diff --git a/packages/ui/src/lib/quota/providers/index.ts b/packages/ui/src/lib/quota/providers/index.ts
index a0261dc7..bcb942d1 100644
--- a/packages/ui/src/lib/quota/providers/index.ts
+++ b/packages/ui/src/lib/quota/providers/index.ts
@@ -14,6 +14,7 @@ export const QUOTA_PROVIDERS: QuotaProviderMeta[] = [
   { id: 'nano-gpt', name: 'NanoGPT' },
   { id: 'openrouter', name: 'OpenRouter' },
   { id: 'zai-coding-plan', name: 'z.ai' },
+  { id: 'zhipuai-coding-plan', name: 'Zhipu AI Coding Plan' },
   { id: 'minimax-cn-coding-plan', name: 'MiniMax Coding Plan (minimaxi.com)' },
   { id: 'minimax-coding-plan', name: 'MiniMax Coding Plan (minimax.io)' },
   { id: 'ollama-cloud', name: 'Ollama Cloud' },
diff --git a/packages/ui/src/types/quota.ts b/packages/ui/src/types/quota.ts
index 91ea729d..1ba803bb 100644
--- a/packages/ui/src/types/quota.ts
+++ b/packages/ui/src/types/quota.ts
@@ -9,6 +9,7 @@ export type QuotaProviderId =
   | 'nano-gpt'
   | 'openrouter'
   | 'zai-coding-plan'
+  | 'zhipuai-coding-plan'
   | 'minimax-coding-plan'
   | 'minimax-cn-coding-plan'
   | 'ollama-cloud'
diff --git a/packages/vscode/src/quotaProviders.ts b/packages/vscode/src/quotaProviders.ts
index 6d5c2aef..fd051e73 100644
--- a/packages/vscode/src/quotaProviders.ts
+++ b/packages/vscode/src/quotaProviders.ts
@@ -71,6 +71,36 @@ type ZaiPayload = {
   };
 };
 
+type ZhipuaiTokensLimit = {
+  type: 'TOKENS_LIMIT';
+  unit?: number;
+  number?: number;
+  nextResetTime?: number;
+  percentage?: number;
+};
+
+type ZhipuaiMcpTimeLimit = {
+  type: 'TIME_LIMIT';
+  unit?: number;
+  number?: number;
+  usage?: number;
+  currentValue?: number;
+  remaining?: number;
+  percentage?: number;
+  nextResetTime?: number;
+  usageDetails?: Array<{
+    modelCode?: string;
+    usage?: number;
+  }>;
+};
+
+type ZhipuaiPayload = {
+  data?: {
+    limits?: Array<ZhipuaiTokensLimit | ZhipuaiMcpTimeLimit>;
+    level?: string;
+  };
+};
+
 export type ProviderResult = {
   providerId: string;
   providerName: string;
@@ -355,6 +385,11 @@ export const listConfiguredQuotaProviders = () => {
     configured.add('zai-coding-plan');
   }
 
+  const zhipuaiAuth = normalizeAuthEntry(getAuthEntry(auth, ['zhipuai-coding-plan']));
+  if (zhipuaiAuth && ((zhipuaiAuth as Record<string, unknown>).key || (zhipuaiAuth as Record<string, unknown>).token)) {
+    configured.add('zhipuai-coding-plan');
+  }
+
   const kimiAuth = normalizeAuthEntry(getAuthEntry(auth, ['kimi-for-coding', 'kimi']));
   if (kimiAuth && ((kimiAuth as Record<string, unknown>).key || (kimiAuth as Record<string, unknown>).token)) {
     configured.add('kimi-for-coding');
@@ -1259,6 +1294,93 @@ export const fetchZaiQuota = async (): Promise<ProviderResult> => {
   }
 };
 
+export const fetchZhipuaiCodingPlanQuota = async (): Promise<ProviderResult> => {
+  const auth = readAuthFile();
+  const entry = normalizeAuthEntry(getAuthEntry(auth, ['zhipuai-coding-plan'])) as Record<string, unknown> | null;
+  const apiKey = (entry?.key as string | undefined) ?? (entry?.token as string | undefined);
+
+  if (!apiKey) {
+    return buildResult({
+      providerId: 'zhipuai-coding-plan',
+      providerName: 'Zhipu AI Coding Plan',
+      ok: false,
+      configured: false,
+      error: 'Not configured',
+    });
+  }
+
+  try {
+    const response = await fetch('https://open.bigmodel.cn/api/monitor/usage/quota/limit', {
+      method: 'GET',
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        'Content-Type': 'application/json',
+      },
+    });
+
+    if (!response.ok) {
+      return buildResult({
+        providerId: 'zhipuai-coding-plan',
+        providerName: 'Zhipu AI Coding Plan',
+        ok: false,
+        configured: true,
+        error: `API error: ${response.status}`,
+      });
+    }
+
+    const payload = await response.json() as ZhipuaiPayload;
+    const limits = Array.isArray(payload?.data?.limits) ? payload.data.limits : [];
+
+    const tokensLimit = limits.find((limit): limit is ZhipuaiTokensLimit => limit?.type === 'TOKENS_LIMIT');
+    const mcpToolsTimeLimit = limits.find((limit): limit is ZhipuaiMcpTimeLimit => limit?.type === 'TIME_LIMIT');
+
+    const windows: Record<string, UsageWindow> = {};
+
+    // Handle TOKENS_LIMIT (5-hour window for token usage)
+    if (tokensLimit) {
+      const windowSeconds = resolveWindowSeconds(tokensLimit);
+      const resetAt = tokensLimit?.nextResetTime ? normalizeTimestamp(tokensLimit.nextResetTime) : null;
+      const usedPercent = typeof tokensLimit?.percentage === 'number' ? tokensLimit.percentage : null;
+
+      windows['Tokens'] = toUsageWindow({
+        usedPercent,
+        windowSeconds,
+        resetAt,
+      });
+    }
+
+    // Handle TIME_LIMIT (MCP tools monthly window)
+    if (mcpToolsTimeLimit) {
+      // TIME_LIMIT unit=5 means 1 month (30 days)
+      const monthSeconds = 30 * 24 * 60 * 60;
+      const resetAt = mcpToolsTimeLimit?.nextResetTime ? normalizeTimestamp(mcpToolsTimeLimit.nextResetTime) : null;
+      const usedPercent = typeof mcpToolsTimeLimit?.percentage === 'number' ? mcpToolsTimeLimit.percentage : null;
+
+      windows['MCP Tools'] = toUsageWindow({
+        usedPercent,
+        windowSeconds: monthSeconds,
+        resetAt,
+      });
+    }
+
+    return buildResult({
+      providerId: 'zhipuai-coding-plan',
+      providerName: 'Zhipu AI Coding Plan',
+      ok: true,
+      configured: true,
+      usage: { windows },
+    });
+  } catch (error) {
+    return buildResult({
+      providerId: 'zhipuai-coding-plan',
+      providerName: 'Zhipu AI Coding Plan',
+      ok: false,
+      configured: true,
+      error: error instanceof Error ? error.message : 'Request failed',
+    });
+  }
+};
+
 const NANO_GPT_DAILY_WINDOW_SECONDS = 86400;
 
 export const fetchNanoGptQuota = async (): Promise<ProviderResult> => {
@@ -1384,6 +1506,8 @@ export const fetchQuotaForProvider = async (providerId: string): Promise<Provide
       return fetchOpenRouterQuota();
     case 'zai-coding-plan':
       return fetchZaiQuota();
+    case 'zhipuai-coding-plan':
+      return fetchZhipuaiCodingPlanQuota();
     default:
       return buildResult({
         providerId,
diff --git a/packages/web/server/lib/quota/DOCUMENTATION.md b/packages/web/server/lib/quota/DOCUMENTATION.md
index 78e14e0e..d1006119 100644
--- a/packages/web/server/lib/quota/DOCUMENTATION.md
+++ b/packages/web/server/lib/quota/DOCUMENTATION.md
@@ -26,6 +26,7 @@ These provider IDs are currently dispatchable via `fetchQuotaForProvider(provide
 | `nano-gpt` | NanoGPT | `providers/nanogpt.js` | `nano-gpt`, `nanogpt`, `nano_gpt` |
 | `openrouter` | OpenRouter | `providers/openrouter.js` | `openrouter` |
 | `zai-coding-plan` | z.ai | `providers/zai.js` | `zai-coding-plan`, `zai`, `z.ai` |
+| `zhipuai-coding-plan` | Zhipu AI Coding Plan | `providers/zhipuai-coding-plan.js` | `zhipuai-coding-plan` |
 | `minimax-coding-plan` | MiniMax Coding Plan (minimax.io) | `providers/minimax-coding-plan.js` | `minimax-coding-plan` |
 | `minimax-cn-coding-plan` | MiniMax Coding Plan (minimaxi.com) | `providers/minimax-cn-coding-plan.js` | `minimax-cn-coding-plan` |
 | `ollama-cloud` | Ollama Cloud | `providers/ollama-cloud.js` | Cookie file at `~/.config/ollama-quota/cookie` (raw session cookie string) |
diff --git a/packages/web/server/lib/quota/providers/index.js b/packages/web/server/lib/quota/providers/index.js
index 370cecd6..55fe8cfe 100644
--- a/packages/web/server/lib/quota/providers/index.js
+++ b/packages/web/server/lib/quota/providers/index.js
@@ -16,6 +16,7 @@ import * as nanogpt from './nanogpt.js';
 import * as openai from './openai.js';
 import * as openrouter from './openrouter.js';
 import * as zai from './zai.js';
+import * as zhipuaiCodingPlan from './zhipuai-coding-plan.js';
 import * as minimaxCodingPlan from './minimax-coding-plan.js';
 import * as minimaxCnCodingPlan from './minimax-cn-coding-plan.js';
 import * as ollamaCloud from './ollama-cloud.js';
@@ -46,6 +47,12 @@ const registry = {
     isConfigured: zai.isConfigured,
     fetchQuota: zai.fetchQuota
   },
+  'zhipuai-coding-plan': {
+    providerId: zhipuaiCodingPlan.providerId,
+    providerName: zhipuaiCodingPlan.providerName,
+    isConfigured: zhipuaiCodingPlan.isConfigured,
+    fetchQuota: zhipuaiCodingPlan.fetchQuota
+  },
   'kimi-for-coding': {
     providerId: kimi.providerId,
     providerName: kimi.providerName,
@@ -153,6 +160,7 @@ export const fetchCopilotAddonQuota = copilot.fetchQuotaAddon;
 export const fetchKimiQuota = kimi.fetchQuota;
 export const fetchOpenRouterQuota = openrouter.fetchQuota;
 export const fetchZaiQuota = zai.fetchQuota;
+export const fetchZhipuaiCodingPlanQuota = zhipuaiCodingPlan.fetchQuota;
 export const fetchNanoGptQuota = nanogpt.fetchQuota;
 export const fetchMinimaxCodingPlanQuota = minimaxCodingPlan.fetchQuota;
 export const fetchMinimaxCnCodingPlanQuota = minimaxCnCodingPlan.fetchQuota;
diff --git a/packages/web/server/lib/quota/providers/zhipuai-coding-plan.js b/packages/web/server/lib/quota/providers/zhipuai-coding-plan.js
new file mode 100644
index 00000000..82a0614e
--- /dev/null
+++ b/packages/web/server/lib/quota/providers/zhipuai-coding-plan.js
@@ -0,0 +1,133 @@
+/**
+ * Zhipu AI Coding Plan quota fetch
+ *
+ * API: https://open.bigmodel.cn/api/monitor/usage/quota/limit
+ *
+ * Response limits:
+ * - TOKENS_LIMIT: Token usage (5-hour rolling window)
+ * - TIME_LIMIT: MCP tools usage (monthly window)
+ *
+ * @typedef {Object} TokensLimit
+ * @property {string} type - 'TOKENS_LIMIT'
+ * @property {number} [unit]
+ * @property {number} [number]
+ * @property {number} [nextResetTime]
+ * @property {number} [percentage]
+ *
+ * @typedef {Object} McpToolsTimeLimit
+ * @property {string} type - 'TIME_LIMIT'
+ * @property {number} [unit]
+ * @property {number} [number]
+ * @property {number} [usage]
+ * @property {number} [currentValue]
+ * @property {number} [remaining]
+ * @property {number} [percentage]
+ * @property {number} [nextResetTime]
+ * @property {Array<{modelCode: string, usage: number}>} [usageDetails]
+ */
+import { readAuthFile } from '../../opencode/auth.js';
+import {
+  getAuthEntry,
+  normalizeAuthEntry,
+  buildResult,
+  toUsageWindow,
+  resolveWindowSeconds,
+  normalizeTimestamp
+} from '../utils/index.js';
+
+export const providerId = 'zhipuai-coding-plan';
+export const providerName = 'Zhipu AI Coding Plan';
+export const aliases = ['zhipuai-coding-plan'];
+
+export const isConfigured = () => {
+  const auth = readAuthFile();
+  const entry = normalizeAuthEntry(getAuthEntry(auth, aliases));
+  return Boolean(entry?.key || entry?.token);
+};
+
+export const fetchQuota = async () => {
+  const auth = readAuthFile();
+  const entry = normalizeAuthEntry(getAuthEntry(auth, aliases));
+  const apiKey = entry?.key ?? entry?.token;
+
+  if (!apiKey) {
+    return buildResult({
+      providerId,
+      providerName,
+      ok: false,
+      configured: false,
+      error: 'Not configured'
+    });
+  }
+
+  try {
+    const response = await fetch('https://open.bigmodel.cn/api/monitor/usage/quota/limit', {
+      method: 'GET',
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        'Content-Type': 'application/json'
+      }
+    });
+
+    if (!response.ok) {
+      return buildResult({
+        providerId,
+        providerName,
+        ok: false,
+        configured: true,
+        error: `API error: ${response.status}`
+      });
+    }
+
+    const payload = await response.json();
+    const limits = Array.isArray(payload?.data?.limits) ? payload.data.limits : [];
+
+    const tokensLimit = limits.find((limit) => limit?.type === 'TOKENS_LIMIT');
+    const mcpToolsTimeLimit = limits.find((limit) => limit?.type === 'TIME_LIMIT');
+
+    const windows = {};
+
+    // Handle TOKENS_LIMIT (5-hour window for token usage)
+    if (tokensLimit) {
+      const windowSeconds = resolveWindowSeconds(tokensLimit);
+      const resetAt = tokensLimit?.nextResetTime ? normalizeTimestamp(tokensLimit.nextResetTime) : null;
+      const usedPercent = typeof tokensLimit?.percentage === 'number' ? tokensLimit.percentage : null;
+
+      windows['Tokens'] = toUsageWindow({
+        usedPercent,
+        windowSeconds,
+        resetAt
+      });
+    }
+
+    // Handle TIME_LIMIT (MCP tools monthly window)
+    if (mcpToolsTimeLimit) {
+      // TIME_LIMIT unit=5 means 1 month (30 days)
+      const monthSeconds = 30 * 24 * 60 * 60;
+      const resetAt = mcpToolsTimeLimit?.nextResetTime ? normalizeTimestamp(mcpToolsTimeLimit.nextResetTime) : null;
+      const usedPercent = typeof mcpToolsTimeLimit?.percentage === 'number' ? mcpToolsTimeLimit.percentage : null;
+
+      windows['MCP Tools'] = toUsageWindow({
+        usedPercent,
+        windowSeconds: monthSeconds,
+        resetAt
+      });
+    }
+
+    return buildResult({
+      providerId,
+      providerName,
+      ok: true,
+      configured: true,
+      usage: { windows }
+    });
+  } catch (error) {
+    return buildResult({
+      providerId,
+      providerName,
+      ok: false,
+      configured: true,
+      error: error instanceof Error ? error.message : 'Request failed'
+    });
+  }
+};