@@ -36,8 +36,8 @@ Freebuff includes a curated model catalog. The regular picker currently offers:
 | --------------------------- | ----------------------- | ----------------------------------------------------------------- |
 | **MiMo v2.6 Flash Fast**    | Full and limited access | The default everywhere; balanced performance with image support   |
 | **GLM 5.3 Flash**           | Full and limited access | Deepest reasoning, unmetered                                      |
-| **DeepSeek V4.1 Flash** | Full and limited access | Fast coding and tool use, unmetered                               |
-| **DeepSeek V4.1 Flash Fast** | Full access; paid plans at limited access | Fast mode: the same model on DeepSeek's own API, splitting work across parallel subagents and verifying the result; priced on DeepSeek's peak and off-peak hours |
+| **DeepSeek V4.1 Flash 10/17** | Full and limited access | Fast coding and tool use, unmetered                               |
+| **DeepSeek V4.1 Flash Fast 10/17** | Full access; paid plans at limited access | Fast mode: the same model on DeepSeek's own API, splitting work across parallel subagents and verifying the result; priced on DeepSeek's peak and off-peak hours |
 | **GPT-6 Luna**              | Full access             | Strong all-around with native images; runs on OpenAI flex capacity |
 | **MiMo 2.6 Pro**            | Full access             | Xiaomi's stronger reasoning model, with image support |
 | **Solar Mini 4**            | Full and limited access | Upstage's fast, compact model; 524K context, text only |
@@ -70,7 +70,7 @@ Freebuff uses specialized agents instead of sending every task through one model
 
 ## Free access
 
-Freebuff is available in every country. Supported regions receive full access; other regions and VPN users receive limited access to GLM 5.3 Flash, DeepSeek V4.1 Flash, MiMo v2.6 Flash Fast, Solar Mini 4, and Solar Pro 4. Every model is paid for in hours at the multiplier shown in the picker: an hour of MiMo v2.6 Flash Slow uses one hour of balance, a 3x model uses three. The free limited-access allowance is 5 hours a day, or 4 on a VPN or proxy, spent first on every model, GLM included; earned hours go into your wallet and are used after it. (Balances read in hours since 2026-10-15; 1 hour = 5 Freebucks.)
+Freebuff is available in every country. Supported regions receive full access; other regions and VPN users receive limited access to GLM 5.3 Flash, DeepSeek V4.1 Flash 10/17, MiMo v2.6 Flash Fast, Solar Mini 4, and Solar Pro 4. Every model is paid for in hours at the multiplier shown in the picker: an hour of MiMo v2.6 Flash Slow uses one hour of balance, a 3x model uses three. The free limited-access allowance is 5 hours a day, or 4 on a VPN or proxy, spent first on every model, GLM included; earned hours go into your wallet and are used after it. (Balances read in hours since 2026-10-15; 1 hour = 5 Freebucks.)
 
 Text ads support the included models. Freebuff shows the applicable session limits and any model-specific data-use notice before you start.
 
 
@@ -36,8 +36,8 @@ Freebuff 提供经过筛选的模型目录。常规模型选择器目前包括
 | --------------------------- | -------------- | ------------------------------------------------ |
 | **MiMo v2.6 Flash Fast**    | 完整和受限访问 | 所有模式下的默认模型；均衡性能并支持图像         |
 | **GLM 5.3 Flash**           | 完整和受限访问 | 推理最深入，不消耗会话                           |
-| **DeepSeek V4.1 Flash** | 完整和受限访问 | 快速编程和工具调用，不消耗会话                   |
-| **DeepSeek V4.1 Flash Fast** | 完整访问；受限访问需付费计划 | 快速模式：同一模型运行于 DeepSeek 官方 API，将工作拆分给并行子智能体并自行验证结果；按 DeepSeek 的高峰和非高峰时段定价 |
+| **DeepSeek V4.1 Flash 10/17** | 完整和受限访问 | 快速编程和工具调用，不消耗会话                   |
+| **DeepSeek V4.1 Flash Fast 10/17** | 完整访问；受限访问需付费计划 | 快速模式：同一模型运行于 DeepSeek 官方 API，将工作拆分给并行子智能体并自行验证结果；按 DeepSeek 的高峰和非高峰时段定价 |
 | **GPT-6 Luna**              | 完整访问       | 综合能力强，原生支持图像；运行于 OpenAI flex 容量 |
 | **MiMo 2.6 Pro**            | 完整访问       | 小米更强的推理模型，支持图像 |
 | **Solar Mini 4**            | 完整和受限访问 | Upstage 的快速轻量模型；52.4 万上下文，仅支持文本 |
@@ -70,7 +70,7 @@ Freebuff 使用专业化智能体，而不是把所有任务都交给同一个
 
 ## 免费访问
 
-Freebuff 在所有国家和地区均可使用。受支持的地区提供完整访问；其他地区以及使用 VPN 的用户获得受限访问，包括 DeepSeek V4.1 Flash、GLM 5.3 Flash、MiMo v2.6 Flash Fast、Solar Mini 4 和 Solar Pro 4。所有模型均按选择器中显示的倍数以小时计费：MiMo v2.6 Flash Slow 每小时用掉 1 小时额度，3x 模型用掉 3 小时。受限访问的免费额度为每天 5 小时（使用 VPN 或代理时为 4 小时），所有模型（包括 GLM）都会先使用当天额度；赚取的小时存入钱包，在当天额度用完后使用。（自 2026-10-15 起余额以小时显示；1 小时 = 5 Freebucks。）
+Freebuff 在所有国家和地区均可使用。受支持的地区提供完整访问；其他地区以及使用 VPN 的用户获得受限访问，包括 DeepSeek V4.1 Flash 10/17、GLM 5.3 Flash、MiMo v2.6 Flash Fast、Solar Mini 4 和 Solar Pro 4。所有模型均按选择器中显示的倍数以小时计费：MiMo v2.6 Flash Slow 每小时用掉 1 小时额度，3x 模型用掉 3 小时。受限访问的免费额度为每天 5 小时（使用 VPN 或代理时为 4 小时），所有模型（包括 GLM）都会先使用当天额度；赚取的小时存入钱包，在当天额度用完后使用。（自 2026-10-15 起余额以小时显示；1 小时 = 5 Freebucks。）
 
 内置模型由文字广告支持。开始前，Freebuff 会显示适用的会话限制以及模型特定的数据使用提示。
 
 
@@ -1453,7 +1453,7 @@ describe('freebuff model availability', () => {
       ),
     ).toBe(FREEBUFF_DEEPSEEK_V4_FLASH_MODEL_ID)
     expect(LIMITED_FREEBUFF_MODEL_MISMATCH_MESSAGE).toBe(
-      'Limited free access is only available with MiMo v2.6 Flash Fast or GLM 5.3 Flash or DeepSeek V4.1 Flash or Solar Mini 4 or Solar Pro 4.',
+      'Limited free access is only available with MiMo v2.6 Flash Fast or GLM 5.3 Flash or DeepSeek V4.1 Flash 10/17 or Solar Mini 4 or Solar Pro 4.',
     )
     // No row in the tier supersedes another, so no picker may offer a switch
     // that admission would coerce straight back.
@@ -1727,12 +1727,13 @@ describe('freebuff model availability', () => {
     // Flash carries a VERSION rather than a build date as of 2026-09-10:
     // DeepSeek moved the id onto V4.1 Flash, and a version number is what the
     // date was always standing in for. The invariant is unchanged — the name
-    // must still say which build this is — only its spelling moved.
+    // must still say which build this is — only its spelling moved. The 1017
+    // build (2026-10-17) kept the version, so both names carry the date again.
     const dated = [
-      [FREEBUFF_DEEPSEEK_V4_FLASH_MODEL_ID, 'V4.1'],
+      [FREEBUFF_DEEPSEEK_V4_FLASH_MODEL_ID, 'V4.1 Flash 10/17'],
       // Fast mode (2026-09-26) is the same V4.1 build on its own row; the
-      // version travels with the name.
-      [FREEBUFF_DEEPSEEK_V4_FLASH_FAST_MODEL_ID, 'V4.1'],
+      // version and date travel with the name.
+      [FREEBUFF_DEEPSEEK_V4_FLASH_FAST_MODEL_ID, 'V4.1 Flash Fast 10/17'],
     ] as const
     // Widened to the interface: the const-asserted tuple's union type only
     // exposes optional fields set on EVERY member, so `isNew` is unreachable
 
@@ -1688,11 +1688,13 @@ const DEEPSEEK_V4_FLASH_MODEL = {
   // build date was standing in for, in the vocabulary the vendor and the user
   // both already use.
   //
-  // Note what this costs: `compactChatModelName` and `shortModelName` both
-  // strip a trailing ` MM/DD`, so they are now no-ops on this row and the full
-  // name reaches the compact surfaces. That is intended — 'DeepSeek V4.1 Flash'
-  // is shorter than the dated name it replaces, so nothing got wider.
-  displayName: 'DeepSeek V4.1 Flash',
+  // DATED AGAIN 2026-10-19: DeepSeek moved the id onto V4.1 Flash's 1017 build
+  // on 2026-10-17 with no new version number, so a build date says which V4.1
+  // this is. Every lane serves 1017 (web/src/llm-api/deepseek-router.ts).
+  // `compactChatModelName` and `shortModelName` strip a trailing ` MM/DD`, so
+  // the collapsed triggers still read 'DeepSeek V4.1 Flash'; open menus show
+  // the date.
+  displayName: 'DeepSeek V4.1 Flash 10/17',
   // "Smart & Fast" survived Flash becoming premium on 2026-08-18: it describes
   // the model, and the one word in it that described the TIER ("unlimited") had
   // already gone when Pro took the recommendation on 2026-08-12. The picker
@@ -1826,7 +1828,9 @@ const DEEPSEEK_V4_FLASH_MODEL = {
  */
 const DEEPSEEK_V4_FLASH_FAST_MODEL = {
   id: FREEBUFF_DEEPSEEK_V4_FLASH_FAST_MODEL_ID,
-  displayName: 'DeepSeek V4.1 Flash Fast',
+  // The build date trails 'Fast' so the collapsed triggers strip it, as on the
+  // Flash row.
+  displayName: 'DeepSeek V4.1 Flash Fast 10/17',
   tagline: 'Parallel agents',
   taglineTooltip:
     'Gathers context with parallel subagents. Runs on DeepSeek’s own API.',
 
@@ -43,11 +43,11 @@ and keep the extracted `freebuff` binary and `tree-sitter.wasm` together.
 
 **How can it be free?** Freebuff is supported by text ads.
 
-**What models do you use?** In full mode, the regular picker includes MiMo v2.6 Flash Fast, GLM 5.3 Flash, DeepSeek V4.1 Flash, DeepSeek V4.1 Flash Fast, GPT-6 Luna, MiMo 2.6 Pro, Solar Mini 4, Solar Pro 4, Space Bunny Alpha, Gemini 3.8 Flash, Muse Spark 1.3, Gemini 4 Argon, and GPT-6.1 Sol. Space Bunny Alpha is a beta stealth model from an anonymous provider that retains prompts. Gemini 3.8 Flash and Muse Spark 1.3 require a paid plan: without one they are listed but locked, and selecting one opens the plans page. Gemini 4 Argon and GPT-6.1 Sol are free in the US and need a paid plan elsewhere, and every account, paid or not, gets one session a day on each; Gemini 4 Argon's price is a temporary promotion. GPT-6 Luna and MiMo 2.6 Pro are open to every full-access account. DeepSeek V4.1 Flash Fast is fast mode: the same model on DeepSeek's own API, splitting work across parallel subagents. Muse Spark 1.3 has a 1M-token context, and when it is busy or unavailable it answers on DeepSeek V4.1 Flash instead of leaving you waiting. MiMo v2.6 Flash Fast is the CLI default, and GLM 5.3 Flash is the cheapest model to run. Limited mode uses MiMo v2.6 Flash Fast, GLM 5.3 Flash, DeepSeek V4.1 Flash, Solar Mini 4, Solar Pro 4, and Space Bunny Alpha; the models a paid plan unlocks there are listed too, locked until you have one. Every model is paid for in hours, one multiplier per one-hour session, shown in the model picker: an hour of MiMo v2.6 Flash Slow uses one hour of balance, a 3x model uses three. Models may still serve from a quantized (Q8_0) build.
+**What models do you use?** In full mode, the regular picker includes MiMo v2.6 Flash Fast, GLM 5.3 Flash, DeepSeek V4.1 Flash 10/17, DeepSeek V4.1 Flash Fast 10/17, GPT-6 Luna, MiMo 2.6 Pro, Solar Mini 4, Solar Pro 4, Space Bunny Alpha, Gemini 3.8 Flash, Muse Spark 1.3, Gemini 4 Argon, and GPT-6.1 Sol. Space Bunny Alpha is a beta stealth model from an anonymous provider that retains prompts. Gemini 3.8 Flash and Muse Spark 1.3 require a paid plan: without one they are listed but locked, and selecting one opens the plans page. Gemini 4 Argon and GPT-6.1 Sol are free in the US and need a paid plan elsewhere, and every account, paid or not, gets one session a day on each; Gemini 4 Argon's price is a temporary promotion. GPT-6 Luna and MiMo 2.6 Pro are open to every full-access account. DeepSeek V4.1 Flash Fast is fast mode: the same model on DeepSeek's own API, splitting work across parallel subagents. Muse Spark 1.3 has a 1M-token context, and when it is busy or unavailable it answers on DeepSeek V4.1 Flash instead of leaving you waiting. MiMo v2.6 Flash Fast is the CLI default, and GLM 5.3 Flash is the cheapest model to run. Limited mode uses MiMo v2.6 Flash Fast, GLM 5.3 Flash, DeepSeek V4.1 Flash 10/17, Solar Mini 4, Solar Pro 4, and Space Bunny Alpha; the models a paid plan unlocks there are listed too, locked until you have one. Every model is paid for in hours, one multiplier per one-hour session, shown in the model picker: an hour of MiMo v2.6 Flash Slow uses one hour of balance, a 3x model uses three. Models may still serve from a quantized (Q8_0) build.
 
 **Which countries is Freebuff available in?** All countries. Freebuff runs in "full" mode in the US, Canada, UK, EU, and other select countries, and in "limited" mode everywhere else (or while using a VPN). See [freebuff.com](https://freebuff.com) for the full list.
 
-**What is limited mode?** Limited mode lets you use Freebuff outside the full-access countries, or while using a VPN. It includes GLM 5.3 Flash, DeepSeek V4.1 Flash, MiMo v2.6 Flash Fast, Solar Mini 4, Solar Pro 4, and Space Bunny Alpha. The free limited-access allowance is 5 hours a day, or 4 on a VPN or proxy, and each model's multiplier per one-hour session is shown in the picker. Today's allowance is spent first, whichever model you pick, including GLM 5.3 Flash; Hours you earn on the Earn page go into your wallet and are used once today's allowance runs out.
+**What is limited mode?** Limited mode lets you use Freebuff outside the full-access countries, or while using a VPN. It includes GLM 5.3 Flash, DeepSeek V4.1 Flash 10/17, MiMo v2.6 Flash Fast, Solar Mini 4, Solar Pro 4, and Space Bunny Alpha. The free limited-access allowance is 5 hours a day, or 4 on a VPN or proxy, and each model's multiplier per one-hour session is shown in the picker. Today's allowance is spent first, whichever model you pick, including GLM 5.3 Flash; Hours you earn on the Earn page go into your wallet and are used once today's allowance runs out.
 
 <!-- BEGIN GENERATED FREEBUFF DATA USE -->