diff --git a/extensions/xiaomi/index.ts b/extensions/xiaomi/index.ts
index def263b1cda..8abce6866d1 100644
--- a/extensions/xiaomi/index.ts
+++ b/extensions/xiaomi/index.ts
@@ -2,6 +2,7 @@ import { definePluginEntry } from "openclaw/plugin-sdk/core";
 import { createProviderApiKeyAuthMethod } from "openclaw/plugin-sdk/provider-auth";
 import { buildSingleProviderApiKeyCatalog } from "openclaw/plugin-sdk/provider-catalog";
 import { PROVIDER_LABELS } from "openclaw/plugin-sdk/provider-usage";
+import { xiaomiMediaUnderstandingProvider } from "./media-understanding-provider.js";
 import { applyXiaomiConfig, XIAOMI_DEFAULT_MODEL_REF } from "./onboard.js";
 import { buildXiaomiProvider } from "./provider-catalog.js";
 
@@ -60,5 +61,6 @@ export default definePluginEntry({
         windows: [],
       }),
     });
+    api.registerMediaUnderstandingProvider(xiaomiMediaUnderstandingProvider);
   },
 });
diff --git a/extensions/xiaomi/media-understanding-provider.ts b/extensions/xiaomi/media-understanding-provider.ts
new file mode 100644
index 00000000000..4ec060e039a
--- /dev/null
+++ b/extensions/xiaomi/media-understanding-provider.ts
@@ -0,0 +1,122 @@
+import {
+  describeImageWithModel,
+  describeImagesWithModel,
+  type MediaUnderstandingProvider,
+  type VideoDescriptionRequest,
+  type VideoDescriptionResult,
+  assertOkOrThrowHttpError,
+  normalizeBaseUrl,
+  postJsonRequest,
+} from "openclaw/plugin-sdk/media-understanding";
+
+export const DEFAULT_XIAOMI_VIDEO_BASE_URL = "https://api.xiaomimimo.com/v1";
+const DEFAULT_XIAOMI_VIDEO_MODEL = "mimo-v2-omni";
+const DEFAULT_XIAOMI_VIDEO_PROMPT = "Describe the video.";
+
+type XiaomiVideoPayload = {
+  choices?: Array<{
+    message?: {
+      content?: string | Array<{ text?: string }>;
+      reasoning_content?: string;
+    };
+  }>;
+};
+
+function resolveModel(model?: string): string {
+  const trimmed = model?.trim();
+  return trimmed || DEFAULT_XIAOMI_VIDEO_MODEL;
+}
+
+function resolvePrompt(prompt?: string): string {
+  const trimmed = prompt?.trim();
+  return trimmed || DEFAULT_XIAOMI_VIDEO_PROMPT;
+}
+
+function coerceResponseText(payload: XiaomiVideoPayload): string | null {
+  const message = payload.choices?.[0]?.message;
+  if (!message) {
+    return null;
+  }
+  if (typeof message.content === "string" && message.content.trim()) {
+    return message.content.trim();
+  }
+  if (Array.isArray(message.content)) {
+    const text = message.content
+      .map((part) => (typeof part.text === "string" ? part.text.trim() : ""))
+      .filter(Boolean)
+      .join("\n")
+      .trim();
+    if (text) {
+      return text;
+    }
+  }
+  if (typeof message.reasoning_content === "string" && message.reasoning_content.trim()) {
+    return message.reasoning_content.trim();
+  }
+  return null;
+}
+
+export async function describeXiaomiVideo(
+  params: VideoDescriptionRequest,
+): Promise<VideoDescriptionResult> {
+  const fetchFn = params.fetchFn ?? fetch;
+  const baseUrl = normalizeBaseUrl(params.baseUrl, DEFAULT_XIAOMI_VIDEO_BASE_URL);
+  const model = resolveModel(params.model);
+  const mime = params.mime ?? "video/mp4";
+  const prompt = resolvePrompt(params.prompt);
+  const url = `${baseUrl}/chat/completions`;
+
+  const headers = new Headers(params.headers);
+  if (!headers.has("content-type")) {
+    headers.set("content-type", "application/json");
+  }
+  if (!headers.has("authorization")) {
+    headers.set("authorization", `Bearer ${params.apiKey}`);
+  }
+
+  const body = {
+    model,
+    messages: [
+      {
+        role: "user",
+        content: [
+          { type: "text", text: prompt },
+          {
+            type: "video_url",
+            video_url: {
+              url: `data:${mime};base64,${params.buffer.toString("base64")}`,
+            },
+          },
+        ],
+      },
+    ],
+  };
+
+  const { response: res, release } = await postJsonRequest({
+    url,
+    headers,
+    body,
+    timeoutMs: params.timeoutMs,
+    fetchFn,
+  });
+
+  try {
+    await assertOkOrThrowHttpError(res, "Xiaomi video description failed");
+    const payload = (await res.json()) as XiaomiVideoPayload;
+    const text = coerceResponseText(payload);
+    if (!text) {
+      throw new Error("Xiaomi video description response missing content");
+    }
+    return { text, model };
+  } finally {
+    await release();
+  }
+}
+
+export const xiaomiMediaUnderstandingProvider: MediaUnderstandingProvider = {
+  id: "xiaomi",
+  capabilities: ["image", "video"],
+  describeImage: describeImageWithModel,
+  describeImages: describeImagesWithModel,
+  describeVideo: describeXiaomiVideo,
+};