fix: qwen3.8-max-preview is Token-Plan-only, not pay-as-you-go

v1.11.0 wrongly assumed qwen3.8-max-preview was callable on pay-as-you-go
DashScope and made it the pay-go `qwen` default. A pay-go key actually gets
403 Model.AccessDenied for it (verified: qwen3.7-max [OK], qwen3.8-max
[403] on the same key), and there is no self-serve activation — the preview
is delivered via the Token Plan subscription (sk-sp- keys) at launch.

- Remove the 3.8-max variant from the pay-as-you-go qwen provider; revert
  its default to 3.7-max, so `qwen`/`tongyi` resolve to a model that works.
- Keep qwen3.8-max-preview on the qwen-plan (subscription) provider only.
- Point the intuitive `qwen3.8` / `qwen3.8-max` aliases at qwen-plan-3.8-max
  (its only working home) instead of a dead pay-go key.
- Re-add a pay-go variant once Alibaba opens the preview to pay-as-you-go.

Evidence: dashscope 403 Model.AccessDenied = no permission for the model;
qianwenai.com Token Plan personal doc lists qwen3.8-max-preview under the
subscription; pay-as-you-go model list does not.

Author: 鲁工

README.md

@@ -197,9 +197,8 @@ ccmr claude --print --output-format json "你的问题"
 | `kimi-plan-for-coding-highspeed` | `kimi-plan-highspeed` | Kimi K2.7 Code HighSpeed（Allegretto 及以上） | Kimi Code 会员订阅 |
 | `minimax-m3` | `minimax`, `minimax-cn`, `mm` | MiniMax M3 | MiniMax CN |
 | `minimax-global-m3` | `minimax-global`, `minimax-io` | MiniMax M3 | MiniMax Global |
-| `qwen3.8-max` | `qwen`, `qwen3.8`, `tongyi` | Qwen3.8 Max (Preview) | 阿里云（按量付费） |
-| `qwen3.7-max` | `qwen-max`, `qwen3.7` | Qwen3.7 Max | 阿里云（按量付费） |
-| `qwen-plan-3.8-max` | `qwen-plan`, `qwen-plan-3.8`, `qwen-plan-max` | Qwen3.8 Max (Preview) | 千问 Token Plan（订阅） |
+| `qwen3.7-max` | `qwen`, `qwen-max`, `qwen3.7`, `tongyi` | Qwen3.7 Max | 阿里云（按量付费） |
+| `qwen-plan-3.8-max` | `qwen-plan`, `qwen-plan-3.8`, `qwen-plan-max`, `qwen3.8`, `qwen3.8-max` | Qwen3.8 Max (Preview) | 千问 Token Plan（订阅） |
 | `qwen-plan-3.7-max` | `qwen-plan-3.7` | Qwen3.7 Max | 千问 Token Plan（订阅） |
 | `glm-5.2` | `glm`, `zhipu`, `chatglm` | GLM-5.2 | 智谱 AI（国内） |
 | `glm-5.1` | `glm-5` | GLM-5.1 | 智谱 AI（国内） |
@@ -229,7 +228,7 @@ ccmr claude --print --output-format json "你的问题"
 | Kimi K3 (Coding Plan `kimi-plan-k3-1m` / `kimi-plan-k3`) | 1M / 256K（按档位） | 1M / 128K |
 | Kimi K2.7 Code / HighSpeed (Coding Plan) | 256K | 32K |
 | MiniMax M3 (CN / Global) | 1M | 128K |
-| Qwen3.8 Max Preview (按量付费 / Token Plan) | 1M | 64K |
+| Qwen3.8 Max Preview (仅 Token Plan) | 1M | 64K |
 | Qwen3.7 Max (按量付费 / Token Plan) | 1M | 64K |
 | GLM-5.2 (国内 / 国际) | 1M | 128K |
 | GLM-5.1 (国内 / 国际) | 200K | 128K |
@@ -407,8 +406,7 @@ npx claude-code-model-router claude
 ```bash
 # 使用短名称（向后兼容）
 /model deepseek   # 切换到 DeepSeek V4 Pro
-/model qwen       # 切换到 Qwen3.8 Max Preview（按量付费）
-/model qwen-max   # 切换到 Qwen3.7 Max（按量付费）
+/model qwen       # 切换到 Qwen3.7 Max（按量付费）
 /model qwen-plan  # 切换到 Qwen3.8 Max Preview（千问 Token Plan 订阅）
 /model glm        # 切换到 GLM-5.2（国内 智谱）
 /model glm-global # 切换到 GLM-5.2（国际 Z.ai）
@@ -439,9 +437,8 @@ npx claude-code-model-router claude
 /model kimi-k2.6                 # Kimi K2.6
 /model kimi-k2.7-code            # Kimi K2.7 Code
 /model kimi-k2.7-code-highspeed  # Kimi K2.7 Code HighSpeed
-/model qwen3.8-max               # Qwen3.8 Max Preview（按量付费）
 /model qwen3.7-max               # Qwen3.7 Max（按量付费）
-/model qwen-plan-3.8-max         # Qwen3.8 Max Preview（Token Plan 订阅）
+/model qwen-plan-3.8-max         # Qwen3.8 Max Preview（Token Plan 订阅；别名 qwen3.8 / qwen3.8-max）
 /model qwen-plan-3.7-max         # Qwen3.7 Max（Token Plan 订阅）
 /model seed-2.1-pro              # Doubao Seed 2.1 Pro（按量付费）
 /model seed-2.1-turbo            # Doubao Seed 2.1 Turbo（按量付费）
@@ -530,6 +527,13 @@ DeepSeek Anthropic 兼容接口会忽略 `metadata` 字段，但某些 Claude Co
 
 ## 更新日志
 
+### v1.11.1
+
+- 修正 v1.11.0 的一个错误假设：**`qwen3.8-max-preview` 目前仅通过千问 Token Plan（`sk-sp-` 订阅 Key）发放**，按量付费账号调用返回 `403 Model.AccessDenied`（权限问题，且无自助开通入口）。因此：
+  - 从按量付费 `qwen` provider 移除 `qwen3.8-max` 变体，默认改回 `qwen3.7-max`；裸别名 `qwen` / `tongyi` 回指 `qwen3.7-max`
+  - 3.8 仅保留在 `qwen-plan` provider（订阅可用）；别名 `qwen3.8` / `qwen3.8-max` 现指向 `qwen-plan-3.8-max`
+  - 待阿里将该预览开放到按量付费后，再恢复 pay-go 变体
+
 ### v1.11.0
 
 - 新增 **Qwen3.8 Max Preview**（`qwen3.8-max`，模型 ID `qwen3.8-max-preview`，阿里 2026-07-19 发布的 2.4T 旗舰预览版）：按量付费 `qwen` provider 的默认模型，裸别名 `qwen` / `tongyi` 现指向它；`qwen3.7-max`（别名 `qwen-max` / `qwen3.7`）保留

dist/config.d.ts.map

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-model-router",
-  "version": "1.11.0",
+  "version": "1.11.1",
   "description": "A lightweight API gateway for routing Claude Code requests to multiple AI models",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

dist/config.js

@@ -198,15 +198,12 @@ export const DEFAULT_CONFIG: RouterConfig = {
       auth_type: 'api_key',
       supports_streaming: true,
       supports_tools: true,
-      default_variant: '3.8-max',
+      default_variant: '3.7-max',
       variants: {
-        '3.8-max': {
-          model_key: 'qwen3.8-max',
-          display_name: 'Qwen3.8 Max',
-          model_id: 'qwen3.8-max-preview',
-          max_tokens: 65536,
-          context_window: 1000000,
-        },
+        // qwen3.8-max-preview is Token-Plan-only today; a pay-as-you-go key
+        // gets 403 Model.AccessDenied. It lives on the qwen-plan provider
+        // (sk-sp- subscription key) below, not here. Re-add a pay-go variant
+        // only once Alibaba opens the preview to pay-as-you-go.
         '3.7-max': {
           model_key: 'qwen3.7-max',
           display_name: 'Qwen3.7 Max',
@@ -527,13 +524,14 @@ export const DEFAULT_CONFIG: RouterConfig = {
     'minimax-io': 'minimax-global-m3',
     'minimax-global-m3': 'minimax-global-m3',
     mm: 'minimax-m3',
-    qwen: 'qwen3.8-max',
-    tongyi: 'qwen3.8-max',
-    'qwen3.8': 'qwen3.8-max',
-    'qwen3.8-max': 'qwen3.8-max',
+    qwen: 'qwen3.7-max',
+    tongyi: 'qwen3.7-max',
     'qwen-max': 'qwen3.7-max',
     'qwen3.7-max': 'qwen3.7-max',
     'qwen3.7': 'qwen3.7-max',
+    // qwen3.8-max-preview is reachable only via the Token Plan provider below.
+    'qwen3.8': 'qwen-plan-3.8-max',
+    'qwen3.8-max': 'qwen-plan-3.8-max',
     'qwen-plan': 'qwen-plan-3.8-max',
     'qwen-plan-3.8': 'qwen-plan-3.8-max',
     'qwen-plan-3.8-max': 'qwen-plan-3.8-max',
@@ -1287,14 +1285,9 @@ providers:
     api_key_env: QWEN_API_KEY
     auth_header: x-api-key
     auth_type: api_key
-    default_variant: 3.8-max
+    default_variant: 3.7-max
     variants:
-      3.8-max:
-        model_key: qwen3.8-max
-        display_name: "Qwen3.8 Max"
-        model_id: qwen3.8-max-preview
-        max_tokens: 65536
-        context_window: 1000000
+      # qwen3.8-max-preview 目前仅 Token Plan 发放，按量付费调用 403，见下方 qwen-plan
       3.7-max:
         model_key: qwen3.7-max
         display_name: "Qwen3.7 Max"
@@ -1557,13 +1550,13 @@ aliases:
   minimax-io: minimax-global-m3
   minimax-global-m3: minimax-global-m3
   mm: minimax-m3
-  qwen: qwen3.8-max
-  tongyi: qwen3.8-max
-  qwen3.8: qwen3.8-max
-  qwen3.8-max: qwen3.8-max
+  qwen: qwen3.7-max
+  tongyi: qwen3.7-max
   qwen-max: qwen3.7-max
   qwen3.7-max: qwen3.7-max
   qwen3.7: qwen3.7-max
+  qwen3.8: qwen-plan-3.8-max
+  qwen3.8-max: qwen-plan-3.8-max
   qwen-plan: qwen-plan-3.8-max
   qwen-plan-3.8: qwen-plan-3.8-max
   qwen-plan-3.8-max: qwen-plan-3.8-max

dist/config.js.map

@@ -149,21 +149,20 @@ describe('Kimi Code: coding-plan subscription provider', () => {
   });
 });
 
-describe('Qwen 3.8: flagship variant, 3.5 removal, and Token Plan provider', () => {
+describe('Qwen 3.8: Token-Plan-only, 3.5 removal, pay-go stays on 3.7', () => {
   const manager = new ConfigManager(null);
   const config = manager.getConfig();
 
-  it('exposes qwen3.8-max as the pay-as-you-go default and bare-alias target', () => {
-    const model = config.models['qwen3.8-max'];
+  it('keeps the pay-as-you-go qwen provider on 3.7-max (3.8 is not pay-go)', () => {
+    // qwen3.8-max-preview returns 403 on pay-as-you-go keys (Token-Plan-only),
+    // so it must NOT be a pay-go model; the bare qwen alias stays on 3.7.
+    expect(config.models['qwen3.8-max']).toBeUndefined();
+    const model = config.models['qwen3.7-max'];
     expect(model).toBeDefined();
-    expect(model.model_id).toBe('qwen3.8-max-preview');
-    expect(model.base_url).toBe('https://dashscope.aliyuncs.com/apps/anthropic');
+    expect(model.model_id).toBe('qwen3.7-max');
     expect(model.api_key_env).toBe('QWEN_API_KEY');
-    expect(model.max_tokens).toBe(65536);
-    expect(model.context_window).toBe(1000000);
-    // bare aliases now resolve to the new flagship; qwen-max stays on 3.7
-    expect(manager.resolveModelName('qwen')).toBe('qwen3.8-max');
-    expect(manager.resolveModelName('tongyi')).toBe('qwen3.8-max');
+    expect(manager.resolveModelName('qwen')).toBe('qwen3.7-max');
+    expect(manager.resolveModelName('tongyi')).toBe('qwen3.7-max');
     expect(manager.resolveModelName('qwen-max')).toBe('qwen3.7-max');
   });
 
@@ -174,16 +173,20 @@ describe('Qwen 3.8: flagship variant, 3.5 removal, and Token Plan provider', ()
     expect(config.models[manager.resolveModelName('qwen3.5')]).toBeUndefined();
   });
 
-  it('exposes the Token Plan subscription as its own provider and key', () => {
+  it('serves qwen3.8-max-preview only through the Token Plan provider', () => {
     // sk-sp- keys from platform.qianwenai.com hit the same DashScope Anthropic
-    // endpoint but bill against the subscription -> a separate provider/key.
+    // endpoint but bill against the subscription -> a separate provider/key,
+    // and the only place the preview model actually resolves.
     const model = config.models['qwen-plan-3.8-max'];
     expect(model).toBeDefined();
     expect(model.model_id).toBe('qwen3.8-max-preview');
     expect(model.base_url).toBe('https://dashscope.aliyuncs.com/apps/anthropic');
     expect(model.api_key_env).toBe('QWEN_PLAN_API_KEY');
     expect(model.auth_type).toBe('api_key');
     expect(manager.resolveModelName('qwen-plan')).toBe('qwen-plan-3.8-max');
+    // the intuitive 3.8 names route to the subscription model (its only home)
+    expect(manager.resolveModelName('qwen3.8')).toBe('qwen-plan-3.8-max');
+    expect(manager.resolveModelName('qwen3.8-max')).toBe('qwen-plan-3.8-max');
     expect(config.models['qwen-plan-3.7-max'].model_id).toBe('qwen3.7-max');
     expect(config.models['qwen-plan-3.7-max'].api_key_env).toBe('QWEN_PLAN_API_KEY');
   });