifier/panel.tsx
index ed7d78ca69d..4c9bfc39157 100644
--- a/web/app/components/workflow/nodes/question-classifier/panel.tsx
+++ b/web/app/components/workflow/nodes/question-classifier/panel.tsx
@@ -50,6 +50,7 @@ const Panel: FC<NodePanelProps<QuestionClassifierNodeType>> = ({ id, data }) =>
             popupClassName="w-[387px]!"
             isInWorkflow
             isAdvancedMode={true}
+            supportFirstTokenTimeout
             provider={model?.provider}
             completionParams={model.completion_params}
             modelId={model.name}
diff --git a/web/config/index.ts b/web/config/index.ts
index bf1a48c10e4..5c520db8b76 100644
--- a/web/config/index.ts
+++ b/web/config/index.ts
@@ -337,8 +337,9 @@ export const FIRST_TOKEN_TIMEOUT_PARAMETER_RULE: ModelParameterRule = {
   precision: 0,
   help: {
     en_US:
-      'Max milliseconds to wait for the first streamed token. On timeout the node fails; combine with node retry to re-run it automatically.',
-    zh_Hans: '等待首个流式 Token 的最长毫秒数。超时后节点失败，可配合节点重试自动重跑。',
+      'Max milliseconds to wait for the first streamed token; the same window also bounds each gap between tokens. On timeout the node fails; combine with node retry to re-run it automatically.',
+    zh_Hans:
+      '等待首个流式 Token 的最长毫秒数；同一窗口也约束后续每次 Token 间隔。超时后节点失败，可配合节点重试自动重跑。',
   },
   label: {
     en_US: 'First token timeout (ms)',