docs: restore Go limits copy

feat(go): add Union Alpha
2026-09-16 05:46:23 +00:00 · 2026-09-15 22:52:24 +08:00 · 2026-09-15 22:43:49 +08:00
59 changed files with 253 additions and 37 deletions
@@ -50,4 +50,13 @@ export const goModels = [
    allowance: 60,
    regions: true,
  },
+  {
+    id: "union-alpha",
+    name: "Union Alpha",
+    requests: Infinity,
+    allowance: Infinity,
+    featured: true,
+    fresh: true,
+    unlimited: true,
+  },
 ].sort((a, b) => a.requests - b.requests)
@@ -144,6 +144,11 @@
    }
  }

+  [data-slot="model-row"][data-unlimited] :is([data-slot="requests"], [data-slot="allowance"]) bdi {
+    font-size: 1.5rem;
+    line-height: 1;
+  }
+
  [data-slot="currency"] {
    color: var(--color-text-weak);
  }
@@ -5,9 +5,11 @@ import { useLanguage } from "~/context/language"
 import { goModels } from "./go-models"

 // Compress the request range, with the same domain in both views.
-const max = Math.max(...goModels.map((model) => model.requests))
+const max = Math.max(...goModels.filter((model) => Number.isFinite(model.requests)).map((model) => model.requests))
 const position = (requests: number) =>
-  4 + Math.pow(Math.log10(Math.max(requests / 100, 1)) / Math.log10(max / 100), 2.2) * 96
+  Number.isFinite(requests)
+    ? 4 + Math.pow(Math.log10(Math.max(requests / 100, 1)) / Math.log10(max / 100), 2.2) * 88
+    : 100
 const ticks = [100, 1000, 10000, 40000]

 export function LimitsGraph(props: { href: string }) {
@@ -74,7 +76,13 @@ export function LimitsGraph(props: { href: string }) {
        <div role="rowgroup" data-slot="rows">
          <For each={models()}>
            {(model, index) => (
-              <div role="row" data-slot="model-row" data-model={model.id} style={{ "--delay": `${index() * 30}ms` }}>
+              <div
+                role="row"
+                data-slot="model-row"
+                data-model={model.id}
+                data-unlimited={model.unlimited ? "" : undefined}
+                style={{ "--delay": `${index() * 30}ms` }}
+              >
                <div role="rowheader" data-slot="model">
                  <bdi>{model.name}</bdi>
                  <Show when={model.fresh}>
@@ -83,6 +91,9 @@ export function LimitsGraph(props: { href: string }) {
                  <Show when={model.bonus}>
                    <span data-slot="badge">{i18n.t("go.graph.bonus", { count: model.bonus! })}</span>
                  </Show>
+                  <Show when={model.unlimited}>
+                    <span data-slot="badge">{i18n.t("go.graph.limitedTime")}</span>
+                  </Show>
                  <Show when={model.regions}>
                    <a
                      data-slot="region"
@@ -98,7 +109,11 @@ export function LimitsGraph(props: { href: string }) {
                    </a>
                  </Show>
                </div>
-                <div role="cell" data-slot="usage-value">
+                <div
+                  role="cell"
+                  data-slot="usage-value"
+                  aria-label={model.unlimited ? i18n.t("go.graph.unlimited") : undefined}
+                >
                  <div data-slot="track" aria-hidden="true">
                    <For each={ticks}>
                      {(tick) => <span data-slot="gridline" style={{ "--position": `${position(tick)}%` }} />}
@@ -106,23 +121,46 @@ export function LimitsGraph(props: { href: string }) {
                    <div data-slot="bar" style={{ "--width": `${position(model.requests)}%` }} />
                  </div>
                  <div data-slot="requests">
-                    <Show when={model.baseRequests}>
-                      <s>{format().format(model.baseRequests!)}</s>{" "}
+                    <Show
+                      when={!model.unlimited}
+                      fallback={
+                        <bdi aria-hidden="true" title={i18n.t("go.graph.unlimited")}>
+                          ∞
+                        </bdi>
+                      }
+                    >
+                      <Show when={model.baseRequests}>
+                        <s>{format().format(model.baseRequests!)}</s>{" "}
+                      </Show>
+                      <bdi>{format().format(model.requests)}</bdi>
                    </Show>
-                    <bdi>{format().format(model.requests)}</bdi>
                  </div>
                </div>
-                <div role="cell" data-slot="allowance" data-high={model.allowance >= 60 ? "" : undefined}>
-                  <Show when={model.baseAllowance}>
-                    <s>{currency().format(model.baseAllowance!)}</s>{" "}
+                <div
+                  role="cell"
+                  data-slot="allowance"
+                  data-high={model.allowance >= 60 ? "" : undefined}
+                  aria-label={model.unlimited ? i18n.t("go.graph.unlimited") : undefined}
+                >
+                  <Show
+                    when={!model.unlimited}
+                    fallback={
+                        <bdi aria-hidden="true" title={i18n.t("go.graph.unlimited")}>
+                        ∞
+                      </bdi>
+                    }
+                  >
+                    <Show when={model.baseAllowance}>
+                      <s>{currency().format(model.baseAllowance!)}</s>{" "}
+                    </Show>
+                    <bdi>
+                      <For each={currency().formatToParts(model.allowance)}>
+                        {(part) => (
+                          <span data-slot={part.type === "currency" ? "currency" : undefined}>{part.value}</span>
+                        )}
+                      </For>
+                    </bdi>
                  </Show>
-                  <bdi>
-                    <For each={currency().formatToParts(model.allowance)}>
-                      {(part) => (
-                        <span data-slot={part.type === "currency" ? "currency" : undefined}>{part.value}</span>
-                      )}
-                    </For>
-                  </bdi>
                </div>
              </div>
            )}
@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "يحصل DeepSeek V4.1 Flash على حدود استخدام مضاعفة 4 مرات لفترة محدودة",
+  "go.promo.unionAlpha": "يتوفر Union Alpha مجانًا لفترة محدودة",
  "go.graph.bonus": "استخدام مضاعف {{count}} مرات",
  "nav.github": "GitHub",
  "nav.docs": "الوثائق",
@@ -282,6 +282,7 @@ export const dict = {
  "go.graph.showLess": "عرض نماذج أقل",
  "go.graph.limitedRegions": "مناطق محدودة",
  "go.graph.limitedTime": "لفترة محدودة",
+  "go.graph.unlimited": "غير محدود",
  "go.graph.usageLimits": "حدود الاستخدام",
  "go.graph.aria": "الطلبات كل 5 ساعات: {{free}} مقابل {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash tem limites de uso 4x maiores por tempo limitado",
+  "go.promo.unionAlpha": "O Union Alpha está grátis por tempo limitado",
  "go.graph.bonus": "{{count}}× mais uso",
  "nav.github": "GitHub",
  "nav.docs": "Documentação",
@@ -288,6 +288,7 @@ export const dict = {
  "go.graph.showLess": "Mostrar menos modelos",
  "go.graph.limitedRegions": "regiões limitadas",
  "go.graph.limitedTime": "tempo limitado",
+  "go.graph.unlimited": "ilimitado",
  "go.graph.usageLimits": "Limites de uso",
  "go.graph.aria": "Requisições por 5h: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash får firedoblet brugsgrænse i en begrænset periode",
+  "go.promo.unionAlpha": "Union Alpha er gratis i en begrænset periode",
  "go.graph.bonus": "{{count}}× forbrug",
  "nav.github": "GitHub",
  "nav.docs": "Dokumentation",
@@ -285,6 +285,7 @@ export const dict = {
  "go.graph.showLess": "Vis færre modeller",
  "go.graph.limitedRegions": "begrænsede regioner",
  "go.graph.limitedTime": "begrænset periode",
+  "go.graph.unlimited": "ubegrænset",
  "go.graph.usageLimits": "Forbrugsgrænser",
  "go.graph.aria": "Forespørgsler pr. 5t: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash erhält für begrenzte Zeit 4x Nutzungslimits",
+  "go.promo.unionAlpha": "Union Alpha ist für begrenzte Zeit kostenlos",
  "go.graph.bonus": "{{count}}× Nutzung",
  "nav.github": "GitHub",
  "nav.docs": "Dokumentation",
@@ -287,6 +287,7 @@ export const dict = {
  "go.graph.showLess": "Weniger Modelle anzeigen",
  "go.graph.limitedRegions": "begrenzte Regionen",
  "go.graph.limitedTime": "begrenzte Zeit",
+  "go.graph.unlimited": "unbegrenzt",
  "go.graph.usageLimits": "Nutzungslimits",
  "go.graph.aria": "Anfragen pro 5h: {{free}} vs {{go}}",

@@ -1,5 +1,5 @@
 export const dict = {
-  "go.promo.deepseek": "DeepSeek V4.1 Flash gets 4× usage limits for a limited time",
+  "go.promo.unionAlpha": "Union Alpha is free for a limited time",
  "go.graph.bonus": "{{count}}× usage",
  "nav.github": "GitHub",
  "nav.docs": "Docs",
@@ -282,6 +282,7 @@ export const dict = {
  "go.graph.showLess": "Show fewer models",
  "go.graph.limitedRegions": "limited regions",
  "go.graph.limitedTime": "limited time",
+  "go.graph.unlimited": "unlimited",
  "go.graph.tick": "{{n}}x",
  "go.graph.usageLimits": "Usage limits",
  "go.graph.aria": "Requests per 5h: {{free}} vs {{go}}",
@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash tiene límites de uso 4x mayores por tiempo limitado",
+  "go.promo.unionAlpha": "Union Alpha es gratis por tiempo limitado",
  "go.graph.bonus": "{{count}}× de uso",
  "nav.github": "GitHub",
  "nav.docs": "Documentación",
@@ -289,6 +289,7 @@ export const dict = {
  "go.graph.showLess": "Mostrar menos modelos",
  "go.graph.limitedRegions": "regiones limitadas",
  "go.graph.limitedTime": "tiempo limitado",
+  "go.graph.unlimited": "ilimitado",
  "go.graph.usageLimits": "Límites de uso",
  "go.graph.aria": "Solicitudes por 5h: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash bénéficie de limites d’utilisation 4x supérieures pour une durée limitée",
+  "go.promo.unionAlpha": "Union Alpha est gratuit pendant une durée limitée",
  "go.graph.bonus": "{{count}}× d’utilisation",
  "app.meta.description": "OpenCode - L'agent de code open source.",
  "nav.github": "GitHub",
@@ -290,6 +290,7 @@ export const dict = {
  "go.graph.showLess": "Afficher moins de modèles",
  "go.graph.limitedRegions": "régions limitées",
  "go.graph.limitedTime": "durée limitée",
+  "go.graph.unlimited": "illimité",
  "go.graph.usageLimits": "Limites d’utilisation",
  "go.graph.aria": "Requêtes par 5h : {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash offre limiti di utilizzo 4x superiori per un periodo limitato",
+  "go.promo.unionAlpha": "Union Alpha è gratuito per un periodo limitato",
  "go.graph.bonus": "Utilizzo {{count}}×",
  "nav.github": "GitHub",
  "nav.docs": "Documentazione",
@@ -286,6 +286,7 @@ export const dict = {
  "go.graph.showLess": "Mostra meno modelli",
  "go.graph.limitedRegions": "regioni limitate",
  "go.graph.limitedTime": "periodo limitato",
+  "go.graph.unlimited": "illimitato",
  "go.graph.usageLimits": "Limiti di utilizzo",
  "go.graph.aria": "Richieste ogni 5h: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flashの利用上限が期間限定で4倍に",
+  "go.promo.unionAlpha": "Union Alphaは期間限定で無料です",
  "go.graph.bonus": "利用枠{{count}}倍",
  "nav.github": "GitHub",
  "nav.docs": "ドキュメント",
@@ -285,6 +285,7 @@ export const dict = {
  "go.graph.showLess": "折りたたむ",
  "go.graph.limitedRegions": "一部の地域に限定",
  "go.graph.limitedTime": "期間限定",
+  "go.graph.unlimited": "無制限",
  "go.graph.usageLimits": "利用制限",
  "go.graph.aria": "5時間あたりのリクエスト数: {{free}} 対 {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash 사용 한도가 한시적으로 4배 확대됩니다",
+  "go.promo.unionAlpha": "Union Alpha는 한정 기간 동안 무료로 이용할 수 있습니다",
  "go.graph.bonus": "사용량 {{count}}배",
  "nav.github": "GitHub",
  "nav.docs": "문서",
@@ -281,6 +281,7 @@ export const dict = {
  "go.graph.showLess": "접기",
  "go.graph.limitedRegions": "일부 지역에서만 제공",
  "go.graph.limitedTime": "한정된 기간",
+  "go.graph.unlimited": "무제한",
  "go.graph.usageLimits": "사용 한도",
  "go.graph.aria": "5시간당 요청 수: {{free}} 대 {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash får 4x bruksgrense i en begrenset periode",
+  "go.promo.unionAlpha": "Union Alpha er gratis i en begrenset periode",
  "go.graph.bonus": "{{count}}× bruk",
  "nav.github": "GitHub",
  "nav.docs": "Dokumentasjon",
@@ -285,6 +285,7 @@ export const dict = {
  "go.graph.showLess": "Vis færre modeller",
  "go.graph.limitedRegions": "begrensede regioner",
  "go.graph.limitedTime": "begrenset periode",
+  "go.graph.unlimited": "ubegrenset",
  "go.graph.usageLimits": "Bruksgrenser",
  "go.graph.aria": "Forespørsler per 5t: {{free}} vs {{go}}",

@@ -2,7 +2,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash oferuje 4x wyższe limity użycia przez ograniczony czas",
+  "go.promo.unionAlpha": "Union Alpha jest dostępny bezpłatnie przez ograniczony czas",
  "go.graph.bonus": "{{count}}× większy limit",
  "nav.github": "GitHub",
  "nav.docs": "Dokumentacja",
@@ -287,6 +287,7 @@ export const dict = {
  "go.graph.showLess": "Pokaż mniej modeli",
  "go.graph.limitedRegions": "ograniczone regiony",
  "go.graph.limitedTime": "ograniczony czas",
+  "go.graph.unlimited": "bez limitu",
  "go.graph.usageLimits": "Limity użycia",
  "go.graph.aria": "Żądania na 5h: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash получает 4x лимиты использования на ограниченное время",
+  "go.promo.unionAlpha": "Union Alpha можно использовать бесплатно в течение ограниченного времени",
  "go.graph.bonus": "Лимит ×{{count}}",
  "nav.github": "GitHub",
  "nav.docs": "Документация",
@@ -290,6 +290,7 @@ export const dict = {
  "go.graph.showLess": "Показать меньше моделей",
  "go.graph.limitedRegions": "доступно в отдельных регионах",
  "go.graph.limitedTime": "ограниченное время",
+  "go.graph.unlimited": "без ограничений",
  "go.graph.usageLimits": "Лимиты использования",
  "go.graph.aria": "Запросов за 5ч: {{free}} против {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash เพิ่มโควตาการใช้งานเป็น 4 เท่าในช่วงเวลาจำกัด",
+  "go.promo.unionAlpha": "ใช้ Union Alpha ฟรีในช่วงเวลาจำกัด",
  "go.graph.bonus": "ใช้งาน {{count}} เท่า",
  "nav.github": "GitHub",
  "nav.docs": "เอกสาร",
@@ -284,6 +284,7 @@ export const dict = {
  "go.graph.showLess": "แสดงโมเดลน้อยลง",
  "go.graph.limitedRegions": "เฉพาะบางภูมิภาค",
  "go.graph.limitedTime": "ช่วงเวลาจำกัด",
+  "go.graph.unlimited": "ไม่จำกัด",
  "go.graph.usageLimits": "ขีดจำกัดการใช้งาน",
  "go.graph.aria": "คำขอต่อ 5 ชม.: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash sınırlı bir süre için 4x kullanım limiti sunuyor",
+  "go.promo.unionAlpha": "Union Alpha sınırlı bir süre boyunca ücretsiz",
  "go.graph.bonus": "{{count}}× kullanım",
  "nav.github": "GitHub",
  "nav.docs": "Dokümantasyon",
@@ -287,6 +287,7 @@ export const dict = {
  "go.graph.showLess": "Daha az model göster",
  "go.graph.limitedRegions": "sınırlı bölgeler",
  "go.graph.limitedTime": "sınırlı süre",
+  "go.graph.unlimited": "sınırsız",
  "go.graph.usageLimits": "Kullanım limitleri",
  "go.graph.aria": "5 saatlik istekler: {{free}} vs {{go}}",

@@ -2,7 +2,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash отримує 4x ліміти використання протягом обмеженого часу",
+  "go.promo.unionAlpha": "Union Alpha можна використовувати безкоштовно протягом обмеженого часу",
  "go.graph.bonus": "Ліміт ×{{count}}",
  "nav.github": "GitHub",
  "nav.docs": "Документація",
@@ -285,6 +285,7 @@ export const dict = {
  "go.graph.showLess": "Показати менше моделей",
  "go.graph.limitedRegions": "обмежені регіони",
  "go.graph.limitedTime": "обмежений час",
+  "go.graph.unlimited": "без обмежень",
  "go.graph.usageLimits": "Ліміти використання",
  "go.graph.aria": "Запитів за 5 год: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash 限时享受 4 倍使用额度",
+  "go.promo.unionAlpha": "Union Alpha 限时免费",
  "go.graph.bonus": "{{count}} 倍用量",
  "nav.github": "GitHub",
  "nav.docs": "文档",
@@ -274,6 +274,7 @@ export const dict = {
  "go.graph.showLess": "收起模型",
  "go.graph.limitedRegions": "仅限部分地区",
  "go.graph.limitedTime": "限时",
+  "go.graph.unlimited": "无限制",
  "go.graph.usageLimits": "使用限制",
  "go.graph.aria": "每 5 小时请求数: {{free}} vs {{go}}",

@@ -3,7 +3,7 @@ import { dict as en } from "./en"

 export const dict = {
  ...en,
-  "go.promo.deepseek": "DeepSeek V4.1 Flash 限時享有 4 倍使用額度",
+  "go.promo.unionAlpha": "Union Alpha 限時免費",
  "go.graph.bonus": "{{count}} 倍用量",
  "nav.github": "GitHub",
  "nav.docs": "文件",
@@ -273,6 +273,7 @@ export const dict = {
  "go.graph.showLess": "收起模型",
  "go.graph.limitedRegions": "僅限部分地區",
  "go.graph.limitedTime": "限時",
+  "go.graph.unlimited": "無限制",
  "go.graph.usageLimits": "使用限制",
  "go.graph.aria": "每 5 小時請求數：{{free}} vs {{go}}",

@@ -52,6 +52,7 @@ const models = [
  { name: "DeepSeek V4 Flash Vision Exp", training: "go.faq.a5.notUsed", retention: "go.faq.a5.retention0" },
  { name: "Hy4 preview", training: "go.faq.a5.notUsed", retention: "go.faq.a5.retention0" },
  { name: "Hy3", training: "go.faq.a5.notUsed", retention: "go.faq.a5.retention0" },
+  { name: "Union Alpha", training: "go.faq.a5.notUsed", retention: "go.faq.a5.retention0" },
 ] as const

 export default function Home() {
@@ -84,7 +85,7 @@ export default function Home() {
            <div data-component="desktop-app-banner">
              <span data-slot="badge">{i18n.t("home.banner.badge")}</span>
              <div data-slot="content">
-                <span data-slot="text">{i18n.t("go.promo.deepseek")}</span>
+                <span data-slot="text">{i18n.t("go.promo.unionAlpha")}</span>
              </div>
            </div>
            <div data-slot="hero-copy">
@@ -667,8 +667,9 @@ export function LiteSection(props: { lite: LiteSubscription | undefined }) {
            <li>MiMo-V2.5-Pro</li>
            <li>Hy4 preview</li>
            <li>Hy3</li>
+            <li>Union Alpha</li>
          </ul>
-          <p data-slot="promo-description">{i18n.t("go.promo.deepseek")}</p>
+          <p data-slot="promo-description">{i18n.t("go.promo.unionAlpha")}</p>
          <p data-slot="promo-description">{i18n.t("workspace.lite.promo.footer")}</p>
          <div data-slot="subscribe-actions">
            <button
@@ -76,6 +76,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (لفترة محدودة)

 قد تتغير قائمة النماذج مع استمرارنا في اختبار نماذج جديدة وإضافتها.

@@ -170,6 +171,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30   | $1.20   | $0.006          | -               | **$15**                                                     |
 | Hy4 preview                             | $0.834  | $2.501  | $0.042          | -               | **$30**                                                     |
 | Hy3                                     | $0.14   | $0.58   | $0.035          | -               | **$60**                                                     |
+| Union Alpha                             | Free    | Free    | Free            | -               | **غير محدود**<br /><small>لفترة محدودة</small>              |
 | Grok 4.6 (≤ 200K tokens)                | $2.00   | $6.00   | $0.50           | -               | **$15**                                                     |
 | Grok 4.6 (> 200K tokens)                | $4.00   | $12.00  | $1.00           | -               | **$15**                                                     |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20   | $1.20   | $0.02           | $0.25           | **$15**                                                     |
@@ -210,6 +212,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
 | DeepSeek V4 Flash Vision Exp                                    | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                     | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                             | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                     | غير محدود                 | غير محدود                  | غير محدود                   |
 | Grok 4.6                                                        | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                    | 2,050                     | 5,100                      | 10,250                      |

@@ -302,6 +305,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 يستخدم [model id](/docs/config/#models) في إعدادات OpenCode لديك التنسيق `opencode-go/<model-id>`. على سبيل المثال، بالنسبة إلى Kimi K3، ستستخدم `opencode-go/kimi-k3` في إعداداتك.

@@ -348,6 +352,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | غير مستخدَمة  | 0 أيام             |
 | Hy4 preview                  | غير مستخدَمة  | 0 أيام             |
 | Hy3                          | غير مستخدَمة  | 0 أيام             |
+| Union Alpha                  | غير مستخدَمة  | 0 أيام             |

 - **Grok 4.6:** تعطّل ZDR ميزات API مهمة تعتمد على البيانات المخزنة، بما في ذلك Responses API ذات الحالة، وFiles and Collections، وBatch API. [اعرف المزيد](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** تُنشأ سجلات مراقبة إساءة الاستخدام لكل استخدام لميزات API، ويُحتفظ بها لمدة تصل إلى 30 يومًا. [اعرف المزيد](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -119,6 +119,7 @@ OpenCode Zen هي بوابة AI تتيح لك الوصول إلى هذه الن
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -146,6 +147,7 @@ https://opencode.ai/zen/v1/models
 | النموذج                           | الإدخال | الإخراج | القراءة المخزنة | الكتابة المخزنة |
 | --------------------------------- | ------- | ------- | --------------- | --------------- |
 | Big Pickle                        | Free    | Free    | Free            | -               |
+| Union Alpha                       | Free    | Free    | Free            | -               |
 | MiMo-V2.5 Free                    | Free    | Free    | Free            | -               |
 | Ling 3.0 Flash Fin Free           | Free    | Free    | Free            | -               |
 | Nemotron 3 Ultra Free             | Free    | Free    | Free            | -               |
@@ -242,6 +244,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.
 - Nemotron 3.5 Lightning Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.
 - Big Pickle نموذج خفي ومتاح مجانا على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.
+- Union Alpha نموذج خفي ومتاح مجانا على OpenCode لفترة محدودة. يتبع مزوده سياسة عدم الاحتفاظ بالبيانات ولا يستخدم بياناتك لتدريب النماذج.
 - Muse Spark 1.3 Contributor Free متاح على OpenCode لفترة محدودة. يستخدم الفريق هذه الفترة لجمع الملاحظات وتحسين النموذج.

 <a href={email}>تواصل معنا</a> إذا كانت لديك أي أسئلة.
@@ -86,6 +86,7 @@ Trenutna lista modela uključuje:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (ograničeno vrijeme)

 Lista modela se može mijenjati dok testiramo i dodajemo nove.

@@ -180,6 +181,7 @@ Cijene tokena navedene su za 1M tokena.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                   |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                   |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                   |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Neograničeno**<br /><small>ograničeno vrijeme</small>  |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                   |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                   |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                   |
@@ -220,6 +222,7 @@ Tabela ispod daje procijenjeni broj zahtjeva na osnovu tipičnih obrazaca koriš
 | DeepSeek V4 Flash Vision Exp                                  | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                   | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                           | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                   | Neograničeno              | Neograničeno               | Neograničeno                |
 | Grok 4.6                                                      | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                  | 2,050                     | 5,100                      | 10,250                      |

@@ -314,6 +317,7 @@ Također možete pristupiti Go modelima putem sljedećih API endpointa.
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 [Model id](/docs/config/#models) u vašoj OpenCode konfiguraciji
 koristi format `opencode-go/<model-id>`. Na primjer, za Kimi K3, koristili biste
@@ -362,6 +366,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Ne koristi se     | 0 dana               |
 | Hy4 preview                  | Ne koristi se     | 0 dana               |
 | Hy3                          | Ne koristi se     | 0 dana               |
+| Union Alpha                  | Ne koristi se     | 0 dana               |

 - **Grok 4.6:** ZDR onemogućava važne API funkcije koje zavise od pohranjenih podataka, uključujući Responses API s očuvanjem stanja, Files and Collections i Batch API. [Saznajte više](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Zapisi o nadzoru zloupotrebe generišu se za svako korištenje API funkcija i čuvaju do 30 dana. [Saznajte više](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -124,6 +124,7 @@ Našim modelima možete pristupiti i preko sljedećih API endpointa.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ Podržavamo pay-as-you-go model. Ispod su cijene **po 1M tokena**.
 | Model                             | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -249,6 +251,7 @@ Besplatni modeli:
 - Nemotron 3 Ultra Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.
 - Nemotron 3.5 Lightning Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.
 - Big Pickle je stealth model koji je besplatan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.
+- Union Alpha je stealth model koji je besplatan na OpenCode ograničeno vrijeme. Pružalac usluge slijedi politiku nultog zadržavanja i ne koristi vaše podatke za treniranje modela.
 - Muse Spark 1.3 Contributor Free je dostupan na OpenCode ograničeno vrijeme. Tim koristi ovo vrijeme da prikupi povratne informacije i poboljša model.

 <a href={email}>Kontaktirajte nas</a> ako imate bilo kakvih pitanja.
@@ -86,6 +86,7 @@ Den nuværende liste over modeller inkluderer:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (i en begrænset periode)

 Listen over modeller kan ændre sig, efterhånden som vi tester og tilføjer nye.

@@ -180,6 +181,7 @@ Tokenpriser er angivet pr. 1M tokens.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                   |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                   |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                   |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Ubegrænset**<br /><small>i en begrænset periode</small> |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                   |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                   |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                   |
@@ -220,6 +222,7 @@ Tabellen nedenfor viser et estimeret antal anmodninger baseret på typiske Go-fo
 | DeepSeek V4 Flash Vision Exp                                  | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                   | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                           | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                   | Ubegrænset                | Ubegrænset                 | Ubegrænset                  |
 | Grok 4.6                                                      | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                  | 2,050                     | 5,100                      | 10,250                      |

@@ -314,6 +317,7 @@ Du kan også få adgang til Go-modeller gennem følgende API-endpoints.
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 Dit [model id](/docs/config/#models) i din OpenCode config
 bruger formatet `opencode-go/<model-id>`. For eksempel for Kimi K3, vil du
@@ -362,6 +366,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Ikke brugt   | 0 dage         |
 | Hy4 preview                  | Ikke brugt   | 0 dage         |
 | Hy3                          | Ikke brugt   | 0 dage         |
+| Union Alpha                  | Ikke brugt   | 0 dage         |

 - **Grok 4.6:** ZDR deaktiverer vigtige API-funktioner, der afhænger af lagrede data, herunder den tilstandsbevarende Responses API, Files and Collections og Batch API. [Læs mere](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Logfiler til overvågning af misbrug genereres ved al brug af API-funktioner og opbevares i op til 30 dage. [Læs mere](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -124,6 +124,7 @@ Du kan også få adgang til vores modeller gennem følgende API-endpoints.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ Vi understøtter en pay-as-you-go-model. Nedenfor er priserne **pr. 1M tokens**.
 | Model                             | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -249,6 +251,7 @@ De gratis modeller:
 - Nemotron 3 Ultra Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.
 - Nemotron 3.5 Lightning Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.
 - Big Pickle er en stealth-model, som er gratis på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.
+- Union Alpha er en stealth-model, som er gratis på OpenCode i en begrænset periode. Udbyderen følger en nul-opbevaringspolitik og bruger ikke dine data til at træne modeller.
 - Muse Spark 1.3 Contributor Free er tilgængelig på OpenCode i en begrænset periode. Teamet bruger denne tid til at indsamle feedback og forbedre modellen.

 <a href={email}>Kontakt os</a>, hvis du har spørgsmål.
@@ -78,6 +78,7 @@ Die aktuelle Liste der Modelle umfasst:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (für begrenzte Zeit)

 Die Liste der Modelle kann sich ändern, während wir neue testen und hinzufügen.

@@ -172,6 +173,7 @@ Tokenpreise gelten pro 1M Tokens.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                     |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                     |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                     |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Unbegrenzt**<br /><small>für begrenzte Zeit</small>       |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                     |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                     |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                     |
@@ -212,6 +214,7 @@ Die folgende Tabelle enthält eine geschätzte Anzahl von Anfragen basierend auf
 | DeepSeek V4 Flash Vision Exp                                    | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                     | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                             | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                     | Unbegrenzt                | Unbegrenzt                 | Unbegrenzt                  |
 | Grok 4.6                                                        | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                    | 2,050                     | 5,100                      | 10,250                      |

@@ -304,6 +307,7 @@ Du kannst auf die Go-Modelle auch über die folgenden API-Endpunkte zugreifen.
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 Die [Modell-ID](/docs/config/#models) in deiner OpenCode Config verwendet das Format `opencode-go/<model-id>`. Für Kimi K3 würdest du beispielsweise `opencode-go/kimi-k3` in deiner Config verwenden.

@@ -350,6 +354,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Nicht verwendet | 0 Tage            |
 | Hy4 preview                  | Nicht verwendet | 0 Tage            |
 | Hy3                          | Nicht verwendet | 0 Tage            |
+| Union Alpha                  | Nicht verwendet | 0 Tage            |

 - **Grok 4.6:** ZDR deaktiviert wichtige API-Funktionen, die von gespeicherten Daten abhängen, einschließlich der zustandsbehafteten Responses API, Files and Collections und der Batch API. [Mehr erfahren](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Für die Nutzung aller API-Funktionen werden Protokolle zur Missbrauchsüberwachung erstellt und bis zu 30 Tage lang aufbewahrt. [Mehr erfahren](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -115,6 +115,7 @@ Du kannst auch über die folgenden API-Endpunkte auf unsere Modelle zugreifen.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -142,6 +143,7 @@ Wir unterstützen ein Pay-as-you-go-Modell. Unten findest du die Preise **pro 1M
 | Model                             | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -238,6 +240,7 @@ Die kostenlosen Modelle:
 - Nemotron 3 Ultra Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.
 - Nemotron 3.5 Lightning Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.
 - Big Pickle ist ein Stealth-Modell, das für begrenzte Zeit kostenlos auf OpenCode verfügbar ist. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.
+- Union Alpha ist ein Stealth-Modell, das für begrenzte Zeit kostenlos auf OpenCode verfügbar ist. Der Anbieter befolgt eine Zero-Retention-Richtlinie und verwendet deine Daten nicht zum Trainieren von Modellen.
 - Muse Spark 1.3 Contributor Free ist für begrenzte Zeit auf OpenCode verfügbar. Das Team nutzt diese Zeit, um Feedback zu sammeln und das Modell zu verbessern.

 <a href={email}>Kontaktiere uns</a>, wenn du Fragen hast.
@@ -86,6 +86,7 @@ La lista actual de modelos incluye:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (por tiempo limitado)

 La lista de modelos puede cambiar a medida que probamos y agregamos otros nuevos.

@@ -180,6 +181,7 @@ Los precios de tokens se indican por 1M tokens.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30   | $1.20  | $0.006           | -                  | **$15**                                                       |
 | Hy4 preview                             | $0.834  | $2.501 | $0.042           | -                  | **$30**                                                       |
 | Hy3                                     | $0.14   | $0.58  | $0.035           | -                  | **$60**                                                       |
+| Union Alpha                             | Free    | Free   | Free             | -                  | **Ilimitado**<br /><small>por tiempo limitado</small>          |
 | Grok 4.6 (≤ 200K tokens)                | $2.00   | $6.00  | $0.50            | -                  | **$15**                                                       |
 | Grok 4.6 (> 200K tokens)                | $4.00   | $12.00 | $1.00            | -                  | **$15**                                                       |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20   | $1.20  | $0.02            | $0.25              | **$15**                                                       |
@@ -220,6 +222,7 @@ La siguiente tabla ofrece una cantidad estimada de peticiones basada en los patr
 | DeepSeek V4 Flash Vision Exp                                      | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                       | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                               | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                       | Ilimitado                 | Ilimitado                  | Ilimitado                   |
 | Grok 4.6                                                          | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                      | 2,050                     | 5,100                      | 10,250                      |

@@ -314,6 +317,7 @@ También puedes acceder a los modelos de Go a través de los siguientes endpoint
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 El [ID del modelo](/docs/config/#models) en tu configuración de OpenCode
 usa el formato `opencode-go/<model-id>`. Por ejemplo, para Kimi K3, usarías
@@ -362,6 +366,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | No utilizado             | 0 días             |
 | Hy4 preview                  | No utilizado             | 0 días             |
 | Hy3                          | No utilizado             | 0 días             |
+| Union Alpha                  | No utilizado             | 0 días             |

 - **Grok 4.6:** ZDR deshabilita funciones importantes de la API que dependen de datos almacenados, incluidas la Responses API con estado, Files and Collections y la Batch API. [Más información](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Se generan registros de supervisión de abusos para todo el uso de funciones de la API y se conservan durante un máximo de 30 días. [Más información](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -124,6 +124,7 @@ También puedes acceder a nuestros modelos a través de los siguientes endpoints
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ Admitimos un modelo de pago por uso. A continuación se muestran los precios **p
 | Modelo                            | Entrada | Salida  | Lectura en caché | Escritura en caché |
 | --------------------------------- | ------- | ------- | ---------------- | ------------------ |
 | Big Pickle                        | Free    | Free    | Free             | -                  |
+| Union Alpha                       | Free    | Free    | Free             | -                  |
 | MiMo-V2.5 Free                    | Free    | Free    | Free             | -                  |
 | Ling 3.0 Flash Fin Free           | Free    | Free    | Free             | -                  |
 | Nemotron 3 Ultra Free             | Free    | Free    | Free             | -                  |
@@ -249,6 +251,7 @@ Los modelos gratuitos:
 - Nemotron 3 Ultra Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.
 - Nemotron 3.5 Lightning Free está disponible en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.
 - Big Pickle es un modelo stealth que es gratuito en OpenCode por tiempo limitado. El equipo está usando este tiempo para recopilar comentarios y mejorar el modelo.
+- Union Alpha es un modelo stealth que es gratuito en OpenCode por tiempo limitado. Su proveedor sigue una política de retención cero y no utiliza tus datos para entrenar modelos.
 - Muse Spark 1.3 Contributor Free está disponible en OpenCode por tiempo limitado. El equipo está aprovechando este período para recopilar comentarios y mejorar el modelo.

 <a href={email}>Contáctanos</a> si tienes alguna pregunta.
@@ -76,6 +76,7 @@ La liste actuelle des modèles comprend :
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (pour une durée limitée)

 La liste des modèles peut changer au fur et à mesure que nous en testons et en ajoutons de nouveaux.

@@ -170,6 +171,7 @@ Les prix des tokens sont indiqués par million de tokens.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                  |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                  |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                  |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Illimité**<br /><small>pour une durée limitée</small>  |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                  |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                  |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                  |
@@ -210,6 +212,7 @@ Le tableau ci-dessous fournit une estimation du nombre de requêtes basée sur l
 | DeepSeek V4 Flash Vision Exp                                 | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                  | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                          | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                  | Illimité                  | Illimité                   | Illimité                    |
 | Grok 4.6                                                     | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                 | 2,050                     | 5,100                      | 10,250                      |

@@ -302,6 +305,7 @@ Vous pouvez également accéder aux modèles Go via les points de terminaison d'
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 L'[ID de modèle](/docs/config/#models) dans votre configuration OpenCode utilise le format `opencode-go/<model-id>`. Par exemple, pour Kimi K3, vous utiliseriez `opencode-go/kimi-k3` dans votre configuration.

@@ -348,6 +352,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Non utilisé              | 0 jour                   |
 | Hy4 preview                  | Non utilisé              | 0 jour                   |
 | Hy3                          | Non utilisé              | 0 jour                   |
+| Union Alpha                  | Non utilisé              | 0 jour                   |

 - **Grok 4.6:** Le ZDR désactive d’importantes fonctionnalités API qui dépendent des données stockées, notamment Responses API avec état, Files and Collections et Batch API. [En savoir plus](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Des journaux de surveillance des abus sont générés pour toute utilisation des fonctionnalités API et conservés pendant un maximum de 30 jours. [En savoir plus](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -115,6 +115,7 @@ Vous pouvez également accéder à nos modèles via les points de terminaison AP
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -142,6 +143,7 @@ Nous prenons en charge un modèle de paiement à l'utilisation. Vous trouverez c
 | Modèle                            | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -238,6 +240,7 @@ Les modèles gratuits :
 - Nemotron 3 Ultra Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.
 - Nemotron 3.5 Lightning Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.
 - Big Pickle est un modèle stealth gratuit sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.
+- Union Alpha est un modèle stealth gratuit sur OpenCode pour une durée limitée. Son fournisseur applique une politique de conservation nulle et n'utilise pas vos données pour entraîner des modèles.
 - Muse Spark 1.3 Contributor Free est disponible sur OpenCode pour une durée limitée. L'équipe utilise cette période pour recueillir des retours et améliorer le modèle.

 <a href={email}>Contactez-nous</a> si vous avez des questions.
@@ -86,6 +86,7 @@ The current list of models includes:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (limited time)

 The list of models may change as we test and add new ones.

@@ -182,6 +183,7 @@ Token prices are per 1M tokens.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                              |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                              |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                              |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Unlimited**<br /><small>limited time</small>       |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                              |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                              |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                              |
@@ -222,6 +224,7 @@ The table below provides an estimated request count based on typical Go usage pa
 | DeepSeek V4 Flash Vision Exp                             | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                              | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                      | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                              | Unlimited                 | Unlimited                  | Unlimited                   |
 | Grok 4.6                                                 | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                             | 2,050                     | 5,100                      | 10,250                      |

@@ -316,6 +319,7 @@ You can also access Go models through the following API endpoints.
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 The [model id](/docs/config/#models) in your OpenCode config
 uses the format `opencode-go/<model-id>`. For example, for Kimi K3, you would
@@ -364,6 +368,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Not used       | 0 days\*       |
 | Hy4 preview                  | Not used       | 0 days         |
 | Hy3                          | Not used       | 0 days         |
+| Union Alpha                  | Not used       | 0 days         |

 - **Grok 4.6:** ZDR disables important API features that depend on stored data, including the stateful Responses API, Files and Collections, and the Batch API. [Learn more](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Abuse monitoring logs are generated for all API feature usage and retained for up to 30 days. [Learn more](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -84,6 +84,7 @@ L'elenco attuale dei modelli include:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (per un periodo limitato)

 L'elenco dei modelli potrebbe cambiare man mano che ne testiamo e aggiungiamo di nuovi.

@@ -178,6 +179,7 @@ I prezzi dei token sono indicati per 1M token.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                   |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                   |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                   |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Illimitato**<br /><small>per un periodo limitato</small> |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                   |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                   |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                   |
@@ -218,6 +220,7 @@ La tabella seguente fornisce una stima del numero di richieste basata su pattern
 | DeepSeek V4 Flash Vision Exp                                  | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                   | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                           | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                   | Illimitato                | Illimitato                 | Illimitato                  |
 | Grok 4.6                                                      | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                  | 2,050                     | 5,100                      | 10,250                      |

@@ -312,6 +315,7 @@ Puoi anche accedere ai modelli Go tramite i seguenti endpoint API.
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 Il [model id](/docs/config/#models) nella tua OpenCode config
 utilizza il formato `opencode-go/<model-id>`. Ad esempio, per Kimi K3, useresti
@@ -360,6 +364,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Non utilizzato            | 0 giorni               |
 | Hy4 preview                  | Non utilizzato            | 0 giorni               |
 | Hy3                          | Non utilizzato            | 0 giorni               |
+| Union Alpha                  | Non utilizzato            | 0 giorni               |

 - **Grok 4.6:** ZDR disabilita importanti funzionalità API che dipendono dai dati archiviati, tra cui la Responses API con stato, Files and Collections e Batch API. [Scopri di più](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** I log di monitoraggio degli abusi vengono generati per l'utilizzo di tutte le funzionalità API e conservati per un massimo di 30 giorni. [Scopri di più](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -124,6 +124,7 @@ Puoi anche accedere ai nostri modelli tramite i seguenti endpoint API.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ Supportiamo un modello pay-as-you-go. Qui sotto trovi i prezzi **per 1M token**.
 | Modello                           | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -249,6 +251,7 @@ I modelli gratuiti:
 - Nemotron 3 Ultra Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.
 - Nemotron 3.5 Lightning Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.
 - Big Pickle è un modello stealth che è gratuito su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.
+- Union Alpha è un modello stealth gratuito su OpenCode per un periodo limitato. Il suo provider segue una politica di conservazione zero e non usa i tuoi dati per addestrare modelli.
 - Muse Spark 1.3 Contributor Free è disponibile su OpenCode per un periodo limitato. Il team usa questo periodo per raccogliere feedback e migliorare il modello.

 <a href={email}>Contattaci</a> se hai domande.
@@ -76,6 +76,7 @@ OpenCode Goをサブスクライブできるのは、1つのワークスペー
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (期間限定)

 新しいモデルをテストして追加するにつれて、モデルのリストは変更される場合があります。

@@ -167,6 +168,7 @@ OpenCodeに加えて、以下のクライアントがOpenCode Goで正常に動
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                              |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                              |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                              |
+| Union Alpha                             | Free   | Free   | Free        | -            | **無制限**<br /><small>期間限定</small>               |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                              |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                              |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                              |
@@ -207,6 +209,7 @@ OpenCodeに加えて、以下のクライアントがOpenCode Goで正常に動
 | DeepSeek V4 Flash Vision Exp                             | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                              | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                      | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                              | 無制限                    | 無制限                     | 無制限                      |
 | Grok 4.6                                                 | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                             | 2,050                     | 5,100                      | 10,250                      |

@@ -299,6 +302,7 @@ Goでは月額$10を支払い、含まれる月間利用枠はモデルによっ
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 OpenCode設定の[model id](/docs/config/#models)は、`opencode-go/<model-id>`という形式を使用します。たとえば、Kimi K3の場合は、設定で`opencode-go/kimi-k3`を使用します。

@@ -345,6 +349,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | 使用なし             | 0日         |
 | Hy4 preview                  | 使用なし             | 0日         |
 | Hy3                          | 使用なし             | 0日         |
+| Union Alpha                  | 使用なし             | 0日         |

 - **Grok 4.6:** ZDRでは、保存データに依存する重要なAPI機能（ステートフルなResponses API、Files and Collections、Batch APIなど）が無効になります。[詳しく見る](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr)。
 - **GPT 5.6 Luna:** 不正使用監視ログはすべてのAPI機能の使用時に生成され、最大30日間保持されます。[詳しく見る](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring)。
@@ -115,6 +115,7 @@ OpenCode Zen は、OpenCode のほかのプロバイダーと同じように動
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -142,6 +143,7 @@ https://opencode.ai/zen/v1/models
 | Model                             | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -238,6 +240,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free は期間限定で OpenCode で利用できます。チームはこの期間中にフィードバックを集め、モデルを改善しています。
 - Nemotron 3.5 Lightning Free は期間限定で OpenCode で利用できます。チームはこの期間中にフィードバックを集め、モデルを改善しています。
 - Big Pickle はステルスモデルで、期間限定で OpenCode で無料提供されています。チームはこの期間中にフィードバックを集め、モデルを改善しています。
+- Union Alpha はステルスモデルで、期間限定で OpenCode で無料提供されています。プロバイダーはゼロ保持ポリシーに従い、データをモデルのトレーニングに使用しません。
 - Muse Spark 1.3 Contributor Free は期間限定で OpenCode で利用できます。チームはこの期間を活用してフィードバックを収集し、モデルを改善しています。

 ご不明な点があれば、<a href={email}>お問い合わせください</a>。
@@ -76,6 +76,7 @@ workspace당 한 명의 멤버만 OpenCode Go를 구독할 수 있습니다.
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (한정된 기간)

 새로운 모델을 테스트하고 추가함에 따라 이 목록은 변경될 수 있습니다.

@@ -167,6 +168,7 @@ OpenCode 외에도 다음 클라이언트가 OpenCode Go에서 올바르게 작
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                |
+| Union Alpha                             | Free   | Free   | Free        | -            | **무제한**<br /><small>한정된 기간</small>              |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                |
@@ -207,6 +209,7 @@ OpenCode 외에도 다음 클라이언트가 OpenCode Go에서 올바르게 작
 | DeepSeek V4 Flash Vision Exp                               | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                        | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                | 무제한                    | 무제한                     | 무제한                      |
 | Grok 4.6                                                   | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                               | 2,050                     | 5,100                      | 10,250                      |

@@ -299,6 +302,7 @@ Go에서는 월 $10를 지불하며, 포함된 월간 사용량은 모델마다
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 OpenCode config의 [model id](/docs/config/#models)는 `opencode-go/<model-id>` 형식을 사용합니다. 예를 들어 Kimi K3의 경우 config에서 `opencode-go/kimi-k3`를 사용하면 됩니다.

@@ -345,6 +349,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | 사용되지 않음 | 0일         |
 | Hy4 preview                  | 사용되지 않음 | 0일         |
 | Hy3                          | 사용되지 않음 | 0일         |
+| Union Alpha                  | 사용되지 않음 | 0일         |

 - **Grok 4.6:** ZDR은 저장된 데이터에 의존하는 중요한 API 기능(상태 저장형 Responses API, Files and Collections, Batch API 포함)을 비활성화합니다. [자세히 알아보기](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** 모든 API 기능 사용에 대해 악용 모니터링 로그가 생성되며 최대 30일 동안 보존됩니다. [자세히 알아보기](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -115,6 +115,7 @@ OpenCode Zen은 OpenCode의 다른 provider와 똑같이 작동합니다.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -142,6 +143,7 @@ https://opencode.ai/zen/v1/models
 | 모델                              | 입력   | 출력    | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -238,6 +240,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다.
 - Nemotron 3.5 Lightning Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다.
 - Big Pickle은 한정된 기간 동안 OpenCode에서 무료로 제공되는 stealth model입니다. 팀은 이 기간에 피드백을 수집하고 모델을 개선합니다.
+- Union Alpha는 한정된 기간 동안 OpenCode에서 무료로 제공되는 stealth model입니다. 제공업체는 데이터 미보관 정책을 따르며 사용자의 데이터를 모델 학습에 사용하지 않습니다.
 - Muse Spark 1.3 Contributor Free는 한정된 기간 동안 OpenCode에서 제공됩니다. 팀은 이 기간을 활용해 피드백을 수집하고 모델을 개선하고 있습니다.

 궁금한 점이 있으면 <a href={email}>Contact us</a>로 문의해 주세요.
@@ -86,6 +86,7 @@ Den nåværende listen over modeller inkluderer:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (i en begrenset periode)

 Listen over modeller kan endres etter hvert som vi tester og legger til nye.

@@ -180,6 +181,7 @@ Tokenpriser er oppgitt per 1M tokens.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                   |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                   |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                   |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Ubegrenset**<br /><small>i en begrenset periode</small> |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                   |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                   |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                   |
@@ -220,6 +222,7 @@ Tabellen nedenfor viser et estimert antall forespørsler basert på typiske bruk
 | DeepSeek V4 Flash Vision Exp                                  | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                   | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                           | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                   | Ubegrenset                | Ubegrenset                 | Ubegrenset                  |
 | Grok 4.6                                                      | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                  | 2,050                     | 5,100                      | 10,250                      |

@@ -314,6 +317,7 @@ Du kan også få tilgang til Go-modeller gjennom følgende API-endepunkter.
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 [Modell-ID-en](/docs/config/#models) i din OpenCode-konfigurasjon
 bruker formatet `opencode-go/<model-id>`. For eksempel, for Kimi K3, vil du
@@ -362,6 +366,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Brukes ikke   | 0 dager         |
 | Hy4 preview                  | Brukes ikke   | 0 dager         |
 | Hy3                          | Brukes ikke   | 0 dager         |
+| Union Alpha                  | Brukes ikke   | 0 dager         |

 - **Grok 4.6:** ZDR deaktiverer viktige API-funksjoner som er avhengige av lagrede data, inkludert den tilstandsbaserte Responses API, Files and Collections og Batch API. [Les mer](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Logger for overvåking av misbruk genereres for all bruk av API-funksjoner og oppbevares i opptil 30 dager. [Les mer](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -124,6 +124,7 @@ Du kan også få tilgang til modellene våre gjennom følgende API-endepunkter.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ Vi støtter en pay-as-you-go-modell. Nedenfor er prisene **per 1M tokens**.
 | Modell                            | Inndata | Utdata  | Bufret lesing | Bufret skriving |
 | --------------------------------- | ------- | ------- | ------------- | --------------- |
 | Big Pickle                        | Free    | Free    | Free          | -               |
+| Union Alpha                       | Free    | Free    | Free          | -               |
 | MiMo-V2.5 Free                    | Free    | Free    | Free          | -               |
 | Ling 3.0 Flash Fin Free           | Free    | Free    | Free          | -               |
 | Nemotron 3 Ultra Free             | Free    | Free    | Free          | -               |
@@ -249,6 +251,7 @@ Gratis-modellene:
 - Nemotron 3 Ultra Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen.
 - Nemotron 3.5 Lightning Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen.
 - Big Pickle er en stealth-modell som er gratis på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen.
+- Union Alpha er en stealth-modell som er gratis på OpenCode i en begrenset periode. Leverandøren følger en nulloppbevaringspolicy og bruker ikke dataene dine til å trene modeller.
 - Muse Spark 1.3 Contributor Free er tilgjengelig på OpenCode i en begrenset periode. Teamet bruker denne tiden til å samle inn tilbakemeldinger og forbedre modellen.

 <a href={email}>Kontakt oss</a> hvis du har spørsmål.
@@ -80,6 +80,7 @@ Obecna lista modeli obejmuje:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (przez ograniczony czas)

 Lista modeli może ulec zmianie w miarę testowania i dodawania nowych.

@@ -174,6 +175,7 @@ Ceny tokenów podano za 1M tokenów.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30   | $1.20   | $0.006         | -              | **$15**                                                 |
 | Hy4 preview                             | $0.834  | $2.501  | $0.042         | -              | **$30**                                                 |
 | Hy3                                     | $0.14   | $0.58   | $0.035         | -              | **$60**                                                 |
+| Union Alpha                             | Free    | Free    | Free           | -              | **Bez limitu**<br /><small>przez ograniczony czas</small> |
 | Grok 4.6 (≤ 200K tokens)                | $2.00   | $6.00   | $0.50          | -              | **$15**                                                 |
 | Grok 4.6 (> 200K tokens)                | $4.00   | $12.00  | $1.00          | -              | **$15**                                                 |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20   | $1.20   | $0.02          | $0.25          | **$15**                                                 |
@@ -214,6 +216,7 @@ Poniższa tabela przedstawia szacunkową liczbę żądań na podstawie typowych
 | DeepSeek V4 Flash Vision Exp                                | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                 | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                         | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                 | Bez limitu                | Bez limitu                 | Bez limitu                  |
 | Grok 4.6                                                    | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                | 2,050                     | 5,100                      | 10,250                      |

@@ -306,6 +309,7 @@ Możesz również uzyskać dostęp do modeli Go za pośrednictwem następującyc
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 [ID modelu](/docs/config/#models) w Twojej konfiguracji OpenCode
 używa formatu `opencode-go/<model-id>`. Na przykład dla Kimi K3 należy użyć
@@ -354,6 +358,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Niewykorzystywane | 0 dni           |
 | Hy4 preview                  | Niewykorzystywane | 0 dni           |
 | Hy3                          | Niewykorzystywane | 0 dni           |
+| Union Alpha                  | Niewykorzystywane | 0 dni           |

 - **Grok 4.6:** ZDR wyłącza ważne funkcje API zależne od przechowywanych danych, w tym stanowy Responses API, Files and Collections oraz Batch API. [Dowiedz się więcej](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Dzienniki monitorowania nadużyć są generowane dla każdego użycia funkcji API i przechowywane przez maksymalnie 30 dni. [Dowiedz się więcej](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -124,6 +124,7 @@ Możesz też uzyskać dostęp do naszych modeli przez poniższe endpointy API.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ Obsługujemy model pay-as-you-go. Poniżej znajdują się ceny **za 1M tokenów*
 | Model                             | Wejście | Wyjście | Odczyt z cache | Zapis do cache |
 | --------------------------------- | ------- | ------- | -------------- | -------------- |
 | Big Pickle                        | Free    | Free    | Free           | -              |
+| Union Alpha                       | Free    | Free    | Free           | -              |
 | MiMo-V2.5 Free                    | Free    | Free    | Free           | -              |
 | Ling 3.0 Flash Fin Free           | Free    | Free    | Free           | -              |
 | Nemotron 3 Ultra Free             | Free    | Free    | Free           | -              |
@@ -249,6 +251,7 @@ Darmowe modele:
 - Nemotron 3 Ultra Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu.
 - Nemotron 3.5 Lightning Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu.
 - Big Pickle to stealth model, który jest darmowy w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu.
+- Union Alpha to stealth model, który jest darmowy w OpenCode przez ograniczony czas. Dostawca stosuje zasadę zerowego przechowywania i nie używa twoich danych do trenowania modeli.
 - Muse Spark 1.3 Contributor Free jest dostępny w OpenCode przez ograniczony czas. Zespół wykorzystuje ten czas do zbierania opinii i ulepszania modelu.

 <a href={email}>Skontaktuj się z nami</a>, jeśli masz pytania.
@@ -86,6 +86,7 @@ A lista atual de modelos inclui:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (por tempo limitado)

 A lista de modelos pode mudar conforme testamos e adicionamos novos.

@@ -180,6 +181,7 @@ Os preços de tokens são indicados por 1M tokens.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30   | $1.20  | $0.006           | -                | **$15**                                                 |
 | Hy4 preview                             | $0.834  | $2.501 | $0.042           | -                | **$30**                                                 |
 | Hy3                                     | $0.14   | $0.58  | $0.035           | -                | **$60**                                                 |
+| Union Alpha                             | Free    | Free   | Free             | -                | **Ilimitado**<br /><small>por tempo limitado</small>    |
 | Grok 4.6 (≤ 200K tokens)                | $2.00   | $6.00  | $0.50            | -                | **$15**                                                 |
 | Grok 4.6 (> 200K tokens)                | $4.00   | $12.00 | $1.00            | -                | **$15**                                                 |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20   | $1.20  | $0.02            | $0.25            | **$15**                                                 |
@@ -220,6 +222,7 @@ A tabela abaixo apresenta uma quantidade estimada de requisições com base nos
 | DeepSeek V4 Flash Vision Exp                                | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                 | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                         | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                 | Ilimitado                 | Ilimitado                  | Ilimitado                   |
 | Grok 4.6                                                    | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                | 2,050                     | 5,100                      | 10,250                      |

@@ -314,6 +317,7 @@ Você também pode acessar os modelos do Go através dos seguintes endpoints de
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 O [ID do modelo](/docs/config/#models) na sua configuração do OpenCode
 usa o formato `opencode-go/<model-id>`. Por exemplo, para o Kimi K3, você usaria
@@ -362,6 +366,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Não usado              | 0 dias            |
 | Hy4 preview                  | Não usado              | 0 dias            |
 | Hy3                          | Não usado              | 0 dias            |
+| Union Alpha                  | Não usado              | 0 dias            |

 - **Grok 4.6:** O ZDR desativa recursos importantes da API que dependem de dados armazenados, incluindo a Responses API com estado, Files and Collections e a Batch API. [Saiba mais](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Logs de monitoramento de abuso são gerados para todo uso de recursos da API e retidos por até 30 dias. [Saiba mais](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -115,6 +115,7 @@ Você também pode acessar nossos modelos pelos seguintes endpoints de API.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -142,6 +143,7 @@ Oferecemos um modelo pay-as-you-go. Abaixo estão os preços **por 1M tokens**.
 | Modelo                            | Entrada | Saída   | Leitura em cache | Escrita em cache |
 | --------------------------------- | ------- | ------- | ---------------- | ---------------- |
 | Big Pickle                        | Free    | Free    | Free             | -                |
+| Union Alpha                       | Free    | Free    | Free             | -                |
 | MiMo-V2.5 Free                    | Free    | Free    | Free             | -                |
 | Ling 3.0 Flash Fin Free           | Free    | Free    | Free             | -                |
 | Nemotron 3 Ultra Free             | Free    | Free    | Free             | -                |
@@ -238,6 +240,7 @@ Os modelos gratuitos:
 - Nemotron 3 Ultra Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo.
 - Nemotron 3.5 Lightning Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo.
 - Big Pickle é um modelo stealth que está gratuito no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo.
+- Union Alpha é um modelo stealth gratuito no OpenCode por tempo limitado. Seu provedor segue uma política de retenção zero e não usa seus dados para treinar modelos.
 - Muse Spark 1.3 Contributor Free está disponível no OpenCode por tempo limitado. A equipe está usando esse período para coletar feedback e melhorar o modelo.

 <a href={email}>Entre em contato</a> se você tiver alguma dúvida.
@@ -86,6 +86,7 @@ OpenCode Go работает так же, как и любой другой пр
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (ограниченное время)

 Список моделей может меняться по мере того, как мы тестируем и добавляем новые.

@@ -180,6 +181,7 @@ OpenCode Go предназначен для [OpenCode](https://opencode.ai) и
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                 |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                 |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                 |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Без ограничений**<br /><small>ограниченное время</small> |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                 |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                 |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                 |
@@ -220,6 +222,7 @@ OpenCode Go предназначен для [OpenCode](https://opencode.ai) и
 | DeepSeek V4 Flash Vision Exp                                | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                 | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                         | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                 | Без ограничений           | Без ограничений            | Без ограничений             |
 | Grok 4.6                                                    | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                | 2,050                     | 5,100                      | 10,250                      |

@@ -314,6 +317,7 @@ OpenCode Go предназначен для [OpenCode](https://opencode.ai) и
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 [ID модели](/docs/config/#models) в вашем конфиге OpenCode
 использует формат `opencode-go/<model-id>`. Например, для Kimi K3 вам нужно
@@ -362,6 +366,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Не используется  | 0 дней          |
 | Hy4 preview                  | Не используется  | 0 дней          |
 | Hy3                          | Не используется  | 0 дней          |
+| Union Alpha                  | Не используется  | 0 дней          |

 - **Grok 4.6:** ZDR отключает важные функции API, зависящие от сохраненных данных, включая Responses API с сохранением состояния, Files and Collections и Batch API. [Подробнее](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Журналы мониторинга злоупотреблений создаются при любом использовании функций API и хранятся до 30 дней. [Подробнее](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -124,6 +124,7 @@ OpenCode Zen работает как любой другой провайдер
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ https://opencode.ai/zen/v1/models
 | Модель                            | Вход   | Выход   | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -249,6 +251,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free доступна в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель.
 - Nemotron 3.5 Lightning Free доступна в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель.
 - Big Pickle — это скрытая модель, которая доступна бесплатно в OpenCode ограниченное время. Команда использует это время, чтобы собирать отзывы и улучшать модель.
+- Union Alpha — это скрытая модель, которая доступна бесплатно в OpenCode ограниченное время. Поставщик соблюдает политику нулевого хранения и не использует ваши данные для обучения моделей.
 - Muse Spark 1.3 Contributor Free доступна в OpenCode в течение ограниченного времени. Команда использует этот период для сбора отзывов и улучшения модели.

 <a href={email}>Свяжитесь с нами</a>, если у вас есть вопросы.
@@ -76,6 +76,7 @@ OpenCode Go ทำงานเหมือนกับผู้ให้บร
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (ในช่วงเวลาจำกัด)

 รายชื่อโมเดลอาจมีการเปลี่ยนแปลงเมื่อเราทำการทดสอบและเพิ่มโมเดลใหม่ๆ

@@ -167,6 +168,7 @@ OpenCode Go ออกแบบมาสำหรับ [OpenCode](https://openco
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                  |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                  |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                  |
+| Union Alpha                             | Free   | Free   | Free        | -            | **ไม่จำกัด**<br /><small>ในช่วงเวลาจำกัด</small>         |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                  |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                  |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                  |
@@ -207,6 +209,7 @@ OpenCode Go ออกแบบมาสำหรับ [OpenCode](https://openco
 | DeepSeek V4 Flash Vision Exp                                 | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                  | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                          | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                  | ไม่จำกัด                  | ไม่จำกัด                   | ไม่จำกัด                    |
 | Grok 4.6                                                     | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                 | 2,050                     | 5,100                      | 10,250                      |

@@ -299,6 +302,7 @@ OpenCode Go ออกแบบมาสำหรับ [OpenCode](https://openco
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 [model id](/docs/config/#models) ใน OpenCode config ของคุณจะใช้รูปแบบ `opencode-go/<model-id>` ตัวอย่างเช่น สำหรับ Kimi K3 คุณจะใช้ `opencode-go/kimi-k3` ใน config ของคุณ

@@ -345,6 +349,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | ไม่นำไปใช้  | 0 วัน              |
 | Hy4 preview                  | ไม่นำไปใช้  | 0 วัน              |
 | Hy3                          | ไม่นำไปใช้  | 0 วัน              |
+| Union Alpha                  | ไม่นำไปใช้  | 0 วัน              |

 - **Grok 4.6:** ZDR ปิดใช้งานฟีเจอร์ API สำคัญที่ต้องอาศัยข้อมูลที่จัดเก็บไว้ ซึ่งรวมถึง Responses API แบบมีสถานะ, Files and Collections และ Batch API [ดูข้อมูลเพิ่มเติม](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr)
 - **GPT 5.6 Luna:** ระบบจะสร้างบันทึกการตรวจสอบการใช้งานในทางที่ผิดสำหรับการใช้งานฟีเจอร์ API ทั้งหมด และเก็บรักษาไว้นานสูงสุด 30 วัน [ดูข้อมูลเพิ่มเติม](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring)
@@ -117,6 +117,7 @@ OpenCode Zen ทำงานเหมือน provider อื่น ๆ ใน
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -144,6 +145,7 @@ https://opencode.ai/zen/v1/models
 | Model                             | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -240,6 +242,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free เปิดให้ใช้บน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล
 - Nemotron 3.5 Lightning Free เปิดให้ใช้บน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล
 - Big Pickle เป็น stealth model ที่ใช้งานฟรีบน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อเก็บ feedback และปรับปรุงโมเดล
+- Union Alpha เป็น stealth model ที่ใช้งานฟรีบน OpenCode ในช่วงเวลาจำกัด ผู้ให้บริการใช้นโยบายไม่เก็บรักษาข้อมูลและไม่นำข้อมูลของคุณไปใช้ฝึกโมเดล
 - Muse Spark 1.3 Contributor Free เปิดให้ใช้งานบน OpenCode ในช่วงเวลาจำกัด ทีมกำลังใช้ช่วงเวลานี้เพื่อรวบรวมความคิดเห็นและปรับปรุงโมเดล

 <a href={email}>ติดต่อเรา</a> หากคุณมีคำถาม
@@ -76,6 +76,7 @@ Mevcut model listesi şunları içerir:
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (sınırlı bir süre için)

 Test edip yenilerini ekledikçe model listesi değişebilir.

@@ -167,6 +168,7 @@ Token fiyatları 1M token başına verilmiştir.
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                                    |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                                    |
 | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                                    |
+| Union Alpha                             | Free   | Free   | Free        | -            | **Sınırsız**<br /><small>sınırlı bir süre için</small>     |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                                    |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                                    |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                                    |
@@ -207,6 +209,7 @@ Aşağıdaki tabloda tipik Go kullanım modellerine dayalı tahmini istek sayıs
 | DeepSeek V4 Flash Vision Exp                                   | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                    | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                            | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                    | Sınırsız                  | Sınırsız                   | Sınırsız                    |
 | Grok 4.6                                                       | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                   | 2,050                     | 5,100                      | 10,250                      |

@@ -299,6 +302,7 @@ Go modellerine aşağıdaki API uç noktaları aracılığıyla da erişebilirsi
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 OpenCode yapılandırmanızdaki [model id](/docs/config/#models) formatı `opencode-go/<model-id>` şeklindedir. Örneğin, Kimi K3 için yapılandırmanızda `opencode-go/kimi-k3` kullanmalısınız.

@@ -345,6 +349,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | Kullanılmaz   | 0 gün        |
 | Hy4 preview                  | Kullanılmaz   | 0 gün        |
 | Hy3                          | Kullanılmaz   | 0 gün        |
+| Union Alpha                  | Kullanılmaz   | 0 gün        |

 - **Grok 4.6:** ZDR, durum bilgisi tutan Responses API, Files and Collections ve Batch API dahil olmak üzere saklanan verilere bağlı önemli API özelliklerini devre dışı bırakır. [Daha fazla bilgi](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
 - **GPT 5.6 Luna:** Tüm API özelliklerinin kullanımı için kötüye kullanım izleme günlükleri oluşturulur ve 30 güne kadar saklanır. [Daha fazla bilgi](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
@@ -115,6 +115,7 @@ Modellerimize aşağıdaki API uç noktaları aracılığıyla da erişebilirsin
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -142,6 +143,7 @@ Kullandıkça öde modelini destekliyoruz. Aşağıda **1M token başına** fiya
 | Model                             | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -238,6 +240,7 @@ Kredi kartı ücretleri maliyet üzerinden yansıtılır (%4.4 + işlem başına
 - Nemotron 3 Ultra Free, sınırlı bir süre için OpenCode'da ücretsizdir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor.
 - Nemotron 3.5 Lightning Free, sınırlı bir süre için OpenCode'da ücretsizdir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor.
 - Big Pickle, sınırlı bir süre için OpenCode'da ücretsiz olan gizli bir modeldir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor.
+- Union Alpha, sınırlı bir süre için OpenCode'da ücretsiz olan gizli bir modeldir. Sağlayıcısı sıfır saklama politikası uygular ve verilerinizi model eğitimi için kullanmaz.
 - Muse Spark 1.3 Contributor Free, sınırlı bir süre için OpenCode'da kullanılabilir. Ekip bu süreyi geri bildirim toplamak ve modeli iyileştirmek için kullanıyor.

 Sorularınız varsa <a href={email}>bizimle iletişime geçin</a>.
@@ -124,6 +124,7 @@ You can also access our models through the following API endpoints.
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -153,6 +154,7 @@ We support a pay-as-you-go model. Below are the prices **per 1M tokens**.
 | Model                             | Input  | Output  | Cached Read | Cached Write |
 | --------------------------------- | ------ | ------- | ----------- | ------------ |
 | Big Pickle                        | Free   | Free    | Free        | -            |
+| Union Alpha                       | Free   | Free    | Free        | -            |
 | MiMo-V2.5 Free                    | Free   | Free    | Free        | -            |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free        | -            |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free        | -            |
@@ -249,6 +251,7 @@ The free models:
 - Nemotron 3 Ultra Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
 - Nemotron 3.5 Lightning Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
 - Big Pickle is a stealth model that's free on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
+- Union Alpha is a stealth model that's free on OpenCode for a limited time. Its provider follows a zero-retention policy and does not use your data for model training.
 - Muse Spark 1.3 Contributor Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.

 <a href={email}>Contact us</a> if you have any questions.
@@ -76,6 +76,7 @@ OpenCode Go 的工作方式与 OpenCode 中的其他提供商一样。
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (限时)

 随着我们进行测试和添加新模型，该列表可能会发生变化。

@@ -166,6 +167,7 @@ Token 价格按每 1M tokens 列示。
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006    | -        | **$15**                                                 |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042    | -        | **$30**                                                 |
 | Hy3                                     | $0.14  | $0.58  | $0.035    | -        | **$60**                                                 |
+| Union Alpha                             | Free   | Free   | Free      | -        | **无限制**<br /><small>限时</small>                    |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50     | -        | **$15**                                                 |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00     | -        | **$15**                                                 |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02     | $0.25    | **$15**                                                 |
@@ -206,6 +208,7 @@ Token 价格按每 1M tokens 列示。
 | DeepSeek V4 Flash Vision Exp                                | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                 | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                         | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                 | 无限制                    | 无限制                     | 无限制                      |
 | Grok 4.6                                                    | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                | 2,050                     | 5,100                      | 10,250                      |

@@ -298,6 +301,7 @@ Token 价格按每 1M tokens 列示。
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 你的 OpenCode 配置中的 [模型 ID](/docs/config/#models) 使用 `opencode-go/<model-id>` 格式。例如，对于 Kimi K3，你将在配置中使用 `opencode-go/kimi-k3`。

@@ -344,6 +348,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | 不使用   | 0 天     |
 | Hy4 preview                  | 不使用   | 0 天     |
 | Hy3                          | 不使用   | 0 天     |
+| Union Alpha                  | 不使用   | 0 天     |

 - **Grok 4.6:** ZDR 会禁用依赖所存储数据的重要 API 功能，包括有状态的 Responses API、Files and Collections 和 Batch API。[了解更多](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr)。
 - **GPT 5.6 Luna:** 所有 API 功能的使用都会生成滥用监控日志，并最多保留 30 天。[了解更多](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring)。
@@ -115,6 +115,7 @@ OpenCode Zen 的工作方式与 OpenCode 中的任何其他提供商相同。
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -142,6 +143,7 @@ https://opencode.ai/zen/v1/models
 | 模型                              | 输入   | 输出    | 缓存读取 | 缓存写入 |
 | --------------------------------- | ------ | ------- | -------- | -------- |
 | Big Pickle                        | Free   | Free    | Free     | -        |
+| Union Alpha                       | Free   | Free    | Free     | -        |
 | MiMo-V2.5 Free                    | Free   | Free    | Free     | -        |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free     | -        |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free     | -        |
@@ -238,6 +240,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。
 - Nemotron 3.5 Lightning Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。
 - Big Pickle 是一个隐身模型，目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。
+- Union Alpha 是一个隐身模型，目前在 OpenCode 上限时免费提供。其提供商遵循零保留策略，不会将你的数据用于模型训练。
 - Muse Spark 1.3 Contributor Free 目前在 OpenCode 上限时免费提供。团队正在利用这段时间收集反馈并改进模型。

 如果你有任何问题，请<a href={email}>联系我们</a>。
@@ -76,6 +76,7 @@ OpenCode Go 的運作方式與 OpenCode 中的任何其他供應商相同。
 - **DeepSeek V4 Flash Vision Exp**
 - **Hy4 preview**
 - **Hy3**
+- **Union Alpha** (限時)

 隨著我們測試並加入新模型，模型清單可能會有所變動。

@@ -166,6 +167,7 @@ Token 價格按每 1M tokens 列示。
 | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006    | -        | **$15**                                                 |
 | Hy4 preview                             | $0.834 | $2.501 | $0.042    | -        | **$30**                                                 |
 | Hy3                                     | $0.14  | $0.58  | $0.035    | -        | **$60**                                                 |
+| Union Alpha                             | Free   | Free   | Free      | -        | **無限制**<br /><small>限時</small>                    |
 | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50     | -        | **$15**                                                 |
 | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00     | -        | **$15**                                                 |
 | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02     | $0.25    | **$15**                                                 |
@@ -206,6 +208,7 @@ Token 價格按每 1M tokens 列示。
 | DeepSeek V4 Flash Vision Exp                                | 6,500                     | 16,250                     | 32,500                      |
 | Hy4 preview                                                 | 1,350                     | 3,380                      | 6,770                       |
 | Hy3                                                         | 4,300                     | 10,750                     | 21,500                      |
+| Union Alpha                                                 | 無限制                    | 無限制                     | 無限制                      |
 | Grok 4.6                                                    | 169                       | 423                        | 845                         |
 | GPT 5.6 Luna                                                | 2,050                     | 5,100                      | 10,250                      |

@@ -298,6 +301,7 @@ Token 價格按每 1M tokens 列示。
 | Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
+| Union Alpha                  | union-alpha                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |

 您的 OpenCode 設定中的 [model id](/docs/config/#models) 使用 `opencode-go/<model-id>` 格式。例如，Kimi K3 在設定中應使用 `opencode-go/kimi-k3`。

@@ -344,6 +348,7 @@ https://opencode.ai/zen/go/v1/models
 | DeepSeek V4 Flash Vision Exp | 不使用   | 0 天     |
 | Hy4 preview                  | 不使用   | 0 天     |
 | Hy3                          | 不使用   | 0 天     |
+| Union Alpha                  | 不使用   | 0 天     |

 - **Grok 4.6:** ZDR 會停用依賴儲存資料的重要 API 功能，包括具狀態的 Responses API、Files and Collections 與 Batch API。[了解更多](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr)。
 - **GPT 5.6 Luna:** 所有 API 功能的使用都會產生濫用監控日誌，並保留最多 30 天。[了解更多](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring)。
@@ -119,6 +119,7 @@ OpenCode Zen 的運作方式和 OpenCode 中的其他供應商一樣。
 | Kimi K2.7 Code                  | kimi-k2.7-code                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Kimi K3                         | kimi-k3                         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Big Pickle                      | big-pickle                      | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
+| Union Alpha                     | union-alpha                     | `https://opencode.ai/zen/v1/messages`                     | `@ai-sdk/anthropic`         |
 | MiMo-V2.5 Free                  | mimo-v2.5-free                  | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Ling 3.0 Flash Fin Free         | ling-3.0-flash-fin-free         | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
 | Nemotron 3 Ultra Free           | nemotron-3-ultra-free           | `https://opencode.ai/zen/v1/chat/completions`             | `@ai-sdk/openai-compatible` |
@@ -147,6 +148,7 @@ https://opencode.ai/zen/v1/models
 | 模型                              | 輸入   | 輸出    | 快取讀取 | 快取寫入 |
 | --------------------------------- | ------ | ------- | -------- | -------- |
 | Big Pickle                        | Free   | Free    | Free     | -        |
+| Union Alpha                       | Free   | Free    | Free     | -        |
 | MiMo-V2.5 Free                    | Free   | Free    | Free     | -        |
 | Ling 3.0 Flash Fin Free           | Free   | Free    | Free     | -        |
 | Nemotron 3 Ultra Free             | Free   | Free    | Free     | -        |
@@ -243,6 +245,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。
 - Nemotron 3.5 Lightning Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。
 - Big Pickle 是一個隱身模型，在 OpenCode 上限時免費提供。團隊正在利用這段時間收集回饋並改進模型。
+- Union Alpha 是一個隱身模型，在 OpenCode 上限時免費提供。其供應商遵循零保留政策，不會將你的資料用於模型訓練。
 - Muse Spark 1.3 Contributor Free 在 OpenCode 上限時提供。團隊正在利用這段時間收集回饋並改進模型。

 如果你有任何問題，請<a href={email}>聯絡我們</a>。
Author	SHA1	Message	Date
Jack	5f42a3f991	docs: restore Go limits copy	2026-09-15 22:52:24 +08:00
Jack	8be0a642da	feat(go): add Union Alpha	2026-09-15 22:43:49 +08:00