diff --git a/ui/src/ui/views/chat.test.ts b/ui/src/ui/views/chat.test.ts
index 6fbc1a7e092..5cdeec46dfa 100644
--- a/ui/src/ui/views/chat.test.ts
+++ b/ui/src/ui/views/chat.test.ts
@@ -312,6 +312,34 @@ describe("chat view", () => {
     expect(container.textContent).not.toContain("757.3k / 200k");
   });
 
+  it("hides the context notice when totalTokens is missing even if inputTokens is high", () => {
+    const container = document.createElement("div");
+    render(
+      renderChat(
+        createProps({
+          sessions: {
+            ts: 0,
+            path: "",
+            count: 1,
+            defaults: { modelProvider: "openai", model: "gpt-5", contextTokens: 200_000 },
+            sessions: [
+              {
+                key: "main",
+                kind: "direct",
+                updatedAt: null,
+                inputTokens: 500_000,
+                contextTokens: 200_000,
+              },
+            ],
+          },
+        }),
+      ),
+      container,
+    );
+
+    expect(container.textContent).not.toContain("context used");
+  });
+
   it("uses the assistant avatar URL for the welcome state when the identity avatar is only initials", () => {
     const container = document.createElement("div");
     render(
diff --git a/ui/src/ui/views/chat.ts b/ui/src/ui/views/chat.ts
index 842b5e97914..1b40059c8b9 100644
--- a/ui/src/ui/views/chat.ts
+++ b/ui/src/ui/views/chat.ts
@@ -255,7 +255,7 @@ function renderContextNotice(
   session: GatewaySessionRow | undefined,
   defaultContextTokens: number | null,
 ) {
-  const used = session?.totalTokens ?? session?.inputTokens ?? 0;
+  const used = session?.totalTokens ?? 0;
   const limit = session?.contextTokens ?? defaultContextTokens ?? 0;
   if (!used || !limit) {
     return nothing;