diff --git a/docs-site/src/content/docs/guides/providers.md b/docs-site/src/content/docs/guides/providers.md
index 0986a883c0..76bc5b90b8 100644
--- a/docs-site/src/content/docs/guides/providers.md
+++ b/docs-site/src/content/docs/guides/providers.md
@@ -764,6 +764,12 @@ Select **Zhipu AI — BigModel Coding Plan (Responses)** (`zhipu-bigmodel-respon
 for the `openai-responses` endpoint `https://open.bigmodel.cn/api/v1`. This is separate
 from `zhipu-bigmodel-coding`, which uses Chat Completions at `/api/coding/paas/v4`.
 
+Both Coding Plan presets use the existing domestic quota monitor with the raw API key
+in `Authorization` and refuse redirects. A custom noncanonical destination remains
+unsupported by that quota probe. Quota-reader support does not expand the Responses
+model roster or establish Flash/model-discovery support; those require separate
+endpoint-specific evidence.
+
 The preset uses a **static roster** (`liveModels: false`) taken from the
 [official BigModel Codex example](https://docs.bigmodel.cn/cn/coding-plan/tool/codex.md):
 
diff --git a/src/providers/quota.ts b/src/providers/quota.ts
index 08da6d24ac..4f2876f9ba 100644
--- a/src/providers/quota.ts
+++ b/src/providers/quota.ts
@@ -2906,7 +2906,8 @@ function keyQuotaReaderForProvider(name: string, provider: OcxProviderConfig): K
   if (name === "deepseek" && isCanonicalDeepSeekBaseUrl(provider.baseUrl)) return fetchDeepSeekQuota;
   if (name === "cline-pass" && isCanonicalClineBaseUrl(provider.baseUrl)) return fetchClineQuota;
   if (isCanonicalOllamaCloudBaseUrl(provider.baseUrl ?? getProviderRegistryEntry(name)?.baseUrl)) return fetchOllamaCloudQuota;
-  if (["zai", "glm", "glm-cn", "zhipu-bigmodel-coding"].includes(name) && isCanonicalZaiBaseUrl(provider.baseUrl)) return fetchZaiQuota;
+  // The domestic Responses preset uses the same Coding Plan monitor, not model discovery.
+  if (["zai", "glm", "glm-cn", "zhipu-bigmodel-coding", "zhipu-bigmodel-responses"].includes(name) && isCanonicalZaiBaseUrl(provider.baseUrl)) return fetchZaiQuota;
   if (["minimax", "minimax-cn"].includes(name) && isCanonicalMinimaxBaseUrl(provider.baseUrl)) return fetchMinimaxQuota;
   if (name === "moonshot" && isCanonicalMoonshotBaseUrl(provider.baseUrl)) return fetchMoonshotQuota;
   if (name === "venice" && isCanonicalVeniceBaseUrl(provider.baseUrl)) return fetchVeniceQuota;
diff --git a/tests/providers/provider-quota.test.ts b/tests/providers/provider-quota.test.ts
index a8d4bef728..f67e0763ba 100644
--- a/tests/providers/provider-quota.test.ts
+++ b/tests/providers/provider-quota.test.ts
@@ -1077,12 +1077,12 @@ describe("fetchProviderQuotaReports", () => {
     expect(seen[0]?.url).toBe("https://api.z.ai/api/monitor/usage/quota/limit");
   });
 
-  test("Z.AI quota probes the BigModel Responses endpoint at /api/v1", async () => {
-    const seen: Array<{ url: string; authorization?: string }> = [];
+  test.each(["zhipu-bigmodel-coding", "zhipu-bigmodel-responses"])("Z.AI quota probes BigModel /api/v1 for %s", async name => {
+    const seen: Array<{ url: string; authorization?: string; redirect?: RequestRedirect }> = [];
     globalThis.fetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
       const url = String(input);
       const headers = init?.headers as Record<string, string> | undefined;
-      seen.push({ url, authorization: headers?.Authorization });
+      seen.push({ url, authorization: headers?.Authorization, redirect: init?.redirect });
       return new Response(JSON.stringify({
         success: true,
         data: {
@@ -1095,10 +1095,9 @@ describe("fetchProviderQuotaReports", () => {
       }), { status: 200 });
     }) as typeof fetch;
 
-    const result = await fetchProviderQuotaReports(
-      keyQuotaConfig("zhipu-bigmodel-coding", "https://open.bigmodel.cn/api/v1", "zai-secret"),
-      true,
-    );
+    const config = keyQuotaConfig(name, "https://open.bigmodel.cn/api/v1", "zai-secret");
+    config.providers[name]!.adapter = name === "zhipu-bigmodel-responses" ? "openai-responses" : "openai-chat";
+    const result = await fetchProviderQuotaReports(config, true);
 
     expect(result.reports).toHaveLength(1);
     expect(result.reports[0]?.source).toBe("zai:quota-limit");
@@ -1110,6 +1109,23 @@ describe("fetchProviderQuotaReports", () => {
     expect(seen).toHaveLength(1);
     expect(seen[0]?.url).toBe("https://open.bigmodel.cn/api/monitor/usage/quota/limit");
     expect(seen[0]?.authorization).toBe("zai-secret");
+    expect(seen[0]?.redirect).toBe("error");
+  });
+
+  test.each([
+    "https://gateway.example.test/api/v1",
+    "https://open.bigmodel.cn/api/paas/v4",
+  ])("BigModel Responses quota does not probe unsupported destination %s", async baseUrl => {
+    let calls = 0;
+    globalThis.fetch = (async () => {
+      calls += 1;
+      return new Response("unexpected", { status: 500 });
+    }) as typeof fetch;
+    const config = keyQuotaConfig("zhipu-bigmodel-responses", baseUrl);
+    config.providers["zhipu-bigmodel-responses"]!.adapter = "openai-responses";
+
+    expect((await fetchProviderQuotaReports(config, true)).reports).toEqual([]);
+    expect(calls).toBe(0);
   });
 
   test("Z.AI quota treats an unsuccessful payload as a no-report", async () => {