diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9ee0658a5a4..b02280869bb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -70,6 +70,7 @@ Docs: https://docs.openclaw.ai
 - Plugins/runtime deps: isolate the internal npm cache used for bundled plugin runtime-dependency repair and let package updates refresh/verify already-current installs, so failed update or sudo doctor runs can be repaired by rerunning `openclaw update`. Thanks @steipete.
 - Agents/delete: keep `--json` output machine-readable and retain workspaces that overlap another agent's workspace instead of moving shared state to Trash. Fixes #70889 and #70890. (#70897) Thanks @kaseonedge.
 - Browser/screenshot: honor `timeoutMs` through host and node screenshot requests, bound raw CDP screenshot commands, and avoid beyond-viewport CDP capture for ordinary viewport screenshots, so Windows Chrome captures no longer hang past the requested deadline. Fixes #68330. Thanks @Woodylai24.
+- Telegram/model picker: show configured model display names when browsing models through provider buttons, matching typed `/models <provider>` output. Fixes #70560. (#71016) Thanks @iskim77.
 - Plugins/runtime deps: stage bundled plugin runtime dependencies for packaged/global installs in an external runtime root and retain already staged deps across repairs, avoiding package-tree update races and npm pruning after upgrades. Thanks @steipete.
 - Plugins/runtime deps: log bundled plugin runtime-dependency staging before synchronous npm installs start and include elapsed timing afterward, so first boot after upgrades no longer looks hung while dependencies are being repaired. Thanks @steipete.
 - Agents/failover: forward embedded run abort signals into provider-owned model streams, cap implicit LLM idle watchdogs below long run timeouts, and mark 429 responses without usable retry timing as non-retryable so GitHub Copilot rate limits fail over or surface promptly instead of hanging until run timeout. Fixes #71120. Thanks @steipete.
diff --git a/extensions/telegram/src/bot.test.ts b/extensions/telegram/src/bot.test.ts
index a9ade8f7c10..dfdd017f50d 100644
--- a/extensions/telegram/src/bot.test.ts
+++ b/extensions/telegram/src/bot.test.ts
@@ -1072,6 +1072,84 @@ describe("createTelegramBot", () => {
     }
   });
 
+  it("renders model callback lists with configured display names", async () => {
+    onSpy.mockClear();
+    replySpy.mockClear();
+    editMessageTextSpy.mockClear();
+
+    const buildModelsProviderDataMock =
+      telegramBotDepsForTest.buildModelsProviderData as unknown as ReturnType<typeof vi.fn>;
+    buildModelsProviderDataMock.mockResolvedValueOnce({
+      byProvider: new Map<string, Set<string>>([["openai", new Set(["gpt-5", "gpt-4.1"])]]),
+      providers: ["openai"],
+      resolvedDefault: { provider: "openai", model: "gpt-5" },
+      modelNames: new Map<string, string>([
+        ["openai/gpt-4.1", "GPT 4.1 Bridge"],
+        ["openai/gpt-5", "GPT Five Bridge"],
+      ]),
+    });
+
+    const config = {
+      agents: {
+        defaults: {
+          model: "openai/gpt-5",
+        },
+      },
+      channels: {
+        telegram: {
+          dmPolicy: "open",
+          allowFrom: ["*"],
+        },
+      },
+    } satisfies NonNullable<Parameters<typeof createTelegramBot>[0]["config"]>;
+
+    loadConfig.mockReturnValue(config);
+    createTelegramBot({
+      token: "tok",
+      config,
+    });
+    const callbackHandler = onSpy.mock.calls.find((call) => call[0] === "callback_query")?.[1] as (
+      ctx: Record<string, unknown>,
+    ) => Promise<void>;
+    expect(callbackHandler).toBeDefined();
+
+    await callbackHandler({
+      callbackQuery: {
+        id: "cbq-model-display-names-1",
+        data: "mdl_list_openai_1",
+        from: { id: 9, first_name: "Ada", username: "ada_bot" },
+        message: {
+          chat: { id: 1234, type: "private" },
+          date: 1736380800,
+          message_id: 23,
+        },
+      },
+      me: { username: "openclaw_bot" },
+      getFile: async () => ({ download: async () => new Uint8Array() }),
+    });
+
+    expect(replySpy).not.toHaveBeenCalled();
+    expect(editMessageTextSpy).toHaveBeenCalledTimes(1);
+    const [, , , params] = editMessageTextSpy.mock.calls[0] ?? [];
+    const buttons = (
+      params as {
+        reply_markup?: {
+          inline_keyboard?: Array<Array<{ text?: string; callback_data?: string }>>;
+        };
+      }
+    ).reply_markup?.inline_keyboard?.flat();
+
+    expect(buttons).toContainEqual({
+      text: "GPT 4.1 Bridge",
+      callback_data: "mdl_sel_openai/gpt-4.1",
+    });
+    expect(buttons).toContainEqual({
+      text: "GPT Five Bridge ✓",
+      callback_data: "mdl_sel_openai/gpt-5",
+    });
+    expect(answerCallbackQuerySpy).toHaveBeenCalledWith("cbq-model-display-names-1");
+  });
+
   it("resets overrides when selecting the configured default model", async () => {
     onSpy.mockClear();
     replySpy.mockClear();