feat(usage): plan:kimi_coding 兼容 kimi-code 0.43.1 quota 用量模型

服务端 api.kimi.com/coding/v1/usages 已由绝对 used/limit 行切换为
quota 模型（usages.limit_5h/limit_7d/limit_month_total/limit_month_code，
条目为 used_ratio 0-1 比率 + reset_time），见上游 #3787。

- parse_kimi_coding 优先解析新结构，旧 limits/usage 结构保留为回退
- used_ratio >1 时按已是百分数处理（防御）
- 新 tier id month_code + 前端 planLabel/i18n 中英文案
- 新增 3 个测试：四窗口解析 / 比率防御 / 空窗口回退旧结构

src-tauri/src/services/coding_plan.rs

@@ -16,11 +16,13 @@ use super::usage_types::{UsageData, UsageResult};
 use std::time::Duration;
 
 // 套餐类 tier id 的唯一来源：所有套餐供应商（Kimi/智谱/MiniMax/OpenCode Go 及
-// 未来新增）都只用这三个 id。前端 src/lib/usage-display.ts 的 planLabel() 依赖
+// 未来新增）都只用这四个 id。前端 src/lib/usage-display.ts 的 planLabel() 依赖
 // 此约定做本地化映射——新增 tier id 时必须同步加映射。
 const TIER_FIVE_HOUR: &str = "five_hour";
 const TIER_WEEKLY_LIMIT: &str = "weekly_limit";
 const TIER_MONTHLY_LIMIT: &str = "monthly_limit";
+/// Kimi quota 模型的月度代码窗口（kimi-code #3787 后 `limit_month_code`）。
+const TIER_MONTH_CODE: &str = "month_code";
 
 /// 套餐条目的统一构造：按百分比表示用量。
 fn percent_tier(name: &str, used_percent: f64, resets_at: Option<String>) -> UsageData {
@@ -70,8 +72,12 @@ fn parse_f64(value: &serde_json::Value) -> Option<f64> {
 // GET {base_url}/usages
 //   默认 https://api.kimi.com/coding/v1/usages
 //   global: https://api.kimi.ai/coding/v1/usages
-// Response: { limits: [{ detail: { limit, remaining, resetTime } }],
+// Response（kimi-code #3787 / 0.43.1 起服务端切换为 quota 模型）:
-//             usage: { limit, remaining, resetTime } }
+//   { usages: { limit_5h, limit_7d, limit_month_total, limit_month_code:
+//               { used_ratio: 0-1, reset_time?: ISO 8601 } },
+//     boosterWallet, goods_version }
+// 旧结构（兼容保留）: { limits: [{ detail: { limit, remaining, resetTime } }],
+//                     usage: { limit, remaining, resetTime } }
 
 /// 由 base_url 拼接 usages 查询 URL；base_url 为空/空白时回退大陆默认。
 /// 纯函数，便于单测。
@@ -95,8 +101,9 @@ pub async fn query_kimi_coding(
         Fetched::Body(body) => {
             let tiers = parse_kimi_coding(&body);
             if tiers.is_empty() {
-                // 响应里没有可解析的套餐档位（limits/usage 缺失或字段变了）。
+                // 响应里没有可解析的套餐档位（quota/usages 与旧 limits/usage
-                // 把原始响应（仅用量数字，无密钥）透出，方便对照接口结构修复。
+                // 均缺失或字段变了）。把原始响应（仅用量数字，无密钥）透出，
+                // 方便对照接口结构修复。
                 let preview = serde_json::to_string(&body)
                     .unwrap_or_else(|_| "<unserializable body>".into());
                 let trimmed: String = preview.chars().take(400).collect();
@@ -111,6 +118,11 @@ pub async fn query_kimi_coding(
 }
 
 fn parse_kimi_coding(body: &serde_json::Value) -> Vec<UsageData> {
+    // 新 quota 模型（kimi-code #3787 / 0.43.1 起服务端下发）：优先解析。
+    if let Some(tiers) = parse_kimi_quota(body) {
+        return tiers;
+    }
+
     let mut tiers = Vec::new();
 
     // 5 小时窗口限额（优先显示）
@@ -130,6 +142,30 @@ fn parse_kimi_coding(body: &serde_json::Value) -> Vec<UsageData> {
     tiers
 }
 
+/// 解析 quota 模型的 `usages` 窗口映射（`limit_5h` / `limit_7d` /
+/// `limit_month_total` / `limit_month_code`）。全部窗口缺失或无可解析
+/// 条目时返回 None，让调用方回退旧结构。
+fn parse_kimi_quota(body: &serde_json::Value) -> Option<Vec<UsageData>> {
+    let usages = body.get("usages")?;
+    let mut tiers = Vec::new();
+    for (key, tier) in [
+        ("limit_5h", TIER_FIVE_HOUR),
+        ("limit_7d", TIER_WEEKLY_LIMIT),
+        ("limit_month_total", TIER_MONTHLY_LIMIT),
+        ("limit_month_code", TIER_MONTH_CODE),
+    ] {
+        let Some(entry) = usages.get(key) else { continue };
+        let Some(ratio) = entry.get("used_ratio").and_then(parse_f64) else {
+            continue;
+        };
+        // used_ratio 规范为 0-1 比率；>1 时视为已是百分数，原样使用。
+        let used_percent = if ratio <= 1.0 { ratio * 100.0 } else { ratio };
+        let resets_at = entry.get("reset_time").and_then(extract_reset_time);
+        tiers.push(percent_tier(tier, used_percent, resets_at));
+    }
+    if tiers.is_empty() { None } else { Some(tiers) }
+}
+
 fn kimi_limit_tier(name: &str, detail: &serde_json::Value) -> UsageData {
     let limit = detail.get("limit").and_then(parse_f64).unwrap_or(1.0);
     let remaining = detail.get("remaining").and_then(parse_f64).unwrap_or(0.0);
@@ -459,6 +495,64 @@ mod tests {
         );
     }
 
+    #[test]
+    fn kimi_coding_quota_model_four_windows() {
+        // kimi-code #3787 / 0.43.1 起服务端下发的 quota 模型：used_ratio 为
+        // 0-1 比率，reset_time 为 ISO 8601 字符串。
+        let body = json!({
+            "goods_version": 3,
+            "usages": {
+                "limit_5h": { "used_ratio": 0.6, "reset_time": "2026-09-15T17:00:00Z" },
+                "limit_7d": { "used_ratio": 0.25 },
+                "limit_month_total": { "used_ratio": 0.1, "reset_time": "2026-10-01T00:00:00Z" },
+                "limit_month_code": { "used_ratio": 0.88 }
+            },
+            "boosterWallet": { "balance": 0 }
+        });
+        let tiers = parse_kimi_coding(&body);
+        assert_eq!(tiers.len(), 4);
+        assert_eq!(tiers[0].plan_name.as_deref(), Some("five_hour"));
+        assert_eq!(tiers[0].used, Some(60.0));
+        assert_eq!(tiers[0].remaining, Some(40.0));
+        assert_eq!(tiers[0].total, Some(100.0));
+        assert_eq!(
+            tiers[0].resets_at.as_deref(),
+            Some("2026-09-15T17:00:00Z")
+        );
+        assert_eq!(tiers[1].plan_name.as_deref(), Some("weekly_limit"));
+        assert_eq!(tiers[1].used, Some(25.0));
+        assert!(tiers[1].resets_at.is_none());
+        assert_eq!(tiers[2].plan_name.as_deref(), Some("monthly_limit"));
+        assert_eq!(tiers[2].used, Some(10.0));
+        assert_eq!(tiers[3].plan_name.as_deref(), Some("month_code"));
+        assert_eq!(tiers[3].used, Some(88.0));
+        assert_eq!(tiers[3].remaining, Some(12.0));
+    }
+
+    #[test]
+    fn kimi_coding_quota_ratio_above_one_is_percent() {
+        // 防御：>1 的 used_ratio 视为已是百分数，不再乘 100。
+        let body = json!({
+            "usages": { "limit_5h": { "used_ratio": 42.0 } }
+        });
+        let tiers = parse_kimi_coding(&body);
+        assert_eq!(tiers.len(), 1);
+        assert_eq!(tiers[0].used, Some(42.0));
+    }
+
+    #[test]
+    fn kimi_coding_quota_missing_windows_falls_back_to_legacy() {
+        // usages 存在但没有任何可解析条目 → 回退旧结构解析。
+        let body = json!({
+            "usages": { "limit_5h": {} },
+            "usage": { "limit": 1000, "remaining": 900, "resetTime": "2026-08-01T00:00:00Z" }
+        });
+        let tiers = parse_kimi_coding(&body);
+        assert_eq!(tiers.len(), 1);
+        assert_eq!(tiers[0].plan_name.as_deref(), Some("weekly_limit"));
+        assert_eq!(tiers[0].used, Some(10.0));
+    }
+
     #[test]
     fn kimi_coding_reset_time_seconds_vs_millis() {
         // 秒级时间戳自动 ×1000

src/i18n/en.ts

@@ -449,6 +449,7 @@ export const enTranslations: Record<TranslationKey, string> = {
   usageTierDaily: "Daily",
   usageTierWeekly: "Weekly",
   usageTierMonthly: "Monthly",
+  usageTierMonthCode: "Monthly (code)",
   usageErrNoKey: "No API key configured",
   usageErrDisabled: "Usage query is disabled in the config panel",
   usageErrLoginExpired: "Kimi Code login expired and auto-refresh failed; run `kimi login` again",

src/i18n/zh.ts

@@ -443,6 +443,7 @@ export const zhTranslations = {
   usageTierDaily: "每日",
   usageTierWeekly: "7天",
   usageTierMonthly: "30天",
+  usageTierMonthCode: "30天（代码）",
   usageErrNoKey: "未配置 API Key",
   usageErrDisabled: "用量查询已在配置面板中停用",
   usageErrLoginExpired: "Kimi Code 登录已过期且自动续期失败，请重新运行 `kimi login`",

src/lib/models-dev-full.json

@@ -1,5 +1,5 @@
 {
-  "last_updated": "2026-09-13",
+  "last_updated": "2026-09-14",
   "providers": {
     "subconscious": {
       "id": "subconscious",
@@ -16470,6 +16470,20 @@
           "output_limit": 32768,
           "image": true
         },
+        {
+          "id": "alibaba/deepseek-v4.1-flash",
+          "name": "DeepSeek V4.1 Flash (Alibaba Cloud)",
+          "cost": {
+            "input": 0.3,
+            "output": 1.2,
+            "cache_read": 0.03
+          },
+          "context": 1000000,
+          "output_limit": 393216,
+          "reasoning": true,
+          "tool_call": true,
+          "image": true
+        },
         {
           "id": "alibaba/qwen-coder-plus",
           "name": "Qwen Coder Plus (Alibaba Cloud)",
@@ -16730,7 +16744,7 @@
           "id": "scx-ai-gp/glm-5.2",
           "name": "GLM-5.2 (SCX.ai)",
           "cost": {
-            "input": 0.8,
+            "input": 0.88,
             "output": 2.55,
             "cache_read": 0.16
           },
@@ -18921,6 +18935,17 @@
           "reasoning": true,
           "tool_call": true
         },
+        {
+          "id": "consensusprotocol/deepseek-v4.1-flash",
+          "name": "DeepSeek V4.1 Flash (Consensus Protocol)",
+          "cost": {
+            "input": 0.2,
+            "output": 0.6,
+            "cache_read": 0.005
+          },
+          "context": 1048576,
+          "output_limit": 384000
+        },
         {
           "id": "consensusprotocol/glm-5.3-flash",
           "name": "GLM-5.3 Flash (Consensus Protocol)",
@@ -38111,9 +38136,9 @@
           "id": "gemma-4-26b-a4b-it",
           "name": "Gemma 4 26B A4B IT",
           "cost": {
-            "input": 0.102,
+            "input": 0.1,
-            "output": 0.356,
+            "output": 0.374,
-            "cache_read": 0.051
+            "cache_read": 0.05
           },
           "context": 256000,
           "output_limit": 25600,
@@ -38129,7 +38154,7 @@
             "output": 4.311648,
             "cache_read": 0.047907
           },
-          "context": 1048576,
+          "context": 1000000,
           "output_limit": 262144,
           "reasoning": true,
           "tool_call": true,
@@ -38195,9 +38220,9 @@
           "id": "minimax-m2.7",
           "name": "MiniMax-M2.7",
           "cost": {
-            "input": 0.396,
+            "input": 0.462,
-            "output": 1.464,
+            "output": 1.728,
-            "cache_read": 0.198
+            "cache_read": 0.231
           },
           "context": 262100,
           "output_limit": 6553,
@@ -38265,7 +38290,7 @@
           "cost": {
             "input": 0.2,
             "output": 0.4,
-            "cache_read": 0.04
+            "cache_write": 0.04
           },
           "context": 1000000,
           "output_limit": 384000,
@@ -38281,7 +38306,7 @@
             "output": 4.3552,
             "cache_read": 0.206872
           },
-          "context": 262000,
+          "context": 256000,
           "output_limit": 16000,
           "reasoning": true,
           "tool_call": true,
@@ -38305,12 +38330,12 @@
           "id": "deepseek-v4.1-flash",
           "name": "DeepSeek V4.1 Flash",
           "cost": {
-            "input": 0.3,
+            "input": 0.32664,
-            "output": 1.2,
+            "output": 1.30656,
-            "cache_read": 0.03
+            "cache_read": 0.032664
           },
-          "context": 1048576,
+          "context": 1000000,
-          "output_limit": 26214,
+          "output_limit": 13107,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true,
@@ -38425,9 +38450,9 @@
           "id": "glm-5",
           "name": "GLM-5",
           "cost": {
-            "input": 0.86,
+            "input": 0.94,
-            "output": 2.752,
+            "output": 3.008,
-            "cache_read": 0.43
+            "cache_read": 0.47
           },
           "context": 202752,
           "output_limit": 20275,
@@ -38452,9 +38477,9 @@
           "id": "kimi-k2.5",
           "name": "Kimi K2.5",
           "cost": {
-            "input": 0.5584,
+            "input": 0.5344,
-            "output": 2.935,
+            "output": 2.815,
-            "cache_read": 0.2792
+            "cache_read": 0.2672
           },
           "context": 262144,
           "output_limit": 26214,
@@ -38467,7 +38492,7 @@
           "name": "GLM-5.1",
           "cost": {
             "input": 1.318,
-            "output": 4.308,
+            "output": 4.268,
             "cache_read": 0.659
           },
           "context": 202750,
@@ -38496,7 +38521,7 @@
           "cost": {
             "input": 2.4,
             "output": 4.8,
-            "cache_read": 0.2
+            "cache_write": 0.2
           },
           "context": 1000000,
           "output_limit": 384000,
@@ -38508,9 +38533,9 @@
           "id": "gpt-oss-120b",
           "name": "GPT OSS 120B",
           "cost": {
-            "input": 0.168,
+            "input": 0.178,
-            "output": 0.66,
+            "output": 0.68,
-            "cache_read": 0.084
+            "cache_read": 0.089
           },
           "context": 128072,
           "output_limit": 13107,
@@ -65693,6 +65718,21 @@
           "tool_call": true,
           "structured_output": true
         },
+        {
+          "id": "Qwen/Qwen3.8-Flash",
+          "name": "Qwen3.8 Flash",
+          "cost": {
+            "input": 0.113,
+            "output": 0.382,
+            "cache_read": 0.0141
+          },
+          "context": 1000000,
+          "output_limit": 131072,
+          "tool_call": true,
+          "structured_output": true,
+          "image": true,
+          "video": true
+        },
         {
           "id": "Qwen/Qwen3-VL-235B-A22B-Instruct",
           "name": "Qwen3 VL 235B A22B Instruct",
@@ -66211,8 +66251,8 @@
             "input": 0.2275,
             "output": 0.91
           },
-          "context": 131072,
+          "context": 40960,
-          "output_limit": 8192,
+          "output_limit": 16384,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -66976,12 +67016,12 @@
           "id": "~deepseek/deepseek-v4-flash-latest",
           "name": "DeepSeek: DeepSeek V4 Flash Latest",
           "cost": {
-            "input": 0.0352,
+            "input": 0.04,
-            "output": 0.1056,
+            "output": 0.1,
-            "cache_read": 0.00112
+            "cache_read": 0.01
           },
           "context": 1048576,
-          "output_limit": 131072,
+          "output_limit": 393216,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -67591,7 +67631,7 @@
             "output": 0.45
           },
           "context": 262144,
-          "output_limit": 16384,
+          "output_limit": 235929,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -67641,8 +67681,8 @@
             "output": 2.2,
             "cache_read": 0.1
           },
-          "context": 256000,
+          "context": 202800,
-          "output_limit": 32768,
+          "output_limit": 182520,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -68842,7 +68882,8 @@
           "name": "MoonshotAI: Kimi Latest",
           "cost": {
             "input": 2.1,
-            "output": 10.95
+            "output": 10.95,
+            "cache_read": 0.23
           },
           "context": 1048576,
           "output_limit": 943718,
@@ -70605,12 +70646,12 @@
           "id": "~z-ai/glm-latest",
           "name": "Z.ai: GLM Latest",
           "cost": {
-            "input": 0.936,
+            "input": 0.92,
-            "output": 3.168,
+            "output": 3.1372,
-            "cache_read": 0.1872
+            "cache_read": 0.184
           },
-          "context": 262144,
+          "context": 1048576,
-          "output_limit": 235929,
+          "output_limit": 943718,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -70718,7 +70759,8 @@
           "name": "Inference.net: Schematron V2 Small",
           "cost": {
             "input": 0.05,
-            "output": 0.23
+            "output": 0.23,
+            "cache_read": 0.05
           },
           "context": 128000,
           "output_limit": 4096,
@@ -70729,7 +70771,8 @@
           "name": "Inference.net: Schematron V2 Turbo",
           "cost": {
             "input": 0.03,
-            "output": 0.15
+            "output": 0.15,
+            "cache_read": 0.03
           },
           "context": 128000,
           "output_limit": 8192,
@@ -70997,8 +71040,8 @@
             "output": 4.4,
             "cache_read": 0.26
           },
-          "context": 202752,
+          "context": 1048576,
-          "output_limit": 182476,
+          "output_limit": 131072,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -71095,8 +71138,8 @@
             "output": 4.4,
             "cache_read": 0.26
           },
-          "context": 1048576,
+          "context": 1048575,
-          "output_limit": 131072,
+          "output_limit": 943717,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -81488,11 +81531,11 @@
           "id": "qwen/qwen3-14b",
           "name": "Qwen3 14B",
           "cost": {
-            "input": 0.2275,
+            "input": 0.12,
-            "output": 0.91
+            "output": 0.24
           },
           "context": 131072,
-          "output_limit": 8192,
+          "output_limit": 16384,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -82261,12 +82304,12 @@
           "id": "~deepseek/deepseek-v4-flash-latest",
           "name": "DeepSeek V4 Flash Latest",
           "cost": {
-            "input": 0.0352,
+            "input": 0.04,
-            "output": 0.1056,
+            "output": 0.1,
-            "cache_read": 0.00112
+            "cache_read": 0.01
           },
           "context": 1310720,
-          "output_limit": 131072,
+          "output_limit": 393216,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -82859,11 +82902,11 @@
           "id": "nvidia/nemotron-3-super-120b-a12b",
           "name": "Nemotron 3 Super 120B A12B",
           "cost": {
-            "input": 0.085,
+            "input": 0.08,
-            "output": 0.4
+            "output": 0.45
           },
           "context": 262144,
-          "output_limit": 16384,
+          "output_limit": 235929,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -82909,12 +82952,12 @@
           "id": "nvidia/nemotron-3-ultra-550b-a55b",
           "name": "Nemotron 3 Ultra 550B A55B",
           "cost": {
-            "input": 0.625,
+            "input": 0.6,
-            "output": 3.125,
+            "output": 2.4,
-            "cache_read": 0.1875
+            "cache_read": 0.12
           },
           "context": 262144,
-          "output_limit": 32768,
+          "output_limit": 182520,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -84157,7 +84200,8 @@
           "name": "Kimi Latest",
           "cost": {
             "input": 2.1,
-            "output": 10.95
+            "output": 10.95,
+            "cache_read": 0.23
           },
           "context": 1048576,
           "output_limit": 943718,
@@ -84224,9 +84268,9 @@
           "id": "deepseek/deepseek-v4-pro-0813",
           "name": "DeepSeek V4 Pro 0813",
           "cost": {
-            "input": 0.57948,
+            "input": 0.9834,
-            "output": 1.73844,
+            "output": 2.9502,
-            "cache_read": 0.019316
+            "cache_read": 0.03278
           },
           "context": 1048576,
           "output_limit": 384000,
@@ -84238,9 +84282,9 @@
           "id": "deepseek/deepseek-v4-flash-0731",
           "name": "DeepSeek V4 Flash 0731",
           "cost": {
-            "input": 0.04,
+            "input": 0.06,
-            "output": 0.08,
+            "output": 0.12,
-            "cache_read": 0.008
+            "cache_read": 0.012
           },
           "context": 1310720,
           "output_limit": 943718,
@@ -84252,9 +84296,9 @@
           "id": "deepseek/deepseek-v4-flash",
           "name": "DeepSeek V4 Flash",
           "cost": {
-            "input": 0.04788,
+            "input": 0.08554,
-            "output": 0.09576,
+            "output": 0.17108,
-            "cache_read": 0.009576
+            "cache_read": 0.017108
           },
           "context": 1048576,
           "output_limit": 384000,
@@ -85829,12 +85873,12 @@
           "id": "~z-ai/glm-latest",
           "name": "GLM Latest",
           "cost": {
-            "input": 0.936,
+            "input": 0.92,
-            "output": 3.168,
+            "output": 3.1372,
-            "cache_read": 0.1872
+            "cache_read": 0.184
           },
           "context": 1310720,
-          "output_limit": 235929,
+          "output_limit": 943718,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -85942,7 +85986,8 @@
           "name": "Schematron V2 Small",
           "cost": {
             "input": 0.05,
-            "output": 0.23
+            "output": 0.23,
+            "cache_read": 0.05
           },
           "context": 128000,
           "output_limit": 4096,
@@ -85953,7 +85998,8 @@
           "name": "Schematron V2 Turbo",
           "cost": {
             "input": 0.03,
-            "output": 0.15
+            "output": 0.15,
+            "cache_read": 0.03
           },
           "context": 128000,
           "output_limit": 8192,
@@ -86062,9 +86108,9 @@
           "id": "tencent/hy3",
           "name": "Hy3",
           "cost": {
-            "input": 0.0825,
+            "input": 0.132,
-            "output": 0.33,
+            "output": 0.528,
-            "cache_read": 0.020625
+            "cache_read": 0.033
           },
           "context": 262144,
           "input_limit": 192000,
@@ -86217,12 +86263,12 @@
           "id": "z-ai/glm-5.2",
           "name": "GLM-5.2",
           "cost": {
-            "input": 0.6,
+            "input": 0.6832,
-            "output": 2,
+            "output": 2.1472,
-            "cache_read": 0.15
+            "cache_read": 0.12688
           },
           "context": 1048576,
-          "output_limit": 182476,
+          "output_limit": 131072,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -86231,9 +86277,9 @@
           "id": "z-ai/glm-5.3-flash",
           "name": "GLM-5.3-Flash",
           "cost": {
-            "input": 0.075,
+            "input": 0.15,
-            "output": 0.25,
+            "output": 0.5,
-            "cache_read": 0.015
+            "cache_read": 0.03
           },
           "context": 1310720,
           "output_limit": 131072,
@@ -86315,12 +86361,12 @@
           "id": "z-ai/glm-5.3",
           "name": "GLM-5.3",
           "cost": {
-            "input": 1.092,
+            "input": 1.4,
-            "output": 3.432,
+            "output": 4.4,
-            "cache_read": 0.2028
+            "cache_read": 0.26
           },
           "context": 1310720,
-          "output_limit": 131072,
+          "output_limit": 943717,
           "reasoning": true,
           "tool_call": true,
           "structured_output": true
@@ -102924,8 +102970,9 @@
           "id": "qwen/deepseek-v4-pro-0813",
           "name": "DeepSeek V4 Pro 0813 (Alibaba)",
           "cost": {
-            "input": 0.5808,
+            "input": 0.66,
-            "output": 1.7424
+            "output": 1.98,
+            "cache_read": 0.066
           },
           "context": 1000000,
           "output_limit": 384000,
@@ -102937,8 +102984,9 @@
           "id": "qwen/deepseek-v4-flash-0731",
           "name": "DeepSeek V4 Flash 0731 (Alibaba)",
           "cost": {
-            "input": 0.176,
+            "input": 0.22,
-            "output": 0.528
+            "output": 0.66,
+            "cache_read": 0.022
           },
           "context": 1000000,
           "output_limit": 384000,
@@ -103080,6 +103128,21 @@
           "output_limit": 8192,
           "reasoning": true
         },
+        {
+          "id": "qwen/deepseek-v4.1-flash",
+          "name": "DeepSeek V4.1 Flash (Alibaba)",
+          "cost": {
+            "input": 0.15,
+            "output": 0.6,
+            "cache_read": 0.015
+          },
+          "context": 1000000,
+          "output_limit": 384000,
+          "reasoning": true,
+          "tool_call": true,
+          "structured_output": true,
+          "image": true
+        },
         {
           "id": "qwen/qwen3-coder-next",
           "name": "Qwen3 Coder Next",
@@ -104143,6 +104206,20 @@
           "reasoning": true,
           "tool_call": true
         },
+        {
+          "id": "tensorx/deepseek/deepseek-v4.1-flash",
+          "name": "DeepSeek V4.1 Flash (TensorX)",
+          "cost": {
+            "input": 0.5,
+            "output": 1.5,
+            "cache_read": 0.125
+          },
+          "context": 1048576,
+          "output_limit": 384000,
+          "reasoning": true,
+          "tool_call": true,
+          "image": true
+        },
         {
           "id": "tensorx/moonshotai/kimi-k2.5",
           "name": "Kimi K2.5 (TensorX)",

src/lib/models-dev.json

@@ -1,5 +1,5 @@
 {
-  "last_updated": "2026-09-13",
+  "last_updated": "2026-09-14",
   "subconscious/subconscious/glm-5.2": {
     "name": "GLM-5.2",
     "context": 1000000,
@@ -13257,6 +13257,18 @@
       "cache_write": 0.25
     }
   },
+  "llmgateway-providers/alibaba/deepseek-v4.1-flash": {
+    "name": "DeepSeek V4.1 Flash (Alibaba Cloud)",
+    "context": 1000000,
+    "reasoning": true,
+    "tool_call": true,
+    "image": true,
+    "cost": {
+      "input": 0.3,
+      "output": 1.2,
+      "cache_read": 0.03
+    }
+  },
   "llmgateway-providers/alibaba/qwen-coder-plus": {
     "name": "Qwen Coder Plus (Alibaba Cloud)",
     "context": 131072,
@@ -13482,7 +13494,7 @@
     "reasoning": true,
     "tool_call": true,
     "cost": {
-      "input": 0.8,
+      "input": 0.88,
       "output": 2.55,
       "cache_read": 0.16
     }
@@ -15353,6 +15365,15 @@
       "cache_read": 0.01
     }
   },
+  "llmgateway-providers/consensusprotocol/deepseek-v4.1-flash": {
+    "name": "DeepSeek V4.1 Flash (Consensus Protocol)",
+    "context": 1048576,
+    "cost": {
+      "input": 0.2,
+      "output": 0.6,
+      "cache_read": 0.005
+    }
+  },
   "llmgateway-providers/consensusprotocol/glm-5.3-flash": {
     "name": "GLM-5.3 Flash (Consensus Protocol)",
     "context": 1048576,
@@ -31345,14 +31366,14 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.102,
+      "input": 0.1,
-      "output": 0.356,
+      "output": 0.374,
-      "cache_read": 0.051
+      "cache_read": 0.05
     }
   },
   "hyper/deepseek-v4-pro-0813": {
     "name": "DeepSeek V4 Pro 0813",
-    "context": 1048576,
+    "context": 1000000,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
@@ -31416,9 +31437,9 @@
     "reasoning": true,
     "tool_call": true,
     "cost": {
-      "input": 0.396,
+      "input": 0.462,
-      "output": 1.464,
+      "output": 1.728,
-      "cache_read": 0.198
+      "cache_read": 0.231
     }
   },
   "hyper/kimi-k2.6": {
@@ -31477,12 +31498,12 @@
     "cost": {
       "input": 0.2,
       "output": 0.4,
-      "cache_read": 0.04
+      "cache_write": 0.04
     }
   },
   "hyper/kimi-k2.7-code": {
     "name": "Kimi K2.7 Code",
-    "context": 262000,
+    "context": 256000,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
@@ -31506,15 +31527,15 @@
   },
   "hyper/deepseek-v4.1-flash": {
     "name": "DeepSeek V4.1 Flash",
-    "context": 1048576,
+    "context": 1000000,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
     "image": true,
     "cost": {
-      "input": 0.3,
+      "input": 0.32664,
-      "output": 1.2,
+      "output": 1.30656,
-      "cache_read": 0.03
+      "cache_read": 0.032664
     }
   },
   "hyper/qwen3.7-flash": {
@@ -31613,9 +31634,9 @@
     "reasoning": true,
     "tool_call": true,
     "cost": {
-      "input": 0.86,
+      "input": 0.94,
-      "output": 2.752,
+      "output": 3.008,
-      "cache_read": 0.43
+      "cache_read": 0.47
     }
   },
   "hyper/qwen3.8-max": {
@@ -31637,9 +31658,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.5584,
+      "input": 0.5344,
-      "output": 2.935,
+      "output": 2.815,
-      "cache_read": 0.2792
+      "cache_read": 0.2672
     }
   },
   "hyper/glm-5.1": {
@@ -31650,7 +31671,7 @@
     "structured_output": true,
     "cost": {
       "input": 1.318,
-      "output": 4.308,
+      "output": 4.268,
       "cache_read": 0.659
     }
   },
@@ -31675,7 +31696,7 @@
     "cost": {
       "input": 2.4,
       "output": 4.8,
-      "cache_read": 0.2
+      "cache_write": 0.2
     }
   },
   "hyper/gpt-oss-120b": {
@@ -31685,9 +31706,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.168,
+      "input": 0.178,
-      "output": 0.66,
+      "output": 0.68,
-      "cache_read": 0.084
+      "cache_read": 0.089
     }
   },
   "hyper/glm-5.3": {
@@ -54422,6 +54443,19 @@
       "output": 0.55
     }
   },
+  "deepinfra/Qwen/Qwen3.8-Flash": {
+    "name": "Qwen3.8 Flash",
+    "context": 1000000,
+    "tool_call": true,
+    "structured_output": true,
+    "image": true,
+    "video": true,
+    "cost": {
+      "input": 0.113,
+      "output": 0.382,
+      "cache_read": 0.0141
+    }
+  },
   "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": {
     "name": "Qwen3 VL 235B A22B Instruct",
     "context": 262144,
@@ -54852,7 +54886,7 @@
   },
   "kilo/qwen/qwen3-14b": {
     "name": "Qwen: Qwen3 14B",
-    "context": 131072,
+    "context": 40960,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
@@ -55512,9 +55546,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.0352,
+      "input": 0.04,
-      "output": 0.1056,
+      "output": 0.1,
-      "cache_read": 0.00112
+      "cache_read": 0.01
     }
   },
   "kilo/dots-studio/dots-3-note-preview:free": {
@@ -56067,7 +56101,7 @@
   },
   "kilo/nvidia/nemotron-3-ultra-550b-a55b": {
     "name": "Nemotron 3 Ultra 550B A55B",
-    "context": 256000,
+    "context": 202800,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
@@ -57115,7 +57149,8 @@
     "video": true,
     "cost": {
       "input": 2.1,
-      "output": 10.95
+      "output": 10.95,
+      "cache_read": 0.23
     }
   },
   "kilo/ibm-granite/granite-4.2-8b": {
@@ -58592,14 +58627,14 @@
   },
   "kilo/~z-ai/glm-latest": {
     "name": "Z.ai: GLM Latest",
-    "context": 262144,
+    "context": 1048576,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.936,
+      "input": 0.92,
-      "output": 3.168,
+      "output": 3.1372,
-      "cache_read": 0.1872
+      "cache_read": 0.184
     }
   },
   "kilo/moonshotai/kimi-k2-0905": {
@@ -58692,7 +58727,8 @@
     "structured_output": true,
     "cost": {
       "input": 0.05,
-      "output": 0.23
+      "output": 0.23,
+      "cache_read": 0.05
     }
   },
   "kilo/inference-net/schematron-v2-turbo": {
@@ -58701,7 +58737,8 @@
     "structured_output": true,
     "cost": {
       "input": 0.03,
-      "output": 0.15
+      "output": 0.15,
+      "cache_read": 0.03
     }
   },
   "kilo/cohere/north-mini-code:free": {
@@ -58919,7 +58956,7 @@
   },
   "kilo/z-ai/glm-5.2": {
     "name": "GLM-5.2",
-    "context": 202752,
+    "context": 1048576,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
@@ -59003,7 +59040,7 @@
   },
   "kilo/z-ai/glm-5.3": {
     "name": "GLM-5.3",
-    "context": 1048576,
+    "context": 1048575,
     "reasoning": true,
     "tool_call": true,
     "structured_output": true,
@@ -67739,8 +67776,8 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.2275,
+      "input": 0.12,
-      "output": 0.91
+      "output": 0.24
     }
   },
   "openrouter/qwen/qwen3.6-plus": {
@@ -68399,9 +68436,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.0352,
+      "input": 0.04,
-      "output": 0.1056,
+      "output": 0.1,
-      "cache_read": 0.00112
+      "cache_read": 0.01
     }
   },
   "openrouter/dots-studio/dots-3-note-preview:free": {
@@ -68906,8 +68943,8 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.085,
+      "input": 0.08,
-      "output": 0.4
+      "output": 0.45
     }
   },
   "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": {
@@ -68948,9 +68985,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.625,
+      "input": 0.6,
-      "output": 3.125,
+      "output": 2.4,
-      "cache_read": 0.1875
+      "cache_read": 0.12
     }
   },
   "openrouter/nvidia/nemotron-3-nano-30b-a3b": {
@@ -70028,7 +70065,8 @@
     "video": true,
     "cost": {
       "input": 2.1,
-      "output": 10.95
+      "output": 10.95,
+      "cache_read": 0.23
     }
   },
   "openrouter/ibm-granite/granite-4.2-8b": {
@@ -70083,9 +70121,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.57948,
+      "input": 0.9834,
-      "output": 1.73844,
+      "output": 2.9502,
-      "cache_read": 0.019316
+      "cache_read": 0.03278
     }
   },
   "openrouter/deepseek/deepseek-v4-flash-0731": {
@@ -70095,9 +70133,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.04,
+      "input": 0.06,
-      "output": 0.08,
+      "output": 0.12,
-      "cache_read": 0.008
+      "cache_read": 0.012
     }
   },
   "openrouter/deepseek/deepseek-v4-flash": {
@@ -70107,9 +70145,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.04788,
+      "input": 0.08554,
-      "output": 0.09576,
+      "output": 0.17108,
-      "cache_read": 0.009576
+      "cache_read": 0.017108
     }
   },
   "openrouter/deepseek/deepseek-v4.1-flash": {
@@ -71428,9 +71466,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.936,
+      "input": 0.92,
-      "output": 3.168,
+      "output": 3.1372,
-      "cache_read": 0.1872
+      "cache_read": 0.184
     }
   },
   "openrouter/moonshotai/kimi-k2-0905": {
@@ -71523,7 +71561,8 @@
     "structured_output": true,
     "cost": {
       "input": 0.05,
-      "output": 0.23
+      "output": 0.23,
+      "cache_read": 0.05
     }
   },
   "openrouter/inference-net/schematron-v2-turbo": {
@@ -71532,7 +71571,8 @@
     "structured_output": true,
     "cost": {
       "input": 0.03,
-      "output": 0.15
+      "output": 0.15,
+      "cache_read": 0.03
     }
   },
   "openrouter/cohere/north-mini-code:free": {
@@ -71625,9 +71665,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.0825,
+      "input": 0.132,
-      "output": 0.33,
+      "output": 0.528,
-      "cache_read": 0.020625
+      "cache_read": 0.033
     }
   },
   "openrouter/tencent/hy4-preview": {
@@ -71755,9 +71795,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.6,
+      "input": 0.6832,
-      "output": 2,
+      "output": 2.1472,
-      "cache_read": 0.15
+      "cache_read": 0.12688
     }
   },
   "openrouter/z-ai/glm-5.3-flash": {
@@ -71769,9 +71809,9 @@
     "image": true,
     "video": true,
     "cost": {
-      "input": 0.075,
+      "input": 0.15,
-      "output": 0.25,
+      "output": 0.5,
-      "cache_read": 0.015
+      "cache_read": 0.03
     }
   },
   "openrouter/z-ai/glm-4.5": {
@@ -71839,9 +71879,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 1.092,
+      "input": 1.4,
-      "output": 3.432,
+      "output": 4.4,
-      "cache_read": 0.2028
+      "cache_read": 0.26
     }
   },
   "openrouter/z-ai/glm-5v-turbo": {
@@ -85559,8 +85599,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.5808,
+      "input": 0.66,
-      "output": 1.7424
+      "output": 1.98,
+      "cache_read": 0.066
     }
   },
   "edenai/qwen/deepseek-v4-flash-0731": {
@@ -85570,8 +85611,9 @@
     "tool_call": true,
     "structured_output": true,
     "cost": {
-      "input": 0.176,
+      "input": 0.22,
-      "output": 0.528
+      "output": 0.66,
+      "cache_read": 0.022
     }
   },
   "edenai/qwen/qwen3-coder-plus": {
@@ -85688,6 +85730,19 @@
       "output": 2.4
     }
   },
+  "edenai/qwen/deepseek-v4.1-flash": {
+    "name": "DeepSeek V4.1 Flash (Alibaba)",
+    "context": 1000000,
+    "reasoning": true,
+    "tool_call": true,
+    "structured_output": true,
+    "image": true,
+    "cost": {
+      "input": 0.15,
+      "output": 0.6,
+      "cache_read": 0.015
+    }
+  },
   "edenai/qwen/qwen3-coder-next": {
     "name": "Qwen3 Coder Next",
     "context": 262144,
@@ -86603,6 +86658,18 @@
       "cache_read": 0.0625
     }
   },
+  "edenai/tensorx/deepseek/deepseek-v4.1-flash": {
+    "name": "DeepSeek V4.1 Flash (TensorX)",
+    "context": 1048576,
+    "reasoning": true,
+    "tool_call": true,
+    "image": true,
+    "cost": {
+      "input": 0.5,
+      "output": 1.5,
+      "cache_read": 0.125
+    }
+  },
   "edenai/tensorx/moonshotai/kimi-k2.5": {
     "name": "Kimi K2.5 (TensorX)",
     "context": 262144,

src/lib/usage-display.ts

@@ -11,9 +11,10 @@ type TranslateFn = (
  *
  * Coverage note: ALL plan-type (套餐) queries flow through
  * src-tauri/src/services/coding_plan.rs::percent_tier, whose names come only
- * from TIER_FIVE_HOUR / TIER_WEEKLY_LIMIT / TIER_MONTHLY_LIMIT — so this
+ * from TIER_FIVE_HOUR / TIER_WEEKLY_LIMIT / TIER_MONTHLY_LIMIT /
- * mapping covers every current and future plan provider automatically. If a
+ * TIER_MONTH_CODE — so this mapping covers every current and future plan
- * new tier id is ever added there, add a case here too.
+ * provider automatically. If a new tier id is ever added there, add a case
+ * here too.
  */
 export function planLabel(name: string, t: TranslateFn): string {
   switch (name) {
@@ -25,6 +26,8 @@ export function planLabel(name: string, t: TranslateFn): string {
       return t("usageTierWeekly");
     case "monthly_limit":
       return t("usageTierMonthly");
+    case "month_code":
+      return t("usageTierMonthCode");
     default:
       return name;
   }