Studio/opencode
5
0
Fork 0
mirror of https://gitee.com/zhangsken/opencode.git synced 2026-10-16 02:24:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

doc: go plus

Browse Source
This commit is contained in:
Frank
2026-09-28 06:43:54 -04:00
parent fed9d78791
commit 482a1cdf0d
20 changed files with 4859 additions and 3259 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.opencode/command/translate.md
+1 -1
View File
@@ -1,6 +1,6 @@
---
description: translate English to other languages
model: opencode/gpt-5.6-sol
model: opencode/gpt-6-sol
---
run git diff and translate changed english doc and UI copy files to other international languages. Translate all languages in parallel to save time.
packages/web/src/content/docs/ar/go.mdx
+255 -173
View File
@@ -1,17 +1,23 @@
---
title: Go
description: اشتراك منخفض التكلفة لنماذج البرمجة المفتوحة.
description: وصول موثوق إلى نماذج البرمجة المفتوحة مع مستويين للاستخدام.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهريًا** يمنحك وصولًا موثوقًا إلى نماذج البرمجة المفتوحة الشائعة.
OpenCode Go يمنحك وصولًا موثوقًا إلى نماذج البرمجة المفتوحة الشائعة، من خلال خطتين شهريتين:
| الخطة | السعر | الاستخدام المتضمن |
| ----- | ----- | ----------------- |
| **Go** | **$10/شهريًا** | وصول أقل تكلفة إلى النماذج أدناه |
| **Go Plus** | **$40/شهريًا** | حدود استخدام أعلى عبر النماذج أدناه |
يعمل Go مثل أي مزود آخر في OpenCode. تشترك في OpenCode Go وتحصل على مفتاح API الخاص بك. وهو **اختياري تمامًا**، ولا تحتاج إلى استخدامه لاستخدام OpenCode.
صُمّم أساسًا للمستخدمين الدوليين، ويوفّر وصولًا عالميًا مستقرًا.
صُممت الخدمة أساسًا للمستخدمين الدوليين، وتوفّر وصولًا عالميًا مستقرًا.
---
@@ -31,7 +37,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
2. ثم عملنا مع عدد قليل من المزودين للتأكد من تقديم هذه النماذج بالشكل الصحيح.
3. وأخيرًا، أجرينا مقارنات معيارية لمزيج النموذج/المزود، وتوصلنا إلى قائمة نشعر بالثقة في التوصية بها.
يمنحك OpenCode Go الوصول إلى هذه النماذج مقابل **$10/شهريًا**.
توفّر خطتا Go وGo Plus الوصول إلى هذه النماذج؛ اختر الخطة التي تناسب مقدار استخدامك لها.
---
@@ -39,12 +45,12 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
يعمل OpenCode Go مثل أي مزود آخر في OpenCode.
1. تسجّل الدخول إلى **<a href={console}>OpenCode Zen</a>**، وتشترك في Go، ثم تنسخ مفتاح API الخاص بك.
1. تسجّل الدخول إلى **<a href={console}>OpenCode Console</a>**، وتشترك في Go أو Go Plus، ثم تنسخ مفتاح API الخاص بك.
2. تشغّل الأمر `/connect` في TUI، وتختار `OpenCode Go`، ثم تلصق مفتاح API الخاص بك.
3. شغّل `/models` في TUI لرؤية قائمة النماذج المتاحة عبر Go.
:::note
يمكن لعضو واحد فقط في كل workspace الاشتراك في OpenCode Go.
يمكن لعضو واحد فقط في كل مساحة عمل الاشتراك في OpenCode Go أو Go Plus.
:::
تشمل قائمة النماذج الحالية:
@@ -54,13 +60,13 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (لفترة محدودة)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,9 +77,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
- **Muse Spark 1.2 Contributor** ([مناطق محدودة](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -81,7 +85,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (لفترة محدودة)
- **LongCat 2.5 Preview Free** (لفترة محدودة)
قد تتغير قائمة النماذج مع استمرارنا في اختبار نماذج جديدة وإضافتها.
@@ -130,64 +134,112 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
## حدود الاستخدام
تُحدَّد حدود الاستخدام كمبالغ شهرية بالدولار. يوضح الجدول أدناه الحد الشهري وتكاليف tokens لكل نموذج.
تُحدَّد حدود الاستخدام كمبالغ شهرية بالدولار. يوضح الجدول أدناه الحد الشهري لكل خطة وتكاليف الرموز لكل نموذج. أسعار الرموز هي نفسها في Go وGo Plus.
لكل نموذج حدود الاستخدام التالية: 5 ساعات — 20% من الحد الشهري؛ وأسبوعي — 50%؛ وشهري — 100%.
على سبيل المثال، إذا كان الحد الشهري لنموذج ما $60، فيمكنك إنفاق ما يصل إلى:
على سبيل المثال، إذا كان الحد الشهري لنموذج ما $60 في Go و$120 في Go Plus، فيمكنك إنفاق ما يصل إلى:
- **حد 5 ساعات** — $12 من الاستخدام
- **الحد الأسبوعي** — $30 من الاستخدام
- **الحد الشهري** — $60 من الاستخدام
- **حد 5 ساعات** — $12 في Go أو $24 في Go Plus
- **الحد الأسبوعي** — $30 في Go أو $60 في Go Plus
- **الحد الشهري** — $60 في Go أو $120 في Go Plus
أسعار tokens مُدرجة لكل 1M tokens.
عبر جميع النماذج، تتضمن Go مخصصات قدرها $12 لكل خمس ساعات، و$30 أسبوعيًا، و$60 شهريًا؛ بينما تتضمن Go Plus مخصصات قدرها $48 لكل خمس ساعات، و$120 أسبوعيًا، و$240 شهريًا. يحدد الحد الشهري لكل نموذج أدناه كيفية احتساب استخدامه ضمن هذه المخصصات.
| النموذج | الإدخال | الإخراج | القراءة المخزنة | الكتابة المخزنة | الحد الشهري |
| --------------------------------------- | ------- | ------- | --------------- | --------------- | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **غير محدود**<br /><small>لفترة محدودة</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **غير محدود**<br /><small>لفترة محدودة</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
أسعار الرموز مُدرجة لكل 1M رمز.
<Tabs syncKey="go-plan">
<TabItem label="Go">
| النموذج | الإدخال | الإخراج | القراءة المخزنة | الكتابة المخزنة | الحد الشهري |
| ------- | ------- | ------- | --------------- | --------------- | ----------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | مجاني | مجاني | مجاني | - | **غير محدود**<br /><small>لفترة محدودة</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | مجاني | مجاني | مجاني | - | **غير محدود**<br /><small>لفترة محدودة</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| النموذج | الإدخال | الإخراج | القراءة المخزنة | الكتابة المخزنة | الحد الشهري |
| ------- | ------- | ------- | --------------- | --------------- | ----------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | مجاني | مجاني | مجاني | - | **غير محدود**<br /><small>لفترة محدودة</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | مجاني | مجاني | مجاني | - | **غير محدود**<br /><small>لفترة محدودة</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** مجاني لفترة محدودة.
@@ -199,73 +251,110 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
### الطلبات المقدّرة
يوضح الجدول أدناه عددًا تقديريًا للطلبات استنادًا إلى أنماط استخدام Go المعتادة:
تقدّر الجداول أدناه أعداد الطلبات استنادًا إلى أنماط استخدام Go المعتادة. تتناسب تقديرات Go Plus مع حد الاستخدام الأعلى لكل نموذج.
| Model | الطلبات لكل 5 ساعات | الطلبات في الأسبوع | الطلبات في الشهر |
| ---------------------------- | ------------------- | ------------------ | ---------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | غير محدود | غير محدود | غير محدود |
| LongCat 2.5 Preview Free | غير محدود | غير محدود | غير محدود |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
تستخدم التقديرات أعداد tokens التالية لكل طلب؛ ويختلف الاستخدام الفعلي.
| النموذج | الطلبات لكل 5 ساعات | الطلبات في الأسبوع | الطلبات في الشهر |
| ------- | ------------------- | ------------------ | ---------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | غير محدود | غير محدود | غير محدود |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | غير محدود | غير محدود | غير محدود |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
- Grok 4.7/4.6 — ‏390 input، و32,500 cached، و120 output tokens لكل طلب
- GLM-5.3-Flash — ‏1,000 input، و55,000 cached، و200 output tokens لكل طلب
- GLM-5.3/5.2/5.1 — ‏700 input، و52,000 cached، و150 output tokens لكل طلب
- GPT 6 Luna — ‏1,000 توكن إدخال، و50,000 توكن مخزّن مؤقتًا، و220 توكن إخراج لكل طلب
- GPT 5.6 Luna — ‏1,000 توكن إدخال، و50,000 توكن مخزّن مؤقتًا، و220 توكن إخراج لكل طلب
- Kimi K3 — ‏1,050 input، و76,500 cached، و300 output tokens لكل طلب
- Kimi K2.7/K2.6 — ‏870 input، و55,000 cached، و200 output tokens لكل طلب
- LongCat-2.0 — ‏920 input، و88,900 cached، و200 output tokens لكل طلب
- DeepSeek V4.1 Flash — ‏410 input، و71,300 cached، و310 output tokens لكل طلب
- DeepSeek V4 Pro — ‏750 input، و82,000 cached، و290 output tokens لكل طلب
- DeepSeek V4 Flash — ‏410 input، و71,300 cached، و310 output tokens لكل طلب
- DeepSeek V4 Flash Vision Exp — ‏410 input، و71,300 cached، و310 output tokens لكل طلب
- MiniMax M3 — ‏510 input، و56,000 cached، و190 output tokens لكل طلب
- MiniMax M2.7 — ‏300 input، و55,000 cached، و125 output tokens لكل طلب
- Muse Spark 1.3 Contributor — ‏620 input، و71,400 cached، و300 output tokens لكل طلب
- Muse Spark 1.2 Contributor — ‏620 input، و71,400 cached، و300 output tokens لكل طلب
- Qwen3.8 Max — ‏420 input، و66,000 cached، و200 output tokens لكل طلب
- Qwen3.8 Flash — ‏600 input، و58,000 cached، و200 output tokens لكل طلب
- Qwen3.7 Max — ‏420 input، و66,000 cached، و200 output tokens لكل طلب
- Qwen3.7 Plus — ‏500 input، و57,000 cached، و190 output tokens لكل طلب
- Qwen3.6 Plus — ‏500 input، و57,000 cached، و190 output tokens لكل طلب
- Hy4 preview — ‏830 input، و71,500 cached، و295 output tokens لكل طلب
- Hy3 — ‏830 input، و71,500 cached، و295 output tokens لكل طلب
- MiMo-V2.6-Flash — ‏830 input، و71,500 cached، و295 output tokens لكل طلب
- MiMo-V2.6-Pro — ‏790 input، و86,000 cached، و305 output tokens لكل طلب
- MiMo-V2.5 — ‏830 input، و71,500 cached، و295 output tokens لكل طلب
- MiMo-V2.5-Pro — ‏790 input، و86,000 cached، و305 output tokens لكل طلب
</TabItem>
<TabItem label="Go Plus">
| النموذج | الطلبات لكل 5 ساعات | الطلبات في الأسبوع | الطلبات في الشهر |
| ------- | ------------------- | ------------------ | ---------------- |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | غير محدود | غير محدود | غير محدود |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | غير محدود | غير محدود | غير محدود |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
تستخدم التقديرات أعداد الرموز التالية لكل طلب؛ ويختلف الاستخدام الفعلي.
- Grok 4.7/4.6 — 390 رمز إدخال، و32,500 رمزًا مخزنًا مؤقتًا، و120 رمز إخراج لكل طلب
- GLM-5.3-Flash — 1,000 رمز إدخال، و55,000 رمز مخزن مؤقتًا، و200 رمز إخراج لكل طلب
- GLM-5.3/5.2 — 700 رمز إدخال، و52,000 رمز مخزن مؤقتًا، و150 رمز إخراج لكل طلب
- GPT 6 Luna — 1,000 رمز إدخال، و50,000 رمز مخزن مؤقتًا، و220 رمز إخراج لكل طلب
- GPT 5.6 Luna — 1,000 رمز إدخال، و50,000 رمز مخزن مؤقتًا، و220 رمز إخراج لكل طلب
- Kimi K3 — 1,050 رمز إدخال، و76,500 رمز مخزن مؤقتًا، و300 رمز إخراج لكل طلب
- Kimi K2.7/K2.6 — 870 رمز إدخال، و55,000 رمز مخزن مؤقتًا، و200 رمز إخراج لكل طلب
- LongCat-2.0 — 920 رمز إدخال، و88,900 رمز مخزن مؤقتًا، و200 رمز إخراج لكل طلب
- DeepSeek V4.1 Flash — 410 رمز إدخال، و71,300 رمز مخزن مؤقتًا، و310 رمز إخراج لكل طلب
- DeepSeek V4 Pro — 750 رمز إدخال، و82,000 رمز مخزن مؤقتًا، و290 رمز إخراج لكل طلب
- DeepSeek V4 Flash — 410 رمز إدخال، و71,300 رمز مخزن مؤقتًا، و310 رمز إخراج لكل طلب
- DeepSeek V4 Flash Vision Exp — 410 رمز إدخال، و71,300 رمز مخزن مؤقتًا، و310 رمز إخراج لكل طلب
- MiniMax M3 — 510 رمز إدخال، و56,000 رمز مخزن مؤقتًا، و190 رمز إخراج لكل طلب
- MiniMax M2.7 — 300 رمز إدخال، و55,000 رمز مخزن مؤقتًا، و125 رمز إخراج لكل طلب
- Muse Spark 1.3 Contributor — 620 رمز إدخال، و71,400 رمز مخزن مؤقتًا، و300 رمز إخراج لكل طلب
- Muse Spark 1.2 Contributor — 620 رمز إدخال، و71,400 رمز مخزن مؤقتًا، و300 رمز إخراج لكل طلب
- MiMo-V2.6-Flash — 830 رمز إدخال، و71,500 رمز مخزن مؤقتًا، و295 رمز إخراج لكل طلب
- MiMo-V2.6-Pro — 790 رمز إدخال، و86,000 رمز مخزن مؤقتًا، و305 رمز إخراج لكل طلب
- MiMo-V2.5 — 830 رمز إدخال، و71,500 رمز مخزن مؤقتًا، و295 رمز إخراج لكل طلب
- MiMo-V2.5-Pro — 790 رمز إدخال، و86,000 رمز مخزن مؤقتًا، و305 رمز إخراج لكل طلب
- Qwen3.8 Max — 420 رمز إدخال، و66,000 رمز مخزن مؤقتًا، و200 رمز إخراج لكل طلب
- Qwen3.8 Flash — 600 رمز إدخال، و58,000 رمز مخزن مؤقتًا، و200 رمز إخراج لكل طلب
- Qwen3.7 Plus — 500 رمز إدخال، و57,000 رمز مخزن مؤقتًا، و190 رمز إخراج لكل طلب
- Hy4 preview — 830 رمز إدخال، و71,500 رمز مخزن مؤقتًا، و295 رمز إخراج لكل طلب
- Hy3 — 830 رمز إدخال، و71,500 رمز مخزن مؤقتًا، و295 رمز إخراج لكل طلب
يمكنك تتبّع استخدامك الحالي في **<a href={console}>console</a>**.
@@ -285,7 +374,7 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
### لماذا يكون الاستخدام أقل لبعض النماذج
مع Go، تدفع $10 شهريًا، ويختلف الاستخدام الشهري المتضمن حسب النموذج.
مع Go، يختلف الاستخدام الشهري المتضمن حسب النموذج.
نحقق ذلك لمعظم النماذج من خلال الخصومات على الكميات الكبيرة وسعة GPU المحجوزة. ثم ننقل هذه الوفورات إليك في صورة استخدام شهري أعلى.
@@ -299,8 +388,8 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
يمكنك أيضًا الوصول إلى نماذج Go عبر نقاط نهاية API التالية.
| Model | Model ID | Endpoint | AI SDK Package |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| النموذج | معرّف النموذج | نقطة النهاية | حزمة AI SDK |
| ------- | ------------- | ------------ | ----------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| GPT 6 Luna | gpt-6-luna | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -308,11 +397,11 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -323,20 +412,16 @@ OpenCode Go هو اشتراك منخفض التكلفة بقيمة **$10/شهر
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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.
يستخدم [معرّف النموذج](/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.
---
@@ -352,47 +437,44 @@ https://opencode.ai/zen/go/v1/models
## الخصوصية
| النموذج | تدريب النموذج | الاحتفاظ بالبيانات |
| ---------------------------- | ------------- | ------------------ |
| Grok 4.7 | غير مستخدَمة | 30 يومًا |
| Grok 4.6 | غير مستخدَمة | 30 يومًا |
| GPT 6 Luna | غير مستخدَمة | 30 يومًا |
| GPT 5.6 Luna | غير مستخدَمة | 30 يومًا |
| GLM-5.3-Flash | غير مستخدَمة | 0 أيام |
| GLM-5.3 | غير مستخدَمة | 0 أيام |
| GLM-5.2 | غير مستخدَمة | 0 أيام |
| GLM-5.1 | غير مستخدَمة | 0 أيام |
| Kimi K3 | غير مستخدَمة | 0 أيام |
| Kimi K2.7 Code | غير مستخدَمة | 0 أيام |
| Kimi K2.6 | غير مستخدَمة | 0 أيام |
| LongCat-2.0 | غير مستخدَمة | 0 أيام |
| MiMo-V2.6-Pro | غير مستخدَمة | 0 أيام |
| MiMo-V2.6-Flash | غير مستخدَمة | 0 أيام |
| MiMo-V2.5-Pro | غير مستخدَمة | 0 أيام |
| MiMo-V2.5 | غير مستخدَمة | 0 أيام |
| Qwen3.8 Max | غير مستخدَمة | 0 أيام |
| Qwen3.8 Flash | غير مستخدَمة | 0 أيام |
| Qwen3.7 Max | غير مستخدَمة | 0 أيام |
| Qwen3.7 Plus | غير مستخدَمة | 0 أيام |
| Qwen3.6 Plus | غير مستخدَمة | 0 أيام |
| MiniMax M3 | غير مستخدَمة | 0 أيام |
| MiniMax M2.7 | غير مستخدَمة | 0 أيام |
| Muse Spark 1.3 Contributor | نعم | ليست ZDR |
| Muse Spark 1.2 Contributor | نعم | ليست ZDR |
| DeepSeek V4.1 Flash | غير مستخدَمة | 0 أيام |
| DeepSeek V4 Pro | غير مستخدَمة | 0 أيام |
| DeepSeek V4 Flash | غير مستخدَمة | 0 أيام |
| DeepSeek V4 Flash Vision Exp | غير مستخدَمة | 0 أيام |
| Hy4 preview | غير مستخدَمة | 0 أيام |
| Hy3 | غير مستخدَمة | 0 أيام |
| Space Bunny Free | غير مستخدَمة | 0 أيام |
| LongCat 2.5 Preview Free | غير مستخدَمة | 0 أيام |
| النموذج | تدريب النموذج | الاحتفاظ بالبيانات |
| ------- | ------------- | ------------------ |
| Grok 4.7 | غير مستخدَمة | 30 يومًا |
| Grok 4.6 | غير مستخدَمة | 30 يومًا |
| GPT 6 Luna | غير مستخدَمة | 30 يومًا |
| GPT 5.6 Luna | غير مستخدَمة | 30 يومًا |
| GLM-5.3-Flash | غير مستخدَمة | 0 أيام |
| GLM-5.3 | غير مستخدَمة | 0 أيام |
| GLM-5.2 | غير مستخدَمة | 0 أيام |
| Kimi K3 | غير مستخدَمة | 0 أيام |
| Kimi K2.7 Code | غير مستخدَمة | 0 أيام |
| Kimi K2.6 | غير مستخدَمة | 0 أيام |
| LongCat-2.0 | غير مستخدَمة | 0 أيام |
| MiMo-V2.6-Pro | غير مستخدَمة | 0 أيام |
| MiMo-V2.6-Flash | غير مستخدَمة | 0 أيام |
| MiMo-V2.5-Pro | غير مستخدَمة | 0 أيام |
| MiMo-V2.5 | غير مستخدَمة | 0 أيام |
| Qwen3.8 Max | غير مستخدَمة | 0 أيام |
| Qwen3.8 Flash | غير مستخدَمة | 0 أيام |
| Qwen3.7 Plus | غير مستخدَمة | 0 أيام |
| MiniMax M3 | غير مستخدَمة | 0 أيام |
| MiniMax M2.7 | غير مستخدَمة | 0 أيام |
| Muse Spark 1.3 Contributor | نعم | ليست ZDR |
| Muse Spark 1.2 Contributor | نعم | ليست ZDR |
| DeepSeek V4.1 Flash | غير مستخدَمة | 0 أيام\* |
| DeepSeek V4 Pro | غير مستخدَمة | 0 أيام\* |
| DeepSeek V4 Flash | غير مستخدَمة | 0 أيام\* |
| DeepSeek V4 Flash Vision Exp | غير مستخدَمة | 0 أيام\* |
| Hy4 preview | غير مستخدَمة | 0 أيام |
| Hy3 | غير مستخدَمة | 0 أيام |
| Space Bunny Free | غير مستخدَمة | 0 أيام |
| LongCat 2.5 Preview Free | غير مستخدَمة | 0 أيام |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** أسعار توكنات مخفّضة للغاية مقابل منح الإذن باستخدام مطالباتك وإكمالات النموذج لتدريب نماذج Meta المستقبلية. يقتصر التوفر على المناطق التي تسمح بها [سياسة الاستخدام الجغرافي](https://ai.developer.meta.com/legal/geographic-use-policy) الخاصة بـ Meta. [اعرف المزيد](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** أسعار توكنات مخفّضة للغاية مقابل منح الإذن باستخدام مطالباتك وإكمالات النموذج لتدريب نماذج Meta المستقبلية. يقتصر التوفر على المناطق التي تسمح بها [سياسة الاستخدام الجغرافي](https://ai.developer.meta.com/legal/geographic-use-policy) الخاصة بـ Meta. [اعرف المزيد](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** تُجدَّد اتفاقية ZDR شهريًا. الاتفاقية الحالية سارية حتى 30 سبتمبر 2026.
- **Muse Spark 1.3 Contributor:** أسعار رموز مخفّضة للغاية مقابل منح الإذن باستخدام مطالباتك وإكمالات النموذج لتدريب نماذج Meta المستقبلية. يقتصر التوفر على المناطق التي تسمح بها [سياسة الاستخدام الجغرافي](https://ai.developer.meta.com/legal/geographic-use-policy) الخاصة بـ Meta. [اعرف المزيد](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** أسعار رموز مخفّضة للغاية مقابل منح الإذن باستخدام مطالباتك وإكمالات النموذج لتدريب نماذج Meta المستقبلية. يقتصر التوفر على المناطق التي تسمح بها [سياسة الاستخدام الجغرافي](https://ai.developer.meta.com/legal/geographic-use-policy) الخاصة بـ Meta. [اعرف المزيد](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** تُجدَّد اتفاقية ZDR شهريًا. الاتفاقية الحالية سارية حتى 31 أكتوبر 2026.
---
packages/web/src/content/docs/bs/go.mdx
+236 -162
View File
@@ -1,19 +1,23 @@
---
title: Go
description: Povoljna pretplata za otvorene modele za programiranje.
description: Pouzdan pristup otvorenim modelima za programiranje uz dva nivoa korištenja.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go je povoljna pretplata od **$10/mjesečno** koja vam pruža pouzdan pristup popularnim otvorenim modelima za programiranje.
OpenCode Go vam pruža pouzdan pristup popularnim otvorenim modelima za programiranje kroz dvije mjesečne pretplate:
Go radi kao bilo koji drugi provajder u OpenCode-u. Pretplatite se na OpenCode Go i
dobijete svoj API ključ. On je **potpuno opcionalan** i ne morate ga koristiti da
biste koristili OpenCode.
| Plan | Cijena | Uključena potrošnja |
| ---- | ------ | ------------------- |
| **Go** | **$10/mjesečno** | Povoljniji pristup modelima navedenim ispod |
| **Go Plus** | **$40/mjesečno** | Viša ograničenja korištenja za modele navedene ispod |
Prvenstveno je namijenjen međunarodnim korisnicima i pruža stabilan globalni pristup.
Go radi kao bilo koji drugi provajder u OpenCode-u. Pretplatite se na OpenCode Go i dobijete svoj API ključ. On je **potpuno opcionalan** i ne morate ga koristiti da biste koristili OpenCode.
Usluga je prvenstveno namijenjena međunarodnim korisnicima i pruža stabilan globalni pristup.
---
@@ -39,7 +43,7 @@ Da bismo to popravili, uradili smo nekoliko stvari:
3. Na kraju smo benchmarkovali kombinaciju modela/provajdera i osmislili
listu koju rado preporučujemo.
OpenCode Go vam daje pristup ovim modelima za **$10/mjesečno**.
I Go i Go Plus pružaju pristup ovim modelima; odaberite plan koji odgovara tome koliko ih koristite.
---
@@ -47,14 +51,12 @@ OpenCode Go vam daje pristup ovim modelima za **$10/mjesečno**.
OpenCode Go radi kao bilo koji drugi provajder u OpenCode-u.
1. Prijavite se na **<a href={console}>OpenCode Zen</a>**, pretplatite se na Go i
kopirajte svoj API ključ.
2. Pokrenite komandu `/connect` u TUI-ju, odaberite `OpenCode Go` i zalijepite
svoj API ključ.
1. Prijavite se na **<a href={console}>OpenCode Console</a>**, pretplatite se na Go ili Go Plus i kopirajte svoj API ključ.
2. Pokrenite komandu `/connect` u TUI-ju, odaberite `OpenCode Go` i zalijepite svoj API ključ.
3. Pokrenite `/models` u TUI-ju da vidite listu modela dostupnih kroz Go.
:::note
Samo jedan član po radnom prostoru (workspace) može se pretplatiti na OpenCode Go.
Samo jedan član po radnom prostoru može se pretplatiti na OpenCode Go ili Go Plus.
:::
Trenutna lista modela uključuje:
@@ -64,13 +66,13 @@ Trenutna lista modela uključuje:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (ograničeno vrijeme)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -81,9 +83,7 @@ Trenutna lista modela uključuje:
- **Muse Spark 1.2 Contributor** ([ograničene regije](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -91,7 +91,7 @@ Trenutna lista modela uključuje:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (ograničeno vrijeme)
- **LongCat 2.5 Preview Free** (ograničeno vrijeme)
Lista modela se može mijenjati dok testiramo i dodajemo nove.
@@ -140,64 +140,112 @@ istražili. Povezani izvještaji prate ispravke i zaobilazna rješenja.
## Ograničenja upotrebe
Ograničenja upotrebe definirana su kao mjesečni iznosi u dolarima. Tabela ispod prikazuje mjesečno ograničenje i troškove tokena za svaki model.
Ograničenja upotrebe definirana su kao mjesečni iznosi u dolarima. Tabela ispod prikazuje mjesečno ograničenje svakog plana i troškove tokena za svaki model. Cijene tokena jednake su za Go i Go Plus.
Svaki model ima sljedeća ograničenja upotrebe: 5 sati — 20% mjesečnog ograničenja; sedmično — 50%; i mjesečno — 100%.
Na primjer, ako model ima mjesečno ograničenje od $60, možete potrošiti do:
Na primjer, ako model ima mjesečno ograničenje od $60 na Go i $120 na Go Plus, možete potrošiti do:
- **Ograničenje od 5 sati** — $12 potrošnje
- **Sedmično ograničenje** — $30 potrošnje
- **Mjesečno ograničenje** — $60 potrošnje
- **Ograničenje od 5 sati** — $12 na Go ili $24 na Go Plus
- **Sedmično ograničenje** — $30 na Go ili $60 na Go Plus
- **Mjesečno ograničenje** — $60 na Go ili $120 na Go Plus
Za sve modele zajedno, Go ima ograničenja od $12 za pet sati, $30 sedmično i $60 mjesečno; Go Plus ima ograničenja od $48 za pet sati, $120 sedmično i $240 mjesečno. Mjesečno ograničenje svakog modela ispod određuje kako se njegovo korištenje uračunava u ta ograničenja.
Cijene tokena navedene su za 1M tokena.
| Model | Input | Output | Cached Read | Cached Write | Mjesečno ograničenje |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ------------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Neograničeno**<br /><small>ograničeno vrijeme</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Neograničeno**<br /><small>ograničeno vrijeme</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Ulaz | Izlaz | Keširano čitanje | Keširano pisanje | Mjesečno ograničenje |
| ----- | ---- | ----- | ---------------- | ---------------- | -------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Besplatno | Besplatno | Besplatno | - | **Neograničeno**<br /><small>ograničeno vrijeme</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Besplatno | Besplatno | Besplatno | - | **Neograničeno**<br /><small>ograničeno vrijeme</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Model | Ulaz | Izlaz | Keširano čitanje | Keširano pisanje | Mjesečno ograničenje |
| ----- | ---- | ----- | ---------------- | ---------------- | -------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Besplatno | Besplatno | Besplatno | - | **Neograničeno**<br /><small>ograničeno vrijeme</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Besplatno | Besplatno | Besplatno | - | **Neograničeno**<br /><small>ograničeno vrijeme</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Besplatan ograničeno vrijeme.
@@ -209,49 +257,88 @@ Cijene tokena navedene su za 1M tokena.
### Procijenjeni broj zahtjeva
Tabela ispod daje procijenjeni broj zahtjeva na osnovu tipičnih obrazaca korištenja Go-a:
Tabele ispod procjenjuju broj zahtjeva na osnovu tipičnih obrazaca korištenja Go-a. Procjene za Go Plus rastu u skladu s višim ograničenjem korištenja svakog modela.
| Model | zahtjeva na 5 sati | zahtjeva sedmično | zahtjeva mjesečno |
| ---------------------------- | ------------------ | ----------------- | ----------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Neograničeno | Neograničeno | Neograničeno |
| LongCat 2.5 Preview Free | Neograničeno | Neograničeno | Neograničeno |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Zahtjeva na 5 sati | Zahtjeva sedmično | Zahtjeva mjesečno |
| ----- | ------------------ | ----------------- | ----------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Neograničeno | Neograničeno | Neograničeno |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Neograničeno | Neograničeno | Neograničeno |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Model | Zahtjeva na 5 sati | Zahtjeva sedmično | Zahtjeva mjesečno |
| ----- | ------------------ | ----------------- | ----------------- |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Neograničeno | Neograničeno | Neograničeno |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Neograničeno | Neograničeno | Neograničeno |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Procjene koriste sljedeći broj tokena po zahtjevu; stvarna potrošnja varira.
- Grok 4.7/4.6 — 390 ulaznih, 32,500 keširanih, 120 izlaznih tokena po zahtjevu
- GLM-5.3-Flash — 1,000 ulaznih (input), 55,000 keširanih, 200 izlaznih (output) tokena po zahtjevu
- GLM-5.3/5.2/5.1 — 700 ulaznih (input), 52,000 keširanih, 150 izlaznih (output) tokena po zahtjevu
- GLM-5.3-Flash — 1,000 ulaznih, 55,000 keširanih, 200 izlaznih tokena po zahtjevu
- GLM-5.3/5.2 — 700 ulaznih, 52,000 keširanih, 150 izlaznih tokena po zahtjevu
- GPT 6 Luna — 1,000 ulaznih, 50,000 keširanih, 220 izlaznih tokena po zahtjevu
- GPT 5.6 Luna — 1,000 ulaznih, 50,000 keširanih, 220 izlaznih tokena po zahtjevu
- Kimi K3 — 1,050 ulaznih, 76,500 keširanih, 300 izlaznih tokena po zahtjevu
@@ -265,17 +352,15 @@ Procjene koriste sljedeći broj tokena po zahtjevu; stvarna potrošnja varira.
- MiniMax M2.7 — 300 ulaznih, 55,000 keširanih, 125 izlaznih tokena po zahtjevu
- Muse Spark 1.3 Contributor — 620 ulaznih, 71,400 keširanih, 300 izlaznih tokena po zahtjevu
- Muse Spark 1.2 Contributor — 620 ulaznih, 71,400 keširanih, 300 izlaznih tokena po zahtjevu
- Qwen3.8 Max — 420 ulaznih, 66,000 keširanih, 200 izlaznih tokena po zahtjevu
- Qwen3.8 Flash — 600 ulaznih, 58,000 keširanih, 200 izlaznih tokena po zahtjevu
- Qwen3.7 Max — 420 ulaznih, 66,000 keširanih, 200 izlaznih tokena po zahtjevu
- Qwen3.7 Plus — 500 ulaznih, 57,000 keširanih, 190 izlaznih tokena po zahtjevu
- Qwen3.6 Plus — 500 ulaznih, 57,000 keširanih, 190 izlaznih tokena po zahtjevu
- Hy4 preview — 830 ulaznih, 71,500 keširanih, 295 izlaznih tokena po zahtjevu
- Hy3 — 830 ulaznih, 71,500 keširanih, 295 izlaznih tokena po zahtjevu
- MiMo-V2.6-Flash — 830 ulaznih, 71,500 keširanih, 295 izlaznih tokena po zahtjevu
- MiMo-V2.6-Pro — 790 ulaznih, 86,000 keširanih, 305 izlaznih tokena po zahtjevu
- MiMo-V2.5 — 830 ulaznih, 71,500 keširanih, 295 izlaznih tokena po zahtjevu
- MiMo-V2.5-Pro — 790 ulaznih, 86,000 keširanih, 305 izlaznih tokena po zahtjevu
- Qwen3.8 Max — 420 ulaznih, 66,000 keširanih, 200 izlaznih tokena po zahtjevu
- Qwen3.8 Flash — 600 ulaznih, 58,000 keširanih, 200 izlaznih tokena po zahtjevu
- Qwen3.7 Plus — 500 ulaznih, 57,000 keširanih, 190 izlaznih tokena po zahtjevu
- Hy4 preview — 830 ulaznih, 71,500 keširanih, 295 izlaznih tokena po zahtjevu
- Hy3 — 830 ulaznih, 71,500 keširanih, 295 izlaznih tokena po zahtjevu
Svoju trenutnu potrošnju možete pratiti u **<a href={console}>konzoli</a>**.
@@ -289,15 +374,13 @@ Ograničenja upotrebe mogu se promijeniti kako budemo učili iz rane upotrebe i
### Upotreba preko ograničenja
Ako također imate kredite na svom Zen balansu, možete omogućiti **Use balance**
opciju u konzoli. Kada je omogućeno, Go će preći na vaš Zen balans
nakon što dostignete ograničenja upotrebe umjesto blokiranja zahtjeva.
Ako također imate kredite na svom Zen balansu, možete omogućiti opciju **Use balance** u konzoli. Kada je omogućena, Go će preći na vaš Zen balans nakon što dostignete ograničenja upotrebe umjesto blokiranja zahtjeva.
---
### Zašto neki modeli imaju manju uključenu potrošnju
Uz Go plaćate $10 mjesečno, a uključena mjesečna potrošnja razlikuje se po modelu.
Uz Go, uključena mjesečna potrošnja razlikuje se po modelu.
Za većinu modela to postižemo količinskim popustima i rezervisanim GPU kapacitetom. Tu uštedu zatim prenosimo na vas kroz veću mjesečnu potrošnju.
@@ -311,8 +394,8 @@ Za ove modele i dalje dobijate malo više nego da direktno plaćate provajderima
Također možete pristupiti Go modelima putem sljedećih API endpointa.
| Model | Model ID | Endpoint | AI SDK Paket |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Model | ID modela | Endpoint | AI SDK paket |
| ----- | --------- | -------- | ------------ |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| GPT 6 Luna | gpt-6-luna | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -320,11 +403,11 @@ Također možete pristupiti Go modelima putem sljedećih API endpointa.
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -335,22 +418,16 @@ Također možete pristupiti Go modelima putem sljedećih API endpointa.
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
[Model id](/docs/config/#models) u vašoj OpenCode konfiguraciji
koristi format `opencode-go/<model-id>`. Na primjer, za Kimi K3, koristili biste
`opencode-go/kimi-k3` u svojoj konfiguraciji.
[ID modela](/docs/config/#models) u vašoj OpenCode konfiguraciji koristi format `opencode-go/<model-id>`. Na primjer, za Kimi K3 koristili biste `opencode-go/kimi-k3` u svojoj konfiguraciji.
---
@@ -366,47 +443,44 @@ https://opencode.ai/zen/go/v1/models
## Privatnost
| Model | Treniranje modela | Zadržavanje podataka |
| ---------------------------- | ----------------- | -------------------- |
| Grok 4.7 | Ne koristi se | 30 dana |
| Grok 4.6 | Ne koristi se | 30 dana |
| GPT 6 Luna | Ne koristi se | 30 dana |
| GPT 5.6 Luna | Ne koristi se | 30 dana |
| GLM-5.3-Flash | Ne koristi se | 0 dana |
| GLM-5.3 | Ne koristi se | 0 dana |
| GLM-5.2 | Ne koristi se | 0 dana |
| GLM-5.1 | Ne koristi se | 0 dana |
| Kimi K3 | Ne koristi se | 0 dana |
| Kimi K2.7 Code | Ne koristi se | 0 dana |
| Kimi K2.6 | Ne koristi se | 0 dana |
| LongCat-2.0 | Ne koristi se | 0 dana |
| MiMo-V2.6-Pro | Ne koristi se | 0 dana |
| MiMo-V2.6-Flash | Ne koristi se | 0 dana |
| MiMo-V2.5-Pro | Ne koristi se | 0 dana |
| MiMo-V2.5 | Ne koristi se | 0 dana |
| Qwen3.8 Max | Ne koristi se | 0 dana |
| Qwen3.8 Flash | Ne koristi se | 0 dana |
| Qwen3.7 Max | Ne koristi se | 0 dana |
| Qwen3.7 Plus | Ne koristi se | 0 dana |
| Qwen3.6 Plus | Ne koristi se | 0 dana |
| MiniMax M3 | Ne koristi se | 0 dana |
| MiniMax M2.7 | Ne koristi se | 0 dana |
| Muse Spark 1.3 Contributor | Da | Nije ZDR |
| Muse Spark 1.2 Contributor | Da | Nije ZDR |
| DeepSeek V4.1 Flash | Ne koristi se | 0 dana |
| DeepSeek V4 Pro | Ne koristi se | 0 dana |
| DeepSeek V4 Flash | Ne koristi se | 0 dana |
| DeepSeek V4 Flash Vision Exp | Ne koristi se | 0 dana |
| Hy4 preview | Ne koristi se | 0 dana |
| Hy3 | Ne koristi se | 0 dana |
| Space Bunny Free | Ne koristi se | 0 dana |
| LongCat 2.5 Preview Free | Ne koristi se | 0 dana |
| Model | Treniranje modela | Zadržavanje podataka |
| ----- | ----------------- | -------------------- |
| Grok 4.7 | Ne koristi se | 30 dana |
| Grok 4.6 | Ne koristi se | 30 dana |
| GPT 6 Luna | Ne koristi se | 30 dana |
| GPT 5.6 Luna | Ne koristi se | 30 dana |
| GLM-5.3-Flash | Ne koristi se | 0 dana |
| GLM-5.3 | Ne koristi se | 0 dana |
| GLM-5.2 | Ne koristi se | 0 dana |
| Kimi K3 | Ne koristi se | 0 dana |
| Kimi K2.7 Code | Ne koristi se | 0 dana |
| Kimi K2.6 | Ne koristi se | 0 dana |
| LongCat-2.0 | Ne koristi se | 0 dana |
| MiMo-V2.6-Pro | Ne koristi se | 0 dana |
| MiMo-V2.6-Flash | Ne koristi se | 0 dana |
| MiMo-V2.5-Pro | Ne koristi se | 0 dana |
| MiMo-V2.5 | Ne koristi se | 0 dana |
| Qwen3.8 Max | Ne koristi se | 0 dana |
| Qwen3.8 Flash | Ne koristi se | 0 dana |
| Qwen3.7 Plus | Ne koristi se | 0 dana |
| MiniMax M3 | Ne koristi se | 0 dana |
| MiniMax M2.7 | Ne koristi se | 0 dana |
| Muse Spark 1.3 Contributor | Da | Nije ZDR |
| Muse Spark 1.2 Contributor | Da | Nije ZDR |
| DeepSeek V4.1 Flash | Ne koristi se | 0 dana\* |
| DeepSeek V4 Pro | Ne koristi se | 0 dana\* |
| DeepSeek V4 Flash | Ne koristi se | 0 dana\* |
| DeepSeek V4 Flash Vision Exp | Ne koristi se | 0 dana\* |
| Hy4 preview | Ne koristi se | 0 dana |
| Hy3 | Ne koristi se | 0 dana |
| Space Bunny Free | Ne koristi se | 0 dana |
| LongCat 2.5 Preview Free | Ne koristi se | 0 dana |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Znatno snižene cijene tokena u zamjenu za dopuštenje da se vaši promptovi i odgovori modela koriste za treniranje budućih Meta modela. Dostupnost je ograničena na regije dopuštene [Pravilima geografskog korištenja](https://ai.developer.meta.com/legal/geographic-use-policy) kompanije Meta. [Saznajte više](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Znatno snižene cijene tokena u zamjenu za dopuštenje da se vaši promptovi i odgovori modela koriste za treniranje budućih Meta modela. Dostupnost je ograničena na regije dopuštene [Pravilima geografskog korištenja](https://ai.developer.meta.com/legal/geographic-use-policy) kompanije Meta. [Saznajte više](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR sporazum obnavlja se mjesečno. Trenutni sporazum važi do 30. septembra 2026.
- **DeepSeek:** ZDR sporazum obnavlja se mjesečno. Trenutni sporazum važi do 31. oktobra 2026.
---
packages/web/src/content/docs/da/go.mdx
+254 -180
View File
@@ -1,19 +1,23 @@
---
title: Go
description: Lavprisabonnement til åbne kodningsmodeller.
description: Pålidelig adgang til åbne kodningsmodeller med to forbrugsniveauer.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go er et lavprisabonnement til **$10/måned**, der giver dig pålidelig adgang til populære åbne kodningsmodeller.
OpenCode Go giver dig pålidelig adgang til populære åbne kodningsmodeller med to månedlige abonnementer:
Go fungerer som enhver anden udbyder i OpenCode. Du abonnerer på OpenCode Go og
får din API-nøgle. Det er **helt valgfrit**, og du behøver ikke at bruge det for at
bruge OpenCode.
| Abonnement | Pris | Inkluderet forbrug |
| ---------- | ---- | ------------------ |
| **Go** | **$10/måned** | Billigere adgang til modellerne nedenfor |
| **Go Plus** | **$40/måned** | Højere forbrugsgrænser på tværs af modellerne nedenfor |
Det er primært udviklet til internationale brugere og giver stabil global adgang.
Go fungerer som enhver anden udbyder i OpenCode. Du abonnerer på OpenCode Go og får din API-nøgle. Det er **helt valgfrit**, og du behøver ikke at bruge det for at bruge OpenCode.
Tjenesten er primært udviklet til internationale brugere og giver stabil global adgang.
---
@@ -39,7 +43,7 @@ For at løse dette, gjorde vi et par ting:
3. Til sidst benchmarkede vi kombinationen af model og udbyder, og kom frem til
en liste, som vi trygt kan anbefale.
OpenCode Go giver dig adgang til disse modeller for **$10/måned**.
Både Go og Go Plus giver adgang til disse modeller. Vælg det abonnement, der passer til, hvor meget du bruger dem.
---
@@ -47,14 +51,12 @@ OpenCode Go giver dig adgang til disse modeller for **$10/måned**.
OpenCode Go fungerer som enhver anden udbyder i OpenCode.
1. Du logger ind på **<a href={console}>OpenCode Zen</a>**, abonnerer på Go, og
kopierer din API-nøgle.
2. Du kører kommandoen `/connect` i TUI'en, vælger `OpenCode Go`, og indsætter
din API-nøgle.
1. Du logger ind på **<a href={console}>OpenCode Console</a>**, abonnerer på Go eller Go Plus og kopierer din API-nøgle.
2. Du kører kommandoen `/connect` i TUI'en, vælger `OpenCode Go` og indsætter din API-nøgle.
3. Kør `/models` i TUI'en for at se listen over tilgængelige modeller gennem Go.
:::note
Kun ét medlem per arbejdsområde kan abonnere på OpenCode Go.
Kun ét medlem per arbejdsområde kan abonnere på OpenCode Go eller Go Plus.
:::
Den nuværende liste over modeller inkluderer:
@@ -64,13 +66,13 @@ Den nuværende liste over modeller inkluderer:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (i en begrænset periode)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -81,9 +83,7 @@ Den nuværende liste over modeller inkluderer:
- **Muse Spark 1.2 Contributor** ([begrænsede regioner](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -91,7 +91,7 @@ Den nuværende liste over modeller inkluderer:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (i en begrænset periode)
- **LongCat 2.5 Preview Free** (i en begrænset periode)
Listen over modeller kan ændre sig, efterhånden som vi tester og tilføjer nye.
@@ -140,64 +140,112 @@ undersøgte. De linkede rapporter følger rettelser og løsninger.
## Forbrugsgrænser
Forbrugsgrænser defineres som månedlige beløb i dollars. Tabellen nedenfor viser den månedlige grænse og tokenpriserne for hver model.
Forbrugsgrænser defineres som månedlige beløb i dollars. Tabellen nedenfor viser den månedlige grænse for hvert abonnement og tokenpriserne for hver model. Tokenpriserne er de samme for Go og Go Plus.
Hver model har følgende forbrugsgrænser: 5 timer — 20 % af den månedlige grænse; ugentligt — 50 %; og månedligt — 100 %.
Hvis en model for eksempel har en månedlig grænse på $60, kan du bruge op til:
Hvis en model for eksempel har en månedlig grænse på $60 med Go og $120 med Go Plus, kan du bruge op til:
- **5-timers grænse** — $12 i forbrug
- **Ugentlig grænse** — $30 i forbrug
- **Månedlig grænse** — $60 i forbrug
- **5-timers grænse** — $12 med Go eller $24 med Go Plus
- **Ugentlig grænse** — $30 med Go eller $60 med Go Plus
- **Månedlig grænse** — $60 med Go eller $120 med Go Plus
På tværs af modeller har Go grænser på $12 pr. fem timer, $30 om ugen og $60 om måneden. Go Plus har grænser på $48 pr. fem timer, $120 om ugen og $240 om måneden. Den månedlige grænse for hver model nedenfor bestemmer, hvordan dens forbrug tæller med i disse grænser.
Tokenpriser er angivet pr. 1M tokens.
| Model | Input | Output | Cached Read | Cached Write | Månedlig grænse |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | --------------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Ubegrænset**<br /><small>i en begrænset periode</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Ubegrænset**<br /><small>i en begrænset periode</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Input | Output | Cachelagret læsning | Cachelagret skrivning | Månedlig grænse |
| ----- | ----- | ------ | ------------------- | --------------------- | --------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Ubegrænset**<br /><small>i en begrænset periode</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Ubegrænset**<br /><small>i en begrænset periode</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Model | Input | Output | Cachelagret læsning | Cachelagret skrivning | Månedlig grænse |
| ----- | ----- | ------ | ------------------- | --------------------- | --------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Ubegrænset**<br /><small>i en begrænset periode</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Ubegrænset**<br /><small>i en begrænset periode</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Gratis i en begrænset periode.
@@ -209,73 +257,110 @@ Tokenpriser er angivet pr. 1M tokens.
### Estimerede anmodninger
Tabellen nedenfor viser et estimeret antal anmodninger baseret på typiske Go-forbrugsmønstre:
Tabellerne nedenfor estimerer antallet af anmodninger ud fra typiske Go-forbrugsmønstre. Estimaterne for Go Plus skalerer med hver models højere forbrugsgrænse.
| Model | anmodninger pr. 5 timer | anmodninger pr. uge | anmodninger pr. måned |
| ---------------------------- | ----------------------- | ------------------- | --------------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ubegrænset | Ubegrænset | Ubegrænset |
| LongCat 2.5 Preview Free | Ubegrænset | Ubegrænset | Ubegrænset |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Anmodninger pr. 5 timer | Anmodninger pr. uge | Anmodninger pr. måned |
| ----- | ----------------------- | ------------------- | --------------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Ubegrænset | Ubegrænset | Ubegrænset |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ubegrænset | Ubegrænset | Ubegrænset |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Model | Anmodninger pr. 5 timer | Anmodninger pr. uge | Anmodninger pr. måned |
| ----- | ----------------------- | ------------------- | --------------------- |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Ubegrænset | Ubegrænset | Ubegrænset |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Ubegrænset | Ubegrænset | Ubegrænset |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Estimaterne bruger følgende antal tokens pr. anmodning; det faktiske forbrug varierer.
- Grok 4.7/4.6 — 390 input, 32.500 cachelagrede, 120 output-tokens pr. anmodning
- GLM-5.3-Flash — 1.000 input, 55.000 cachelagrede, 200 output-tokens pr. anmodning
- GLM-5.3/5.2/5.1 — 700 input, 52.000 cachelagrede, 150 output-tokens pr. anmodning
- GPT 6 Luna — 1.000 input, 50.000 cachelagrede, 220 output-tokens pr. anmodning
- GPT 5.6 Luna — 1.000 input, 50.000 cachelagrede, 220 output-tokens pr. anmodning
- Kimi K3 — 1.050 input, 76.500 cachelagrede, 300 output-tokens pr. anmodning
- Kimi K2.7/K2.6 — 870 input, 55.000 cachelagrede, 200 output-tokens pr. anmodning
- LongCat-2.0 — 920 input, 88.900 cachelagrede, 200 output-tokens pr. anmodning
- DeepSeek V4.1 Flash — 410 input, 71.300 cachelagrede, 310 output-tokens pr. anmodning
- DeepSeek V4 Pro — 750 input, 82.000 cachelagrede, 290 output-tokens pr. anmodning
- DeepSeek V4 Flash — 410 input, 71.300 cachelagrede, 310 output-tokens pr. anmodning
- DeepSeek V4 Flash Vision Exp — 410 input, 71.300 cachelagrede, 310 output-tokens pr. anmodning
- MiniMax M3 — 510 input, 56.000 cachelagrede, 190 output-tokens pr. anmodning
- MiniMax M2.7 — 300 input, 55.000 cachelagrede, 125 output-tokens pr. anmodning
- Muse Spark 1.3 Contributor — 620 input, 71.400 cachelagrede, 300 output-tokens pr. anmodning
- Muse Spark 1.2 Contributor — 620 input, 71.400 cachelagrede, 300 output-tokens pr. anmodning
- Qwen3.8 Max — 420 input, 66.000 cachelagrede, 200 output-tokens pr. anmodning
- Qwen3.8 Flash — 600 input, 58.000 cachelagrede, 200 output-tokens pr. anmodning
- Qwen3.7 Max — 420 input, 66.000 cachelagrede, 200 output-tokens pr. anmodning
- Qwen3.7 Plus — 500 input, 57.000 cachelagrede, 190 output-tokens pr. anmodning
- Qwen3.6 Plus — 500 input, 57.000 cachelagrede, 190 output-tokens pr. anmodning
- Hy4 preview — 830 input, 71.500 cachelagrede, 295 output-tokens pr. anmodning
- Hy3 — 830 input, 71.500 cachelagrede, 295 output-tokens pr. anmodning
- MiMo-V2.6-Flash — 830 input, 71.500 cachelagrede, 295 output-tokens pr. anmodning
- MiMo-V2.6-Pro — 790 input, 86.000 cachelagrede, 305 output-tokens pr. anmodning
- MiMo-V2.5 — 830 input, 71.500 cachelagrede, 295 output-tokens pr. anmodning
- MiMo-V2.5-Pro — 790 input, 86.000 cachelagrede, 305 output-tokens pr. anmodning
- Grok 4.7/4.6 — 390 input, 32,500 cachelagrede, 120 output-tokens pr. anmodning
- GLM-5.3-Flash — 1,000 input, 55,000 cachelagrede, 200 output-tokens pr. anmodning
- GLM-5.3/5.2 — 700 input, 52,000 cachelagrede, 150 output-tokens pr. anmodning
- GPT 6 Luna — 1,000 input, 50,000 cachelagrede, 220 output-tokens pr. anmodning
- GPT 5.6 Luna — 1,000 input, 50,000 cachelagrede, 220 output-tokens pr. anmodning
- Kimi K3 — 1,050 input, 76,500 cachelagrede, 300 output-tokens pr. anmodning
- Kimi K2.7/K2.6 — 870 input, 55,000 cachelagrede, 200 output-tokens pr. anmodning
- LongCat-2.0 — 920 input, 88,900 cachelagrede, 200 output-tokens pr. anmodning
- DeepSeek V4.1 Flash — 410 input, 71,300 cachelagrede, 310 output-tokens pr. anmodning
- DeepSeek V4 Pro — 750 input, 82,000 cachelagrede, 290 output-tokens pr. anmodning
- DeepSeek V4 Flash — 410 input, 71,300 cachelagrede, 310 output-tokens pr. anmodning
- DeepSeek V4 Flash Vision Exp — 410 input, 71,300 cachelagrede, 310 output-tokens pr. anmodning
- MiniMax M3 — 510 input, 56,000 cachelagrede, 190 output-tokens pr. anmodning
- MiniMax M2.7 — 300 input, 55,000 cachelagrede, 125 output-tokens pr. anmodning
- Muse Spark 1.3 Contributor — 620 input, 71,400 cachelagrede, 300 output-tokens pr. anmodning
- Muse Spark 1.2 Contributor — 620 input, 71,400 cachelagrede, 300 output-tokens pr. anmodning
- MiMo-V2.6-Flash — 830 input, 71,500 cachelagrede, 295 output-tokens pr. anmodning
- MiMo-V2.6-Pro — 790 input, 86,000 cachelagrede, 305 output-tokens pr. anmodning
- MiMo-V2.5 — 830 input, 71,500 cachelagrede, 295 output-tokens pr. anmodning
- MiMo-V2.5-Pro — 790 input, 86,000 cachelagrede, 305 output-tokens pr. anmodning
- Qwen3.8 Max — 420 input, 66,000 cachelagrede, 200 output-tokens pr. anmodning
- Qwen3.8 Flash — 600 input, 58,000 cachelagrede, 200 output-tokens pr. anmodning
- Qwen3.7 Plus — 500 input, 57,000 cachelagrede, 190 output-tokens pr. anmodning
- Hy4 preview — 830 input, 71,500 cachelagrede, 295 output-tokens pr. anmodning
- Hy3 — 830 input, 71,500 cachelagrede, 295 output-tokens pr. anmodning
Du kan spore dit nuværende forbrug i **<a href={console}>konsollen</a>**.
@@ -289,15 +374,13 @@ Forbrugsgrænser kan ændre sig, efterhånden som vi lærer af tidlig brug og fe
### Forbrug ud over grænserne
Hvis du også har kredit på din Zen-saldo, kan du aktivere indstillingen **Use balance**
i konsollen. Når den er aktiveret, vil Go falde tilbage på din Zen-saldo,
når du har nået dine forbrugsgrænser, i stedet for at blokere anmodninger.
Hvis du også har kredit på din Zen-saldo, kan du aktivere indstillingen **Use balance** i konsollen. Når den er aktiveret, vil Go falde tilbage på din Zen-saldo, når du har nået dine forbrugsgrænser, i stedet for at blokere anmodninger.
---
### Hvorfor nogle modeller har lavere forbrug
Med Go betaler du $10/måned, og det inkluderede månedlige forbrug varierer efter model.
Med Go varierer det inkluderede månedlige forbrug efter model.
For de fleste modeller gør vi dette muligt gennem mængderabatter og reserveret GPU-kapacitet. Vi giver dig derefter disse besparelser videre i form af mere månedligt forbrug.
@@ -311,8 +394,8 @@ Med disse modeller får du stadig lidt mere, end hvis du betalte modeludbyderne
Du kan også få adgang til Go-modeller gennem følgende API-endpoints.
| Model | Model ID | Endpoint | AI SDK Package |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Model | Model-id | Endpoint | AI SDK-pakke |
| ----- | -------- | -------- | ------------ |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| GPT 6 Luna | gpt-6-luna | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -320,11 +403,11 @@ Du kan også få adgang til Go-modeller gennem følgende API-endpoints.
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -335,22 +418,16 @@ Du kan også få adgang til Go-modeller gennem følgende API-endpoints.
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
Dit [model id](/docs/config/#models) i din OpenCode config
bruger formatet `opencode-go/<model-id>`. For eksempel for Kimi K3, vil du
bruge `opencode-go/kimi-k3` i din config.
[Model-id'et](/docs/config/#models) i din OpenCode-konfiguration bruger formatet `opencode-go/<model-id>`. For Kimi K3 skal du for eksempel bruge `opencode-go/kimi-k3` i din konfiguration.
---
@@ -366,47 +443,44 @@ https://opencode.ai/zen/go/v1/models
## Privatliv
| Model | Modeltræning | Dataopbevaring |
| ---------------------------- | ------------ | -------------- |
| Grok 4.7 | Ikke brugt | 30 dage |
| Grok 4.6 | Ikke brugt | 30 dage |
| GPT 6 Luna | Ikke brugt | 30 dage |
| GPT 5.6 Luna | Ikke brugt | 30 dage |
| GLM-5.3-Flash | Ikke brugt | 0 dage |
| GLM-5.3 | Ikke brugt | 0 dage |
| GLM-5.2 | Ikke brugt | 0 dage |
| GLM-5.1 | Ikke brugt | 0 dage |
| Kimi K3 | Ikke brugt | 0 dage |
| Kimi K2.7 Code | Ikke brugt | 0 dage |
| Kimi K2.6 | Ikke brugt | 0 dage |
| LongCat-2.0 | Ikke brugt | 0 dage |
| MiMo-V2.6-Pro | Ikke brugt | 0 dage |
| MiMo-V2.6-Flash | Ikke brugt | 0 dage |
| MiMo-V2.5-Pro | Ikke brugt | 0 dage |
| MiMo-V2.5 | Ikke brugt | 0 dage |
| Qwen3.8 Max | Ikke brugt | 0 dage |
| Qwen3.8 Flash | Ikke brugt | 0 dage |
| Qwen3.7 Max | Ikke brugt | 0 dage |
| Qwen3.7 Plus | Ikke brugt | 0 dage |
| Qwen3.6 Plus | Ikke brugt | 0 dage |
| MiniMax M3 | Ikke brugt | 0 dage |
| MiniMax M2.7 | Ikke brugt | 0 dage |
| Muse Spark 1.3 Contributor | Ja | Ikke ZDR |
| Muse Spark 1.2 Contributor | Ja | Ikke ZDR |
| DeepSeek V4.1 Flash | Ikke brugt | 0 dage |
| DeepSeek V4 Pro | Ikke brugt | 0 dage |
| DeepSeek V4 Flash | Ikke brugt | 0 dage |
| DeepSeek V4 Flash Vision Exp | Ikke brugt | 0 dage |
| Hy4 preview | Ikke brugt | 0 dage |
| Hy3 | Ikke brugt | 0 dage |
| Space Bunny Free | Ikke brugt | 0 dage |
| LongCat 2.5 Preview Free | Ikke brugt | 0 dage |
| Model | Modeltræning | Dataopbevaring |
| ----- | ------------ | -------------- |
| Grok 4.7 | Ikke brugt | 30 dage |
| Grok 4.6 | Ikke brugt | 30 dage |
| GPT 6 Luna | Ikke brugt | 30 dage |
| GPT 5.6 Luna | Ikke brugt | 30 dage |
| GLM-5.3-Flash | Ikke brugt | 0 dage |
| GLM-5.3 | Ikke brugt | 0 dage |
| GLM-5.2 | Ikke brugt | 0 dage |
| Kimi K3 | Ikke brugt | 0 dage |
| Kimi K2.7 Code | Ikke brugt | 0 dage |
| Kimi K2.6 | Ikke brugt | 0 dage |
| LongCat-2.0 | Ikke brugt | 0 dage |
| MiMo-V2.6-Pro | Ikke brugt | 0 dage |
| MiMo-V2.6-Flash | Ikke brugt | 0 dage |
| MiMo-V2.5-Pro | Ikke brugt | 0 dage |
| MiMo-V2.5 | Ikke brugt | 0 dage |
| Qwen3.8 Max | Ikke brugt | 0 dage |
| Qwen3.8 Flash | Ikke brugt | 0 dage |
| Qwen3.7 Plus | Ikke brugt | 0 dage |
| MiniMax M3 | Ikke brugt | 0 dage |
| MiniMax M2.7 | Ikke brugt | 0 dage |
| Muse Spark 1.3 Contributor | Ja | Ikke ZDR |
| Muse Spark 1.2 Contributor | Ja | Ikke ZDR |
| DeepSeek V4.1 Flash | Ikke brugt | 0 dage\* |
| DeepSeek V4 Pro | Ikke brugt | 0 dage\* |
| DeepSeek V4 Flash | Ikke brugt | 0 dage\* |
| DeepSeek V4 Flash Vision Exp | Ikke brugt | 0 dage\* |
| Hy4 preview | Ikke brugt | 0 dage |
| Hy3 | Ikke brugt | 0 dage |
| Space Bunny Free | Ikke brugt | 0 dage |
| LongCat 2.5 Preview Free | Ikke brugt | 0 dage |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Kraftigt nedsatte tokenpriser til gengæld for tilladelse til at bruge dine prompts og modelsvar til at træne fremtidige Meta-modeller. Tilgængeligheden er begrænset til regioner, der er tilladt i henhold til [politikken for geografisk brug](https://ai.developer.meta.com/legal/geographic-use-policy) fra Meta. [Læs mere](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Kraftigt nedsatte tokenpriser til gengæld for tilladelse til at bruge dine prompts og modelsvar til at træne fremtidige Meta-modeller. Tilgængeligheden er begrænset til regioner, der er tilladt i henhold til [politikken for geografisk brug](https://ai.developer.meta.com/legal/geographic-use-policy) fra Meta. [Læs mere](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR-aftalen fornyes månedligt. Den nuværende aftale er gyldig til og med 30. september 2026.
- **DeepSeek:** ZDR-aftalen fornyes månedligt. Den nuværende aftale er gyldig til og med 31. oktober 2026.
---
packages/web/src/content/docs/de/go.mdx
+261 -171
View File
@@ -1,19 +1,25 @@
---
title: Go
description: Kostengünstiges Abonnement für offene Coding-Modelle.
description: Zuverlässiger Zugriff auf offene Coding-Modelle mit zwei Nutzungsstufen.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go ist ein kostengünstiges Abonnement für **10 $/Monat**, das dir zuverlässigen Zugriff auf beliebte offene Coding-Modelle bietet.
OpenCode Go bietet dir zuverlässigen Zugriff auf beliebte offene Coding-Modelle – mit zwei monatlichen Abonnements:
| Abonnement | Preis | Enthaltene Nutzung |
| ---------- | ----- | ------------------ |
| **Go** | **$10/Monat** | Kostengünstiger Zugriff auf die unten aufgeführten Modelle |
| **Go Plus** | **$40/Monat** | Höhere Nutzungslimits für die unten aufgeführten Modelle |
Go funktioniert wie jeder andere Provider in OpenCode. Du abonnierst OpenCode Go und
erhältst deinen API-Key. Es ist **völlig optional** und du musst es nicht nutzen, um
OpenCode zu verwenden.
Es wurde in erster Linie für internationale Nutzer entwickelt und bietet einen stabilen weltweiten Zugriff.
Der Dienst wurde in erster Linie für internationale Nutzer entwickelt und bietet einen stabilen weltweiten Zugriff.
---
@@ -33,7 +39,7 @@ Um dies zu beheben, haben wir einige Dinge getan:
2. Anschließend haben wir mit einigen Providern zusammengearbeitet, um sicherzustellen, dass diese korrekt bereitgestellt werden.
3. Zuletzt haben wir die Kombination aus Modell und Provider einem Benchmark unterzogen und eine Liste erstellt, die wir mit gutem Gewissen empfehlen können.
OpenCode Go bietet dir Zugriff auf diese Modelle für **10 $/Monat**.
Sowohl Go als auch Go Plus bieten Zugriff auf diese Modelle. Wähle das Abonnement, das zu deiner Nutzung passt.
---
@@ -41,12 +47,14 @@ OpenCode Go bietet dir Zugriff auf diese Modelle für **10 $/Monat**.
OpenCode Go funktioniert wie jeder andere Provider in OpenCode.
1. Du meldest dich bei **<a href={console}>OpenCode Zen</a>** an, abonnierst Go und kopierst deinen API-Key.
2. Du führst den Befehl `/connect` in der TUI aus, wählst `OpenCode Go` und fügst deinen API-Key ein.
1. Du meldest dich bei **<a href={console}>OpenCode Console</a>** an, abonnierst Go oder Go Plus und
kopierst deinen API-Key.
2. Du führst den Befehl `/connect` in der TUI aus, wählst `OpenCode Go` und fügst
deinen API-Key ein.
3. Führe `/models` in der TUI aus, um die Liste der über Go verfügbaren Modelle zu sehen.
:::note
Nur ein Mitglied pro Workspace kann OpenCode Go abonnieren.
Nur ein Mitglied pro Workspace kann OpenCode Go oder Go Plus abonnieren.
:::
Die aktuelle Liste der Modelle umfasst:
@@ -56,13 +64,13 @@ Die aktuelle Liste der Modelle umfasst:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (für begrenzte Zeit)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -73,9 +81,7 @@ Die aktuelle Liste der Modelle umfasst:
- **Muse Spark 1.2 Contributor** ([begrenzte Regionen](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -83,7 +89,6 @@ Die aktuelle Liste der Modelle umfasst:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (für begrenzte Zeit)
- **LongCat 2.5 Preview Free** (für begrenzte Zeit)
Die Liste der Modelle kann sich ändern, während wir neue testen und hinzufügen.
@@ -132,64 +137,118 @@ oder sie ist unvollständig. Die verlinkten Berichte dokumentieren Fixes und Pro
## Nutzungslimits
Nutzungslimits werden als monatliche Dollarbeträge festgelegt. Die folgende Tabelle zeigt das monatliche Limit und die Tokenpreise für jedes Modell.
Nutzungslimits werden als monatliche Dollarbeträge festgelegt. Die folgende Tabelle zeigt
das monatliche Limit für jedes Abonnement und die Tokenpreise für jedes Modell. Die Tokenpreise
sind für Go und Go Plus identisch.
Für jedes Modell gelten folgende Nutzungslimits: 5 Stunden — 20 % des monatlichen Limits; wöchentlich — 50 %; und monatlich — 100 %.
Für jedes Modell gelten folgende Nutzungslimits: 5 Stunden — 20 % des monatlichen Limits;
wöchentlich — 50 %; und monatlich — 100 %.
Wenn ein Modell beispielsweise ein monatliches Limit von $60 hat, kannst du bis zu folgende Beträge nutzen:
Wenn ein Modell beispielsweise ein monatliches Limit von $60 bei Go und $120 bei Go Plus
hat, kannst du bis zu folgende Beträge nutzen:
- **5-Stunden-Limit** — Nutzung im Wert von $12
- **Wöchentliches Limit** — Nutzung im Wert von $30
- **Monatliches Limit** — Nutzung im Wert von $60
- **5-Stunden-Limit** — $12 bei Go oder $24 bei Go Plus
- **Wöchentliches Limit** — $30 bei Go oder $60 bei Go Plus
- **Monatliches Limit** — $60 bei Go oder $120 bei Go Plus
Über alle Modelle hinweg bietet Go Kontingente von $12 für fünf Stunden, $30 pro Woche und $60 pro Monat;
Go Plus bietet $48 für fünf Stunden, $120 pro Woche und $240 pro Monat. Das unten angegebene
monatliche Limit jedes Modells bestimmt, wie seine Nutzung auf diese Kontingente angerechnet wird.
Tokenpreise gelten pro 1M Tokens.
| Model | Input | Output | Cached Read | Cached Write | Monatliches Limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ----------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Unbegrenzt**<br /><small>für begrenzte Zeit</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Unbegrenzt**<br /><small>für begrenzte Zeit</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modell | Eingabe | Ausgabe | Cache-Lesevorgang | Cache-Schreibvorgang | Monatliches Limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Kostenlos | Kostenlos | Kostenlos | - | **Unbegrenzt**<br /><small>für begrenzte Zeit</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Kostenlos | Kostenlos | Kostenlos | - | **Unbegrenzt**<br /><small>für begrenzte Zeit</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Modell | Eingabe | Ausgabe | Cache-Lesevorgang | Cache-Schreibvorgang | Monatliches Limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Kostenlos | Kostenlos | Kostenlos | - | **Unbegrenzt**<br /><small>für begrenzte Zeit</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Kostenlos | Kostenlos | Kostenlos | - | **Unbegrenzt**<br /><small>für begrenzte Zeit</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Für begrenzte Zeit kostenlos.
@@ -197,77 +256,115 @@ Tokenpreise gelten pro 1M Tokens.
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Die Peak-Zeiten sind montags bis freitags von 01:00-04:00 und 06:00-10:00 UTC; alle anderen Zeiten, einschließlich der Wochenenden, sind Off-Peak. [Mehr erfahren](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** Bilder werden anhand ihrer Abmessungen in Tokens umgewandelt und zusammen mit Text-Tokens als Input-Tokens abgerechnet. [Mehr erfahren](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** Bilder werden anhand ihrer Abmessungen in Tokens umgewandelt und zusammen mit Text-Tokens als Eingabe-Tokens abgerechnet. [Mehr erfahren](https://api-docs.deepseek.com/quick_start/pricing/).
### Geschätzte Anfragen
Die folgende Tabelle enthält eine geschätzte Anzahl von Anfragen basierend auf typischen Go-Nutzungsmustern:
Die folgenden Tabellen enthalten geschätzte Anzahlen von Anfragen basierend auf typischen Go-Nutzungsmustern. Die Schätzungen für Go
Plus skalieren entsprechend dem höheren Nutzungslimit jedes Modells.
| Model | Anfragen pro 5 Stunden | Anfragen pro Woche | Anfragen pro Monat |
| ---------------------------- | ---------------------- | ------------------ | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Unbegrenzt | Unbegrenzt | Unbegrenzt |
| LongCat 2.5 Preview Free | Unbegrenzt | Unbegrenzt | Unbegrenzt |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modell | Anfragen pro 5 Stunden | Anfragen pro Woche | Anfragen pro Monat |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Unbegrenzt | Unbegrenzt | Unbegrenzt |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Unbegrenzt | Unbegrenzt | Unbegrenzt |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Modell | Anfragen pro 5 Stunden | Anfragen pro Woche | Anfragen pro Monat |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Unbegrenzt | Unbegrenzt | Unbegrenzt |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Unbegrenzt | Unbegrenzt | Unbegrenzt |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Die Schätzungen verwenden die folgenden Token-Anzahlen pro Anfrage; die tatsächliche Nutzung variiert.
- Grok 4.7/4.6 — 390 Input-, 32.500 Cached-, 120 Output-Tokens pro Anfrage
- GLM-5.3-Flash — 1.000 Input-, 55.000 Cached-, 200 Output-Tokens pro Anfrage
- GLM-5.3/5.2/5.1 — 700 Input-, 52.000 Cached-, 150 Output-Tokens pro Anfrage
- GPT 6 Luna — 1.000 Input-, 50.000 Cached-, 220 Output-Tokens pro Anfrage
- GPT 5.6 Luna — 1.000 Input-, 50.000 Cached-, 220 Output-Tokens pro Anfrage
- Kimi K3 — 1.050 Input-, 76.500 Cached-, 300 Output-Tokens pro Anfrage
- Kimi K2.7/K2.6 — 870 Input-, 55.000 Cached-, 200 Output-Tokens pro Anfrage
- LongCat-2.0 — 920 Input-, 88.900 Cached-, 200 Output-Tokens pro Anfrage
- DeepSeek V4.1 Flash — 410 Input-, 71.300 Cached-, 310 Output-Tokens pro Anfrage
- DeepSeek V4 Pro — 750 Input-, 82.000 Cached-, 290 Output-Tokens pro Anfrage
- DeepSeek V4 Flash — 410 Input-, 71.300 Cached-, 310 Output-Tokens pro Anfrage
- DeepSeek V4 Flash Vision Exp — 410 Input-, 71.300 Cached-, 310 Output-Tokens pro Anfrage
- MiniMax M3 — 510 Input-, 56.000 Cached-, 190 Output-Tokens pro Anfrage
- MiniMax M2.7 — 300 Input-, 55.000 Cached-, 125 Output-Tokens pro Anfrage
- Muse Spark 1.3 Contributor — 620 Input-, 71.400 Cached-, 300 Output-Tokens pro Anfrage
- Muse Spark 1.2 Contributor — 620 Input-, 71.400 Cached-, 300 Output-Tokens pro Anfrage
- Qwen3.8 Max — 420 Input-, 66.000 Cached-, 200 Output-Tokens pro Anfrage
- Qwen3.8 Flash — 600 Input-, 58.000 Cached-, 200 Output-Tokens pro Anfrage
- Qwen3.7 Max — 420 Input-, 66.000 Cached-, 200 Output-Tokens pro Anfrage
- Qwen3.7 Plus — 500 Input-, 57.000 Cached-, 190 Output-Tokens pro Anfrage
- Qwen3.6 Plus — 500 Input-, 57.000 Cached-, 190 Output-Tokens pro Anfrage
- Hy4 preview — 830 Input-, 71.500 Cached-, 295 Output-Tokens pro Anfrage
- Hy3 — 830 Input-, 71.500 Cached-, 295 Output-Tokens pro Anfrage
- MiMo-V2.6-Flash — 830 Input-, 71.500 Cached-, 295 Output-Tokens pro Anfrage
- MiMo-V2.6-Pro — 790 Input-, 86.000 Cached-, 305 Output-Tokens pro Anfrage
- MiMo-V2.5 — 830 Input-, 71.500 Cached-, 295 Output-Tokens pro Anfrage
- MiMo-V2.5-Pro — 790 Input-, 86.000 Cached-, 305 Output-Tokens pro Anfrage
- Grok 4.7/4.6 — 390 Eingabe-, 32,500 Cache-, 120 Ausgabe-Tokens pro Anfrage
- GLM-5.3-Flash — 1,000 Eingabe-, 55,000 Cache-, 200 Ausgabe-Tokens pro Anfrage
- GLM-5.3/5.2 — 700 Eingabe-, 52,000 Cache-, 150 Ausgabe-Tokens pro Anfrage
- GPT 6 Luna — 1,000 Eingabe-, 50,000 Cache-, 220 Ausgabe-Tokens pro Anfrage
- GPT 5.6 Luna — 1,000 Eingabe-, 50,000 Cache-, 220 Ausgabe-Tokens pro Anfrage
- Kimi K3 — 1,050 Eingabe-, 76,500 Cache-, 300 Ausgabe-Tokens pro Anfrage
- Kimi K2.7/K2.6 — 870 Eingabe-, 55,000 Cache-, 200 Ausgabe-Tokens pro Anfrage
- LongCat-2.0 — 920 Eingabe-, 88,900 Cache-, 200 Ausgabe-Tokens pro Anfrage
- DeepSeek V4.1 Flash — 410 Eingabe-, 71,300 Cache-, 310 Ausgabe-Tokens pro Anfrage
- DeepSeek V4 Pro — 750 Eingabe-, 82,000 Cache-, 290 Ausgabe-Tokens pro Anfrage
- DeepSeek V4 Flash — 410 Eingabe-, 71,300 Cache-, 310 Ausgabe-Tokens pro Anfrage
- DeepSeek V4 Flash Vision Exp — 410 Eingabe-, 71,300 Cache-, 310 Ausgabe-Tokens pro Anfrage
- MiniMax M3 — 510 Eingabe-, 56,000 Cache-, 190 Ausgabe-Tokens pro Anfrage
- MiniMax M2.7 — 300 Eingabe-, 55,000 Cache-, 125 Ausgabe-Tokens pro Anfrage
- Muse Spark 1.3 Contributor — 620 Eingabe-, 71,400 Cache-, 300 Ausgabe-Tokens pro Anfrage
- Muse Spark 1.2 Contributor — 620 Eingabe-, 71,400 Cache-, 300 Ausgabe-Tokens pro Anfrage
- MiMo-V2.6-Flash — 830 Eingabe-, 71,500 Cache-, 295 Ausgabe-Tokens pro Anfrage
- MiMo-V2.6-Pro — 790 Eingabe-, 86,000 Cache-, 305 Ausgabe-Tokens pro Anfrage
- MiMo-V2.5 — 830 Eingabe-, 71,500 Cache-, 295 Ausgabe-Tokens pro Anfrage
- MiMo-V2.5-Pro — 790 Eingabe-, 86,000 Cache-, 305 Ausgabe-Tokens pro Anfrage
- Qwen3.8 Max — 420 Eingabe-, 66,000 Cache-, 200 Ausgabe-Tokens pro Anfrage
- Qwen3.8 Flash — 600 Eingabe-, 58,000 Cache-, 200 Ausgabe-Tokens pro Anfrage
- Qwen3.7 Plus — 500 Eingabe-, 57,000 Cache-, 190 Ausgabe-Tokens pro Anfrage
- Hy4 preview — 830 Eingabe-, 71,500 Cache-, 295 Ausgabe-Tokens pro Anfrage
- Hy3 — 830 Eingabe-, 71,500 Cache-, 295 Ausgabe-Tokens pro Anfrage
Du kannst deine aktuelle Nutzung in der **<a href={console}>Console</a>** verfolgen.
@@ -287,7 +384,7 @@ Wenn du auch Guthaben auf deinem Zen-Konto hast, kannst du in der Console die Op
### Warum einige Modelle weniger Nutzung bieten
Mit Go zahlst du $10/Monat, und die enthaltene monatliche Nutzung variiert je nach Modell.
Bei Go variiert die enthaltene monatliche Nutzung je nach Modell.
Bei den meisten Modellen ermöglichen wir dies durch Mengenrabatte und reservierte GPU-Kapazität. Diese Ersparnisse geben wir dann in Form von zusätzlicher monatlicher Nutzung an dich weiter.
@@ -301,7 +398,7 @@ Bei diesen Modellen erhältst du immer noch etwas mehr, als wenn du die Modellan
Du kannst auf die Go-Modelle auch über die folgenden API-Endpunkte zugreifen.
| Modell | Modell-ID | Endpunkt | AI SDK Package |
| Modell | Modell-ID | Endpunkt | AI-SDK-Paket |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -310,11 +407,11 @@ Du kannst auf die Go-Modelle auch über die folgenden API-Endpunkte zugreifen.
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -325,24 +422,20 @@ Du kannst auf die Go-Modelle auch über die folgenden API-Endpunkte zugreifen.
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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.
---
### Models
### Modelle
Du kannst die vollständige Liste der verfügbaren Modelle und ihrer Metadaten hier abrufen:
@@ -354,47 +447,44 @@ https://opencode.ai/zen/go/v1/models
## Datenschutz
| Modell | Modelltraining | Datenaufbewahrung |
| ---------------------------- | --------------- | ----------------- |
| Grok 4.7 | Nicht verwendet | 30 Tage |
| Grok 4.6 | Nicht verwendet | 30 Tage |
| GPT 6 Luna | Nicht verwendet | 30 Tage |
| GPT 5.6 Luna | Nicht verwendet | 30 Tage |
| GLM-5.3-Flash | Nicht verwendet | 0 Tage |
| GLM-5.3 | Nicht verwendet | 0 Tage |
| GLM-5.2 | Nicht verwendet | 0 Tage |
| GLM-5.1 | Nicht verwendet | 0 Tage |
| Kimi K3 | Nicht verwendet | 0 Tage |
| Kimi K2.7 Code | Nicht verwendet | 0 Tage |
| Kimi K2.6 | Nicht verwendet | 0 Tage |
| LongCat-2.0 | Nicht verwendet | 0 Tage |
| MiMo-V2.6-Pro | Nicht verwendet | 0 Tage |
| MiMo-V2.6-Flash | Nicht verwendet | 0 Tage |
| MiMo-V2.5-Pro | Nicht verwendet | 0 Tage |
| MiMo-V2.5 | Nicht verwendet | 0 Tage |
| Qwen3.8 Max | Nicht verwendet | 0 Tage |
| Qwen3.8 Flash | Nicht verwendet | 0 Tage |
| Qwen3.7 Max | Nicht verwendet | 0 Tage |
| Qwen3.7 Plus | Nicht verwendet | 0 Tage |
| Qwen3.6 Plus | Nicht verwendet | 0 Tage |
| MiniMax M3 | Nicht verwendet | 0 Tage |
| MiniMax M2.7 | Nicht verwendet | 0 Tage |
| Muse Spark 1.3 Contributor | Ja | Kein ZDR |
| Muse Spark 1.2 Contributor | Ja | Kein ZDR |
| DeepSeek V4.1 Flash | Nicht verwendet | 0 Tage |
| DeepSeek V4 Pro | Nicht verwendet | 0 Tage |
| DeepSeek V4 Flash | Nicht verwendet | 0 Tage |
| DeepSeek V4 Flash Vision Exp | Nicht verwendet | 0 Tage |
| Hy4 preview | Nicht verwendet | 0 Tage |
| Hy3 | Nicht verwendet | 0 Tage |
| Space Bunny Free | Nicht verwendet | 0 Tage |
| LongCat 2.5 Preview Free | Nicht verwendet | 0 Tage |
| Modell | Modelltraining | Datenaufbewahrung |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Nicht verwendet | 30 Tage |
| Grok 4.6 | Nicht verwendet | 30 Tage |
| GPT 6 Luna | Nicht verwendet | 30 Tage |
| GPT 5.6 Luna | Nicht verwendet | 30 Tage |
| GLM-5.3-Flash | Nicht verwendet | 0 Tage |
| GLM-5.3 | Nicht verwendet | 0 Tage |
| GLM-5.2 | Nicht verwendet | 0 Tage |
| Kimi K3 | Nicht verwendet | 0 Tage |
| Kimi K2.7 Code | Nicht verwendet | 0 Tage |
| Kimi K2.6 | Nicht verwendet | 0 Tage |
| LongCat-2.0 | Nicht verwendet | 0 Tage |
| MiMo-V2.6-Pro | Nicht verwendet | 0 Tage |
| MiMo-V2.6-Flash | Nicht verwendet | 0 Tage |
| MiMo-V2.5-Pro | Nicht verwendet | 0 Tage |
| MiMo-V2.5 | Nicht verwendet | 0 Tage |
| Qwen3.8 Max | Nicht verwendet | 0 Tage |
| Qwen3.8 Flash | Nicht verwendet | 0 Tage |
| Qwen3.7 Plus | Nicht verwendet | 0 Tage |
| MiniMax M3 | Nicht verwendet | 0 Tage |
| MiniMax M2.7 | Nicht verwendet | 0 Tage |
| Muse Spark 1.3 Contributor | Ja | Kein ZDR |
| Muse Spark 1.2 Contributor | Ja | Kein ZDR |
| DeepSeek V4.1 Flash | Nicht verwendet | 0 Tage\* |
| DeepSeek V4 Pro | Nicht verwendet | 0 Tage\* |
| DeepSeek V4 Flash | Nicht verwendet | 0 Tage\* |
| DeepSeek V4 Flash Vision Exp | Nicht verwendet | 0 Tage\* |
| Hy4 preview | Nicht verwendet | 0 Tage |
| Hy3 | Nicht verwendet | 0 Tage |
| Space Bunny Free | Nicht verwendet | 0 Tage |
| LongCat 2.5 Preview Free | Nicht verwendet | 0 Tage |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Stark vergünstigte Tokenpreise im Gegenzug für die Erlaubnis, deine Prompts und Vervollständigungen zum Trainieren zukünftiger Meta-Modelle zu verwenden. Die Verfügbarkeit ist auf Regionen beschränkt, die gemäß der [Richtlinie zur geografischen Nutzung](https://ai.developer.meta.com/legal/geographic-use-policy) von Meta zulässig sind. [Mehr erfahren](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Stark vergünstigte Tokenpreise im Gegenzug für die Erlaubnis, deine Prompts und Vervollständigungen zum Trainieren zukünftiger Meta-Modelle zu verwenden. Die Verfügbarkeit ist auf Regionen beschränkt, die gemäß der [Richtlinie zur geografischen Nutzung](https://ai.developer.meta.com/legal/geographic-use-policy) von Meta zulässig sind. [Mehr erfahren](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** Die ZDR-Vereinbarung wird monatlich erneuert. Die aktuelle Vereinbarung gilt bis einschließlich 30. September 2026.
- **DeepSeek:** Die ZDR-Vereinbarung wird monatlich erneuert. Die aktuelle Vereinbarung gilt bis einschließlich 31. Oktober 2026.
---
packages/web/src/content/docs/es/go.mdx
+237 -149
View File
@@ -1,19 +1,25 @@
---
title: Go
description: Suscripción de bajo costo para modelos abiertos de programación.
description: Acceso confiable a modelos abiertos de programación con dos niveles de uso.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go es una suscripción de bajo costo de **$10/mes** que te brinda acceso confiable a modelos abiertos de programación populares.
OpenCode Go te brinda acceso confiable a modelos abiertos de programación populares, con dos planes mensuales:
| Plan | Precio | Uso incluido |
| ---- | ------ | ------------ |
| **Go** | **$10/mes** | Acceso de menor costo a los modelos que aparecen a continuación |
| **Go Plus** | **$40/mes** | Límites de uso más altos para los modelos que aparecen a continuación |
Go funciona como cualquier otro proveedor en OpenCode. Te suscribes a OpenCode Go y
obtienes tu API key. Es **completamente opcional** y no necesitas usarlo para
usar OpenCode.
Está diseñado principalmente para usuarios internacionales y ofrece un acceso global estable.
El servicio está diseñado principalmente para usuarios internacionales y ofrece un acceso global estable.
---
@@ -39,7 +45,7 @@ Para solucionar esto, hicimos un par de cosas:
3. Finalmente, evaluamos el rendimiento de la combinación del modelo/proveedor y elaboramos
una lista que nos sentimos seguros de recomendar.
OpenCode Go te da acceso a estos modelos por **$10/mes**.
Tanto Go como Go Plus brindan acceso a estos modelos; elige el plan que se adapte a tu nivel de uso.
---
@@ -47,14 +53,14 @@ OpenCode Go te da acceso a estos modelos por **$10/mes**.
OpenCode Go funciona como cualquier otro proveedor en OpenCode.
1. Inicias sesión en **<a href={console}>OpenCode Zen</a>**, te suscribes a Go y
1. Inicias sesión en **<a href={console}>OpenCode Console</a>**, te suscribes a Go o Go Plus y
copias tu API key.
2. Ejecutas el comando `/connect` en la TUI, seleccionas `OpenCode Go` y pegas
tu API key.
3. Ejecutas `/models` en la TUI para ver la lista de modelos disponibles a través de Go.
:::note
Solo un miembro por espacio de trabajo puede suscribirse a OpenCode Go.
Solo un miembro por espacio de trabajo puede suscribirse a OpenCode Go o Go Plus.
:::
La lista actual de modelos incluye:
@@ -64,13 +70,13 @@ La lista actual de modelos incluye:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (por tiempo limitado)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -81,9 +87,7 @@ La lista actual de modelos incluye:
- **Muse Spark 1.2 Contributor** ([regiones limitadas](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -91,7 +95,6 @@ La lista actual de modelos incluye:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (por tiempo limitado)
- **LongCat 2.5 Preview Free** (por tiempo limitado)
La lista de modelos puede cambiar a medida que probamos y agregamos otros nuevos.
@@ -140,64 +143,118 @@ investigamos. Los informes enlazados permiten seguir las correcciones y las solu
## Límites de uso
Los límites de uso se definen como importes mensuales en dólares. La siguiente tabla muestra el límite mensual y los costes de tokens de cada modelo.
Los límites de uso se definen como importes mensuales en dólares. La siguiente tabla muestra el
límite mensual de cada plan y los costes de tokens de cada modelo. El precio de los tokens
es el mismo para Go y Go Plus.
Cada modelo tiene los siguientes límites de uso: 5 horas — 20 % del límite mensual; semanal — 50 %; y mensual — 100 %.
Cada modelo tiene los siguientes límites de uso: 5 horas — 20 % del límite mensual;
semanal — 50 %; y mensual — 100 %.
Por ejemplo, si un modelo tiene un límite mensual de $60, puedes gastar hasta:
Por ejemplo, si un modelo tiene un límite mensual de $60 en Go y de $120 en Go Plus,
puedes gastar hasta:
- **Límite de 5 horas** — $12 de uso
- **Límite semanal** — $30 de uso
- **Límite mensual** — $60 de uso
- **Límite de 5 horas** — $12 en Go o $24 en Go Plus
- **Límite semanal** — $30 en Go o $60 en Go Plus
- **Límite mensual** — $60 en Go o $120 en Go Plus
En el conjunto de modelos, Go ofrece asignaciones de $12 cada cinco horas, $30 semanales y $60 mensuales;
Go Plus ofrece $48 cada cinco horas, $120 semanales y $240 mensuales. El límite mensual de cada
modelo que aparece a continuación determina cómo cuenta su uso para esas asignaciones.
Los precios de tokens se indican por 1M tokens.
| Modelo | Entrada | Salida | Lectura en caché | Escritura en caché | Límite mensual |
| --------------------------------------- | ------- | ------ | ---------------- | ------------------ | ----------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Ilimitado**<br /><small>por tiempo limitado</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Ilimitado**<br /><small>por tiempo limitado</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modelo | Entrada | Salida | Lectura en caché | Escritura en caché | Límite mensual |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Ilimitado**<br /><small>por tiempo limitado</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Ilimitado**<br /><small>por tiempo limitado</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Modelo | Entrada | Salida | Lectura en caché | Escritura en caché | Límite mensual |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Ilimitado**<br /><small>por tiempo limitado</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Ilimitado**<br /><small>por tiempo limitado</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Gratis por tiempo limitado.
@@ -209,49 +266,89 @@ Los precios de tokens se indican por 1M tokens.
### Peticiones estimadas
La siguiente tabla ofrece una cantidad estimada de peticiones basada en los patrones típicos de uso de Go:
Las siguientes tablas estiman el número de peticiones según los patrones típicos de uso de Go. Las estimaciones de Go
Plus se ajustan al límite de uso más alto de cada modelo.
| Model | peticiones por 5 horas | peticiones por semana | peticiones por mes |
| ---------------------------- | ---------------------- | --------------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ilimitado | Ilimitado | Ilimitado |
| LongCat 2.5 Preview Free | Ilimitado | Ilimitado | Ilimitado |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modelo | Peticiones por 5 horas | Peticiones por semana | Peticiones por mes |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Ilimitado | Ilimitado | Ilimitado |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ilimitado | Ilimitado | Ilimitado |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Modelo | Peticiones por 5 horas | Peticiones por semana | Peticiones por mes |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Ilimitado | Ilimitado | Ilimitado |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Ilimitado | Ilimitado | Ilimitado |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Las estimaciones usan las siguientes cantidades de tokens por petición; el uso real varía.
- Grok 4.7/4.6 — 390 tokens de entrada, 32,500 en caché, 120 tokens de salida por petición
- GLM-5.3-Flash — 1,000 tokens de entrada, 55,000 en caché, 200 tokens de salida por petición
- GLM-5.3/5.2/5.1 — 700 tokens de entrada, 52,000 en caché, 150 tokens de salida por petición
- GLM-5.3/5.2 — 700 tokens de entrada, 52,000 en caché, 150 tokens de salida por petición
- GPT 6 Luna — 1,000 tokens de entrada, 50,000 en caché, 220 tokens de salida por petición
- GPT 5.6 Luna — 1,000 tokens de entrada, 50,000 en caché, 220 tokens de salida por petición
- Kimi K3 — 1,050 tokens de entrada, 76,500 en caché, 300 tokens de salida por petición
@@ -265,17 +362,15 @@ Las estimaciones usan las siguientes cantidades de tokens por petición; el uso
- MiniMax M2.7 — 300 tokens de entrada, 55,000 en caché, 125 tokens de salida por petición
- Muse Spark 1.3 Contributor — 620 tokens de entrada, 71,400 en caché, 300 tokens de salida por petición
- Muse Spark 1.2 Contributor — 620 tokens de entrada, 71,400 en caché, 300 tokens de salida por petición
- Qwen3.8 Max — 420 tokens de entrada, 66,000 en caché, 200 tokens de salida por petición
- Qwen3.8 Flash — 600 tokens de entrada, 58,000 en caché, 200 tokens de salida por petición
- Qwen3.7 Max — 420 tokens de entrada, 66,000 en caché, 200 tokens de salida por petición
- Qwen3.7 Plus — 500 tokens de entrada, 57,000 en caché, 190 tokens de salida por petición
- Qwen3.6 Plus — 500 tokens de entrada, 57,000 en caché, 190 tokens de salida por petición
- Hy4 preview — 830 tokens de entrada, 71,500 en caché, 295 tokens de salida por petición
- Hy3 — 830 tokens de entrada, 71,500 en caché, 295 tokens de salida por petición
- MiMo-V2.6-Flash — 830 tokens de entrada, 71,500 en caché, 295 tokens de salida por petición
- MiMo-V2.6-Pro — 790 tokens de entrada, 86,000 en caché, 305 tokens de salida por petición
- MiMo-V2.5 — 830 tokens de entrada, 71,500 en caché, 295 tokens de salida por petición
- MiMo-V2.5-Pro — 790 tokens de entrada, 86,000 en caché, 305 tokens de salida por petición
- Qwen3.8 Max — 420 tokens de entrada, 66,000 en caché, 200 tokens de salida por petición
- Qwen3.8 Flash — 600 tokens de entrada, 58,000 en caché, 200 tokens de salida por petición
- Qwen3.7 Plus — 500 tokens de entrada, 57,000 en caché, 190 tokens de salida por petición
- Hy4 preview — 830 tokens de entrada, 71,500 en caché, 295 tokens de salida por petición
- Hy3 — 830 tokens de entrada, 71,500 en caché, 295 tokens de salida por petición
Puedes realizar un seguimiento de tu uso actual en la **<a href={console}>consola</a>**.
@@ -297,7 +392,7 @@ después de que hayas alcanzado tus límites de uso en lugar de bloquear las pet
### Por qué algunos modelos incluyen menos uso
Con Go, pagas $10/mes y el uso mensual incluido varía según el modelo.
Con Go, el uso mensual incluido varía según el modelo.
Para la mayoría de los modelos, lo conseguimos mediante descuentos por volumen y capacidad de GPU reservada. Te trasladamos ese ahorro en forma de un mayor uso mensual.
@@ -311,7 +406,7 @@ Con estos modelos, aun así obtienes un poco más que si pagaras directamente a
También puedes acceder a los modelos de Go a través de los siguientes endpoints de la API.
| Modelo | ID del modelo | Endpoint | Paquete de AI SDK |
| Modelo | ID del modelo | Endpoint | Paquete de AI SDK |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -320,11 +415,11 @@ También puedes acceder a los modelos de Go a través de los siguientes endpoint
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -335,18 +430,14 @@ También puedes acceder a los modelos de Go a través de los siguientes endpoint
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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
@@ -366,47 +457,44 @@ https://opencode.ai/zen/go/v1/models
## Privacidad
| Modelo | Entrenamiento del modelo | Retención de datos |
| ---------------------------- | ------------------------ | ------------------ |
| Grok 4.7 | No utilizado | 30 días |
| Grok 4.6 | No utilizado | 30 días |
| GPT 6 Luna | No utilizado | 30 días |
| GPT 5.6 Luna | No utilizado | 30 días |
| GLM-5.3-Flash | No utilizado | 0 días |
| GLM-5.3 | No utilizado | 0 días |
| GLM-5.2 | No utilizado | 0 días |
| GLM-5.1 | No utilizado | 0 días |
| Kimi K3 | No utilizado | 0 días |
| Kimi K2.7 Code | No utilizado | 0 días |
| Kimi K2.6 | No utilizado | 0 días |
| LongCat-2.0 | No utilizado | 0 días |
| MiMo-V2.6-Pro | No utilizado | 0 días |
| MiMo-V2.6-Flash | No utilizado | 0 días |
| MiMo-V2.5-Pro | No utilizado | 0 días |
| MiMo-V2.5 | No utilizado | 0 días |
| Qwen3.8 Max | No utilizado | 0 días |
| Qwen3.8 Flash | No utilizado | 0 días |
| Qwen3.7 Max | No utilizado | 0 días |
| Qwen3.7 Plus | No utilizado | 0 días |
| Qwen3.6 Plus | No utilizado | 0 días |
| MiniMax M3 | No utilizado | 0 días |
| MiniMax M2.7 | No utilizado | 0 días |
| Muse Spark 1.3 Contributor | Sí | Sin ZDR |
| Muse Spark 1.2 Contributor | Sí | Sin ZDR |
| DeepSeek V4.1 Flash | No utilizado | 0 días |
| DeepSeek V4 Pro | No utilizado | 0 días |
| DeepSeek V4 Flash | No utilizado | 0 días |
| DeepSeek V4 Flash Vision Exp | No utilizado | 0 días |
| Hy4 preview | No utilizado | 0 días |
| Hy3 | No utilizado | 0 días |
| Space Bunny Free | No utilizado | 0 días |
| LongCat 2.5 Preview Free | No utilizado | 0 días |
| Modelo | Entrenamiento del modelo | Retención de datos |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | No utilizado | 30 días |
| Grok 4.6 | No utilizado | 30 días |
| GPT 6 Luna | No utilizado | 30 días |
| GPT 5.6 Luna | No utilizado | 30 días |
| GLM-5.3-Flash | No utilizado | 0 días |
| GLM-5.3 | No utilizado | 0 días |
| GLM-5.2 | No utilizado | 0 días |
| Kimi K3 | No utilizado | 0 días |
| Kimi K2.7 Code | No utilizado | 0 días |
| Kimi K2.6 | No utilizado | 0 días |
| LongCat-2.0 | No utilizado | 0 días |
| MiMo-V2.6-Pro | No utilizado | 0 días |
| MiMo-V2.6-Flash | No utilizado | 0 días |
| MiMo-V2.5-Pro | No utilizado | 0 días |
| MiMo-V2.5 | No utilizado | 0 días |
| Qwen3.8 Max | No utilizado | 0 días |
| Qwen3.8 Flash | No utilizado | 0 días |
| Qwen3.7 Plus | No utilizado | 0 días |
| MiniMax M3 | No utilizado | 0 días |
| MiniMax M2.7 | No utilizado | 0 días |
| Muse Spark 1.3 Contributor | Sí | Sin ZDR |
| Muse Spark 1.2 Contributor | Sí | Sin ZDR |
| DeepSeek V4.1 Flash | No utilizado | 0 días\* |
| DeepSeek V4 Pro | No utilizado | 0 días\* |
| DeepSeek V4 Flash | No utilizado | 0 días\* |
| DeepSeek V4 Flash Vision Exp | No utilizado | 0 días\* |
| Hy4 preview | No utilizado | 0 días |
| Hy3 | No utilizado | 0 días |
| Space Bunny Free | No utilizado | 0 días |
| LongCat 2.5 Preview Free | No utilizado | 0 días |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Precios de tokens muy reducidos a cambio de permitir que tus prompts y las respuestas generadas se utilicen para entrenar futuros modelos de Meta. La disponibilidad está limitada a las regiones permitidas por la [Política de uso geográfico](https://ai.developer.meta.com/legal/geographic-use-policy) de Meta. [Más información](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Precios de tokens muy reducidos a cambio de permitir que tus prompts y las respuestas generadas se utilicen para entrenar futuros modelos de Meta. La disponibilidad está limitada a las regiones permitidas por la [Política de uso geográfico](https://ai.developer.meta.com/legal/geographic-use-policy) de Meta. [Más información](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** El acuerdo de ZDR se renueva mensualmente. El acuerdo actual es válido hasta el 30 de septiembre de 2026.
- **DeepSeek:** El acuerdo de ZDR se renueva mensualmente. El acuerdo actual es válido hasta el 31 de octubre de 2026.
---
packages/web/src/content/docs/fr/go.mdx
+237 -149
View File
@@ -1,17 +1,23 @@
---
title: Go
description: Abonnement à bas coût pour les modèles de codage ouverts.
description: Accès fiable aux modèles de codage ouverts avec deux niveaux d’utilisation.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go est un abonnement à bas coût à **10 $/mois** qui vous donne un accès fiable aux modèles de codage ouverts populaires.
OpenCode Go vous donne un accès fiable aux modèles de codage ouverts populaires, avec deux abonnements mensuels :
| Abonnement | Prix | Utilisation incluse |
| ---------- | ---- | ------------------- |
| **Go** | **10 $/mois** | Accès à moindre coût aux modèles ci-dessous |
| **Go Plus** | **40 $/mois** | Limites d’utilisation plus élevées pour les modèles ci-dessous |
Go fonctionne comme n'importe quel autre fournisseur dans OpenCode. Vous vous abonnez à OpenCode Go et obtenez votre clé d'API. C'est **totalement facultatif** et vous n'avez pas besoin de l'utiliser pour utiliser OpenCode.
Il est conçu principalement pour les utilisateurs internationaux et offre un accès mondial stable.
Le service est conçu principalement pour les utilisateurs internationaux et offre un accès mondial stable.
---
@@ -31,7 +37,7 @@ Pour remédier à cela, nous avons fait plusieurs choses :
2. Nous avons ensuite travaillé avec quelques fournisseurs pour nous assurer qu'ils étaient correctement servis.
3. Enfin, nous avons évalué les performances de la combinaison modèle/fournisseur et avons dressé une liste que nous nous sentons à l'aise de recommander.
OpenCode Go vous donne accès à ces modèles pour **10 $/mois**.
Go et Go Plus donnent tous deux accès à ces modèles ; choisissez l’abonnement adapté à votre utilisation.
---
@@ -39,12 +45,12 @@ OpenCode Go vous donne accès à ces modèles pour **10 $/mois**.
OpenCode Go fonctionne comme n'importe quel autre fournisseur dans OpenCode.
1. Vous vous connectez à **<a href={console}>OpenCode Zen</a>**, vous vous abonnez à Go et copiez votre clé d'API.
1. Vous vous connectez à **<a href={console}>OpenCode Console</a>**, vous vous abonnez à Go ou Go Plus et copiez votre clé d'API.
2. Vous exécutez la commande `/connect` dans la TUI, sélectionnez `OpenCode Go` et collez votre clé d'API.
3. Exécutez `/models` dans la TUI pour voir la liste des modèles disponibles via Go.
:::note
Un seul membre par espace de travail peut s'abonner à OpenCode Go.
Un seul membre par espace de travail peut s'abonner à OpenCode Go ou Go Plus.
:::
La liste actuelle des modèles comprend :
@@ -54,13 +60,13 @@ La liste actuelle des modèles comprend :
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (pour une durée limitée)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,9 +77,7 @@ La liste actuelle des modèles comprend :
- **Muse Spark 1.2 Contributor** ([régions limitées](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -81,7 +85,6 @@ La liste actuelle des modèles comprend :
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (pour une durée limitée)
- **LongCat 2.5 Preview Free** (pour une durée limitée)
La liste des modèles peut changer au fur et à mesure que nous en testons et en ajoutons de nouveaux.
@@ -130,64 +133,118 @@ ou ne les prennent en charge que partiellement. Les rapports associés permetten
## Limites d'utilisation
Les limites d’utilisation sont définies sous forme de montants mensuels en dollars. Le tableau ci-dessous indique la limite mensuelle et les prix des tokens pour chaque modèle.
Les limites d’utilisation sont définies sous forme de montants mensuels en dollars. Le tableau ci-dessous indique la
limite mensuelle de chaque abonnement et les prix des tokens pour chaque modèle. Le prix des tokens
est identique pour Go et Go Plus.
Chaque modèle est soumis aux limites d’utilisation suivantes : 5 heures — 20 % de la limite mensuelle ; hebdomadaire — 50 % ; et mensuelle — 100 %.
Chaque modèle est soumis aux limites d’utilisation suivantes : 5 heures — 20 % de la limite mensuelle ;
hebdomadaire — 50 % ; et mensuelle — 100 %.
Par exemple, si un modèle a une limite mensuelle de $60, vous pouvez utiliser jusqu’à :
Par exemple, si un modèle a une limite mensuelle de $60 avec Go et de $120 avec Go Plus,
vous pouvez dépenser jusqu’à :
- **Limite de 5 heures** — $12 d’utilisation
- **Limite hebdomadaire** — $30 d’utilisation
- **Limite mensuelle** — $60 d’utilisation
- **Limite de 5 heures** — $12 avec Go ou $24 avec Go Plus
- **Limite hebdomadaire** — $30 avec Go ou $60 avec Go Plus
- **Limite mensuelle** — $60 avec Go ou $120 avec Go Plus
Tous modèles confondus, Go offre des enveloppes de $12 sur cinq heures, $30 par semaine et $60 par mois ;
Go Plus offre $48 sur cinq heures, $120 par semaine et $240 par mois. La limite mensuelle de chaque
modèle ci-dessous détermine la part de son utilisation comptabilisée dans ces enveloppes.
Les prix des tokens sont indiqués par million de tokens.
| Modèle | Input | Output | Cached Read | Cached Write | Limite mensuelle |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ------------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Illimité**<br /><small>pour une durée limitée</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Illimité**<br /><small>pour une durée limitée</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modèle | Entrée | Sortie | Lecture en cache | Écriture en cache | Limite mensuelle |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Gratuit | Gratuit | Gratuit | - | **Illimité**<br /><small>pour une durée limitée</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Gratuit | Gratuit | Gratuit | - | **Illimité**<br /><small>pour une durée limitée</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Modèle | Entrée | Sortie | Lecture en cache | Écriture en cache | Limite mensuelle |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Gratuit | Gratuit | Gratuit | - | **Illimité**<br /><small>pour une durée limitée</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Gratuit | Gratuit | Gratuit | - | **Illimité**<br /><small>pour une durée limitée</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Gratuit pour une durée limitée.
@@ -199,49 +256,89 @@ Les prix des tokens sont indiqués par million de tokens.
### Requêtes estimées
Le tableau ci-dessous fournit une estimation du nombre de requêtes basée sur les habitudes d’utilisation typiques de Go :
Les tableaux ci-dessous estiment le nombre de requêtes selon les habitudes d’utilisation typiques de Go. Les estimations de Go
Plus sont proportionnelles à la limite d’utilisation plus élevée de chaque modèle.
| Model | requêtes par 5 heures | requêtes par semaine | requêtes par mois |
| ---------------------------- | --------------------- | -------------------- | ----------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Illimité | Illimité | Illimité |
| LongCat 2.5 Preview Free | Illimité | Illimité | Illimité |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modèle | Requêtes par 5 heures | Requêtes par semaine | Requêtes par mois |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Illimité | Illimité | Illimité |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Illimité | Illimité | Illimité |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Modèle | Requêtes par 5 heures | Requêtes par semaine | Requêtes par mois |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Illimité | Illimité | Illimité |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Illimité | Illimité | Illimité |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Les estimations utilisent les nombres de tokens suivants par requête ; l'utilisation réelle varie.
- Grok 4.7/4.6 — 390 tokens en entrée, 32,500 en cache, 120 tokens en sortie par requête
- GLM-5.3-Flash — 1,000 tokens en entrée, 55,000 en cache, 200 tokens en sortie par requête
- GLM-5.3/5.2/5.1 — 700 tokens en entrée, 52,000 en cache, 150 tokens en sortie par requête
- GLM-5.3/5.2 — 700 tokens en entrée, 52,000 en cache, 150 tokens en sortie par requête
- GPT 6 Luna — 1,000 tokens en entrée, 50,000 en cache, 220 tokens en sortie par requête
- GPT 5.6 Luna — 1,000 tokens en entrée, 50,000 en cache, 220 tokens en sortie par requête
- Kimi K3 — 1,050 tokens en entrée, 76,500 en cache, 300 tokens en sortie par requête
@@ -255,17 +352,15 @@ Les estimations utilisent les nombres de tokens suivants par requête ; l'utilis
- MiniMax M2.7 — 300 tokens en entrée, 55,000 en cache, 125 tokens en sortie par requête
- Muse Spark 1.3 Contributor — 620 tokens en entrée, 71,400 en cache, 300 tokens en sortie par requête
- Muse Spark 1.2 Contributor — 620 tokens en entrée, 71,400 en cache, 300 tokens en sortie par requête
- Qwen3.8 Max — 420 tokens en entrée, 66,000 en cache, 200 tokens en sortie par requête
- Qwen3.8 Flash — 600 tokens en entrée, 58,000 en cache, 200 tokens en sortie par requête
- Qwen3.7 Max — 420 tokens en entrée, 66,000 en cache, 200 tokens en sortie par requête
- Qwen3.7 Plus — 500 tokens en entrée, 57,000 en cache, 190 tokens en sortie par requête
- Qwen3.6 Plus — 500 tokens en entrée, 57,000 en cache, 190 tokens en sortie par requête
- Hy4 preview — 830 tokens en entrée, 71,500 en cache, 295 tokens en sortie par requête
- Hy3 — 830 tokens en entrée, 71,500 en cache, 295 tokens en sortie par requête
- MiMo-V2.6-Flash — 830 tokens en entrée, 71,500 en cache, 295 tokens en sortie par requête
- MiMo-V2.6-Pro — 790 tokens en entrée, 86,000 en cache, 305 tokens en sortie par requête
- MiMo-V2.5 — 830 tokens en entrée, 71,500 en cache, 295 tokens en sortie par requête
- MiMo-V2.5-Pro — 790 tokens en entrée, 86,000 en cache, 305 tokens en sortie par requête
- Qwen3.8 Max — 420 tokens en entrée, 66,000 en cache, 200 tokens en sortie par requête
- Qwen3.8 Flash — 600 tokens en entrée, 58,000 en cache, 200 tokens en sortie par requête
- Qwen3.7 Plus — 500 tokens en entrée, 57,000 en cache, 190 tokens en sortie par requête
- Hy4 preview — 830 tokens en entrée, 71,500 en cache, 295 tokens en sortie par requête
- Hy3 — 830 tokens en entrée, 71,500 en cache, 295 tokens en sortie par requête
Vous pouvez suivre votre utilisation actuelle dans la **<a href={console}>console</a>**.
@@ -285,7 +380,7 @@ Si vous avez également des crédits sur votre solde Zen, vous pouvez activer l'
### Pourquoi certains modèles offrent un volume d'utilisation inférieur
Avec Go, vous payez 10 $/mois, et l’utilisation mensuelle incluse varie selon le modèle.
Avec Go, l’utilisation mensuelle incluse varie selon le modèle.
Pour la plupart des modèles, nous y parvenons grâce à des remises sur volume et à une capacité GPU réservée. Nous vous faisons ensuite bénéficier de ces économies sous la forme d’une utilisation mensuelle plus élevée.
@@ -299,7 +394,7 @@ Pour ces modèles, vous obtenez tout de même un peu plus que si vous payiez dir
Vous pouvez également accéder aux modèles Go via les points de terminaison d'API suivants.
| Modèle | ID de modèle | Point de terminaison | Package AI SDK |
| Modèle | ID de modèle | Point de terminaison | Package AI SDK |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -308,11 +403,11 @@ Vous pouvez également accéder aux modèles Go via les points de terminaison d'
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -323,18 +418,14 @@ Vous pouvez également accéder aux modèles Go via les points de terminaison d'
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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.
@@ -352,47 +443,44 @@ https://opencode.ai/zen/go/v1/models
## Confidentialité
| Modèle | Entraînement des modèles | Conservation des données |
| ---------------------------- | ------------------------ | ------------------------ |
| Grok 4.7 | Non utilisé | 30 jours |
| Grok 4.6 | Non utilisé | 30 jours |
| GPT 6 Luna | Non utilisé | 30 jours |
| GPT 5.6 Luna | Non utilisé | 30 jours |
| GLM-5.3-Flash | Non utilisé | 0 jour |
| GLM-5.3 | Non utilisé | 0 jour |
| GLM-5.2 | Non utilisé | 0 jour |
| GLM-5.1 | Non utilisé | 0 jour |
| Kimi K3 | Non utilisé | 0 jour |
| Kimi K2.7 Code | Non utilisé | 0 jour |
| Kimi K2.6 | Non utilisé | 0 jour |
| LongCat-2.0 | Non utilisé | 0 jour |
| MiMo-V2.6-Pro | Non utilisé | 0 jour |
| MiMo-V2.6-Flash | Non utilisé | 0 jour |
| MiMo-V2.5-Pro | Non utilisé | 0 jour |
| MiMo-V2.5 | Non utilisé | 0 jour |
| Qwen3.8 Max | Non utilisé | 0 jour |
| Qwen3.8 Flash | Non utilisé | 0 jour |
| Qwen3.7 Max | Non utilisé | 0 jour |
| Qwen3.7 Plus | Non utilisé | 0 jour |
| Qwen3.6 Plus | Non utilisé | 0 jour |
| MiniMax M3 | Non utilisé | 0 jour |
| MiniMax M2.7 | Non utilisé | 0 jour |
| Muse Spark 1.3 Contributor | Oui | Pas de ZDR |
| Muse Spark 1.2 Contributor | Oui | Pas de ZDR |
| DeepSeek V4.1 Flash | Non utilisé | 0 jour |
| DeepSeek V4 Pro | Non utilisé | 0 jour |
| DeepSeek V4 Flash | Non utilisé | 0 jour |
| DeepSeek V4 Flash Vision Exp | Non utilisé | 0 jour |
| Hy4 preview | Non utilisé | 0 jour |
| Hy3 | Non utilisé | 0 jour |
| Space Bunny Free | Non utilisé | 0 jour |
| LongCat 2.5 Preview Free | Non utilisé | 0 jour |
| Modèle | Entraînement des modèles | Conservation des données |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Non utilisé | 30 jours |
| Grok 4.6 | Non utilisé | 30 jours |
| GPT 6 Luna | Non utilisé | 30 jours |
| GPT 5.6 Luna | Non utilisé | 30 jours |
| GLM-5.3-Flash | Non utilisé | 0 jour |
| GLM-5.3 | Non utilisé | 0 jour |
| GLM-5.2 | Non utilisé | 0 jour |
| Kimi K3 | Non utilisé | 0 jour |
| Kimi K2.7 Code | Non utilisé | 0 jour |
| Kimi K2.6 | Non utilisé | 0 jour |
| LongCat-2.0 | Non utilisé | 0 jour |
| MiMo-V2.6-Pro | Non utilisé | 0 jour |
| MiMo-V2.6-Flash | Non utilisé | 0 jour |
| MiMo-V2.5-Pro | Non utilisé | 0 jour |
| MiMo-V2.5 | Non utilisé | 0 jour |
| Qwen3.8 Max | Non utilisé | 0 jour |
| Qwen3.8 Flash | Non utilisé | 0 jour |
| Qwen3.7 Plus | Non utilisé | 0 jour |
| MiniMax M3 | Non utilisé | 0 jour |
| MiniMax M2.7 | Non utilisé | 0 jour |
| Muse Spark 1.3 Contributor | Oui | Pas de ZDR |
| Muse Spark 1.2 Contributor | Oui | Pas de ZDR |
| DeepSeek V4.1 Flash | Non utilisé | 0 jour\* |
| DeepSeek V4 Pro | Non utilisé | 0 jour\* |
| DeepSeek V4 Flash | Non utilisé | 0 jour\* |
| DeepSeek V4 Flash Vision Exp | Non utilisé | 0 jour\* |
| Hy4 preview | Non utilisé | 0 jour |
| Hy3 | Non utilisé | 0 jour |
| Space Bunny Free | Non utilisé | 0 jour |
| LongCat 2.5 Preview Free | Non utilisé | 0 jour |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Des tarifs de tokens fortement réduits en échange de l’autorisation d’utiliser vos prompts et vos complétions pour entraîner de futurs modèles Meta. La disponibilité est limitée aux régions autorisées par la [Politique d’utilisation géographique](https://ai.developer.meta.com/legal/geographic-use-policy) de Meta. [En savoir plus](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Des tarifs de tokens fortement réduits en échange de l’autorisation d’utiliser vos prompts et vos complétions pour entraîner de futurs modèles Meta. La disponibilité est limitée aux régions autorisées par la [Politique d’utilisation géographique](https://ai.developer.meta.com/legal/geographic-use-policy) de Meta. [En savoir plus](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** L’accord ZDR est renouvelé chaque mois. L’accord actuel est valable jusqu’au 30 septembre 2026.
- **DeepSeek:** L’accord ZDR est renouvelé chaque mois. L’accord actuel est valable jusqu’au 31 octobre 2026.
---
packages/web/src/content/docs/go.mdx
+169 -74
View File
@@ -4,6 +4,7 @@ description: Reliable access to open coding models with two usage tiers.
---
import config from "../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
@@ -164,47 +165,98 @@ allowances.
Token prices are per 1M tokens.
| Model | Input | Output | Cached Read | Cached Write | Go monthly limit | Go Plus monthly limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------------- | --------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** | **$240** |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Unlimited**<br /><small>limited time</small> | **Unlimited** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$15** | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$30** | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$60** | **$240** |
| Space Bunny Free | Free | Free | Free | - | **Unlimited**<br /><small>limited time</small> | **Unlimited** |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** | **$60** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Input | Output | Cached Read | Cached Write | Monthly limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Unlimited**<br /><small>limited time</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Unlimited**<br /><small>limited time</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Model | Input | Output | Cached Read | Cached Write | Monthly limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Unlimited**<br /><small>limited time</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Free | Free | Free | - | **Unlimited**<br /><small>limited time</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Free for a limited time.
@@ -216,40 +268,83 @@ Token prices are per 1M tokens.
### Estimated requests
The table below provides an estimated request count based on typical Go usage patterns:
The tables below estimate request counts based on typical Go usage patterns. Go
Plus estimates scale with each model's higher usage limit.
| Model | requests per 5 hour | requests per week | requests per month |
| -------------------------------------------------------- | ------------------------- | -------------------------- | --------------------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Unlimited | Unlimited | Unlimited |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Unlimited | Unlimited | Unlimited |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Requests per 5 hours | Requests per week | Requests per month |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Unlimited | Unlimited | Unlimited |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Unlimited | Unlimited | Unlimited |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Model | Requests per 5 hours | Requests per week | Requests per month |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Unlimited | Unlimited | Unlimited |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Unlimited | Unlimited | Unlimited |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
The estimates use the following token counts per request; actual usage varies.
packages/web/src/content/docs/it/go.mdx
+262 -172
View File
@@ -1,19 +1,25 @@
---
title: Go
description: Abbonamento a basso costo per modelli di programmazione aperti.
description: Accesso affidabile ai modelli di programmazione aperti con due livelli di utilizzo.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go è un abbonamento a basso costo da **10 $/mese** che ti offre un accesso affidabile ai popolari modelli di programmazione aperti.
OpenCode Go offre un accesso affidabile ai popolari modelli di programmazione aperti, con due piani mensili:
| Piano | Prezzo | Utilizzo incluso |
| ----- | ------ | ---------------- |
| **Go** | **$10/mese** | Accesso a costo ridotto ai modelli elencati di seguito |
| **Go Plus** | **$40/mese** | Limiti di utilizzo più elevati per i modelli elencati di seguito |
Go funziona come qualsiasi altro provider in OpenCode. Ti abboni a OpenCode Go e
ottieni la tua chiave API. È **completamente facoltativo** e non hai bisogno di usarlo per
ottieni la tua chiave API. È **completamente facoltativo** e non è necessario usarlo per
utilizzare OpenCode.
È progettato principalmente per gli utenti internazionali e garantisce un accesso globale stabile.
Il servizio è progettato principalmente per gli utenti internazionali e garantisce un accesso globale stabile.
---
@@ -37,7 +43,7 @@ Per risolvere questo problema, abbiamo fatto un paio di cose:
3. Infine, abbiamo eseguito dei benchmark sulla combinazione modello/provider e abbiamo stilato
un elenco che ci sentiamo di raccomandare.
OpenCode Go ti dà accesso a questi modelli a **10 $/mese**.
Sia Go sia Go Plus consentono di accedere a questi modelli; scegli il piano più adatto al tuo utilizzo.
---
@@ -45,14 +51,14 @@ OpenCode Go ti dà accesso a questi modelli a **10 $/mese**.
OpenCode Go funziona come qualsiasi altro provider in OpenCode.
1. Accedi a **<a href={console}>OpenCode Zen</a>**, ti abboni a Go e
1. Accedi a **<a href={console}>OpenCode Console</a>**, ti abboni a Go o Go Plus e
copi la tua chiave API.
2. Esegui il comando `/connect` nella TUI, selezioni `OpenCode Go` e incolli
la tua chiave API.
3. Esegui `/models` nella TUI per vedere l'elenco dei modelli disponibili tramite Go.
:::note
Solo un membro per workspace può abbonarsi a OpenCode Go.
Solo un membro per workspace può abbonarsi a OpenCode Go o Go Plus.
:::
L'elenco attuale dei modelli include:
@@ -62,13 +68,13 @@ L'elenco attuale dei modelli include:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (per un periodo limitato)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -79,9 +85,7 @@ L'elenco attuale dei modelli include:
- **Muse Spark 1.2 Contributor** ([regioni limitate](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -89,7 +93,6 @@ L'elenco attuale dei modelli include:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (per un periodo limitato)
- **LongCat 2.5 Preview Free** (per un periodo limitato)
L'elenco dei modelli potrebbe cambiare man mano che ne testiamo e aggiungiamo di nuovi.
@@ -138,64 +141,118 @@ o le supportano solo parzialmente. Le segnalazioni collegate consentono di segui
## Limiti di utilizzo
I limiti di utilizzo sono definiti come importi mensili in dollari. La tabella seguente mostra il limite mensile e i prezzi dei token per ciascun modello.
I limiti di utilizzo sono definiti come importi mensili in dollari. La tabella seguente mostra il
limite mensile di ciascun piano e i costi dei token per ogni modello. I prezzi dei token sono
gli stessi per Go e Go Plus.
Ogni modello ha i seguenti limiti di utilizzo: 5 ore — 20% del limite mensile; settimanale — 50%; mensile — 100%.
Ogni modello ha i seguenti limiti di utilizzo: 5 ore — 20% del limite mensile;
settimanale — 50%; mensile — 100%.
Ad esempio, se un modello ha un limite mensile di $60, puoi utilizzare fino a:
Ad esempio, se un modello ha un limite mensile di $60 con Go e di $120 con
Go Plus, puoi spendere fino a:
- **Limite di 5 ore** — $12 di utilizzo
- **Limite settimanale** — $30 di utilizzo
- **Limite mensile** — $60 di utilizzo
- **Limite di 5 ore** — $12 con Go o $24 con Go Plus
- **Limite settimanale** — $30 con Go o $60 con Go Plus
- **Limite mensile** — $60 con Go o $120 con Go Plus
Considerando tutti i modelli, Go offre $12 ogni cinque ore, $30 a settimana e $60 al mese;
Go Plus offre $48 ogni cinque ore, $120 a settimana e $240 al mese. Il limite mensile
di ciascun modello indicato di seguito determina come il suo utilizzo viene conteggiato rispetto a queste soglie.
I prezzi dei token sono indicati per 1M token.
| Modello | Input | Output | Cached Read | Cached Write | Limite mensile |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Illimitato**<br /><small>per un periodo limitato</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Illimitato**<br /><small>per un periodo limitato</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modello | Input | Output | Lettura dalla cache | Scrittura nella cache | Limite mensile |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Illimitato**<br /><small>per un periodo limitato</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Illimitato**<br /><small>per un periodo limitato</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Modello | Input | Output | Lettura dalla cache | Scrittura nella cache | Limite mensile |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Illimitato**<br /><small>per un periodo limitato</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Illimitato**<br /><small>per un periodo limitato</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Gratis per un periodo limitato.
@@ -207,73 +264,111 @@ I prezzi dei token sono indicati per 1M token.
### Richieste stimate
La tabella seguente fornisce una stima del numero di richieste basata su pattern di utilizzo tipici di Go:
Le tabelle seguenti stimano il numero di richieste in base ai pattern di utilizzo tipici di Go. Le stime di Go
Plus aumentano in proporzione al limite di utilizzo più elevato di ciascun modello.
| Model | richieste ogni 5 ore | richieste a settimana | richieste al mese |
| ---------------------------- | -------------------- | --------------------- | ----------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Illimitato | Illimitato | Illimitato |
| LongCat 2.5 Preview Free | Illimitato | Illimitato | Illimitato |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modello | Richieste ogni 5 ore | Richieste a settimana | Richieste al mese |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Illimitato | Illimitato | Illimitato |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Illimitato | Illimitato | Illimitato |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Modello | Richieste ogni 5 ore | Richieste a settimana | Richieste al mese |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Illimitato | Illimitato | Illimitato |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Illimitato | Illimitato | Illimitato |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Le stime utilizzano i seguenti conteggi di token per richiesta; l'utilizzo effettivo varia.
- Grok 4.7/4.6 — 390 di input, 32.500 in cache, 120 token di output per richiesta
- GLM-5.3-Flash — 1.000 di input, 55.000 in cache, 200 token di output per richiesta
- GLM-5.3/5.2/5.1 — 700 di input, 52.000 in cache, 150 token di output per richiesta
- GPT 6 Luna — 1.000 token di input, 50.000 in cache, 220 token di output per richiesta
- GPT 5.6 Luna — 1.000 token di input, 50.000 in cache, 220 token di output per richiesta
- Kimi K3 — 1.050 di input, 76.500 in cache, 300 token di output per richiesta
- Kimi K2.7/K2.6 — 870 di input, 55.000 in cache, 200 token di output per richiesta
- LongCat-2.0 — 920 di input, 88.900 in cache, 200 token di output per richiesta
- DeepSeek V4.1 Flash — 410 di input, 71.300 in cache, 310 token di output per richiesta
- DeepSeek V4 Pro — 750 di input, 82.000 in cache, 290 token di output per richiesta
- DeepSeek V4 Flash — 410 di input, 71.300 in cache, 310 token di output per richiesta
- DeepSeek V4 Flash Vision Exp — 410 di input, 71.300 in cache, 310 token di output per richiesta
- MiniMax M3 — 510 di input, 56.000 in cache, 190 token di output per richiesta
- MiniMax M2.7 — 300 di input, 55.000 in cache, 125 token di output per richiesta
- Muse Spark 1.3 Contributor — 620 di input, 71.400 in cache, 300 token di output per richiesta
- Muse Spark 1.2 Contributor — 620 di input, 71.400 in cache, 300 token di output per richiesta
- Qwen3.8 Max — 420 di input, 66.000 in cache, 200 token di output per richiesta
- Qwen3.8 Flash — 600 di input, 58.000 in cache, 200 token di output per richiesta
- Qwen3.7 Max — 420 di input, 66.000 in cache, 200 token di output per richiesta
- Qwen3.7 Plus — 500 di input, 57.000 in cache, 190 token di output per richiesta
- Qwen3.6 Plus — 500 di input, 57.000 in cache, 190 token di output per richiesta
- Hy4 preview — 830 di input, 71.500 in cache, 295 token di output per richiesta
- Hy3 — 830 di input, 71.500 in cache, 295 token di output per richiesta
- MiMo-V2.6-Flash — 830 di input, 71.500 in cache, 295 token di output per richiesta
- MiMo-V2.6-Pro — 790 di input, 86.000 in cache, 305 token di output per richiesta
- MiMo-V2.5 — 830 di input, 71.500 in cache, 295 token di output per richiesta
- MiMo-V2.5-Pro — 790 di input, 86.000 in cache, 305 token di output per richiesta
- Grok 4.7/4.6 — 390 di input, 32,500 in cache, 120 token di output per richiesta
- GLM-5.3-Flash — 1,000 di input, 55,000 in cache, 200 token di output per richiesta
- GLM-5.3/5.2 — 700 di input, 52,000 in cache, 150 token di output per richiesta
- GPT 6 Luna — 1,000 di input, 50,000 in cache, 220 token di output per richiesta
- GPT 5.6 Luna — 1,000 di input, 50,000 in cache, 220 token di output per richiesta
- Kimi K3 — 1,050 di input, 76,500 in cache, 300 token di output per richiesta
- Kimi K2.7/K2.6 — 870 di input, 55,000 in cache, 200 token di output per richiesta
- LongCat-2.0 — 920 di input, 88,900 in cache, 200 token di output per richiesta
- DeepSeek V4.1 Flash — 410 di input, 71,300 in cache, 310 token di output per richiesta
- DeepSeek V4 Pro — 750 di input, 82,000 in cache, 290 token di output per richiesta
- DeepSeek V4 Flash — 410 di input, 71,300 in cache, 310 token di output per richiesta
- DeepSeek V4 Flash Vision Exp — 410 di input, 71,300 in cache, 310 token di output per richiesta
- MiniMax M3 — 510 di input, 56,000 in cache, 190 token di output per richiesta
- MiniMax M2.7 — 300 di input, 55,000 in cache, 125 token di output per richiesta
- Muse Spark 1.3 Contributor — 620 di input, 71,400 in cache, 300 token di output per richiesta
- Muse Spark 1.2 Contributor — 620 di input, 71,400 in cache, 300 token di output per richiesta
- MiMo-V2.6-Flash — 830 di input, 71,500 in cache, 295 token di output per richiesta
- MiMo-V2.6-Pro — 790 di input, 86,000 in cache, 305 token di output per richiesta
- MiMo-V2.5 — 830 di input, 71,500 in cache, 295 token di output per richiesta
- MiMo-V2.5-Pro — 790 di input, 86,000 in cache, 305 token di output per richiesta
- Qwen3.8 Max — 420 di input, 66,000 in cache, 200 token di output per richiesta
- Qwen3.8 Flash — 600 di input, 58,000 in cache, 200 token di output per richiesta
- Qwen3.7 Plus — 500 di input, 57,000 in cache, 190 token di output per richiesta
- Hy4 preview — 830 di input, 71,500 in cache, 295 token di output per richiesta
- Hy3 — 830 di input, 71,500 in cache, 295 token di output per richiesta
Puoi monitorare il tuo utilizzo attuale nella **<a href={console}>console</a>**.
@@ -288,14 +383,15 @@ I limiti di utilizzo potrebbero cambiare man mano che raccogliamo dati sull'util
### Utilizzo oltre i limiti
Se hai anche dei crediti nel tuo saldo Zen, puoi abilitare l'opzione **Use balance**
nella console. Quando è abilitata, Go ripiegherà sul tuo saldo Zen
dopo che avrai raggiunto i limiti di utilizzo invece di bloccare le richieste.
nella console. Quando è abilitata, dopo che avrai raggiunto i limiti di utilizzo Go
utilizzerà il tuo saldo Zen invece di bloccare le richieste.
---
### Perché alcuni modelli hanno un utilizzo inferiore
Con Go, paghi $10/mese e l’utilizzo mensile incluso varia in base al modello.
Con Go, l'utilizzo mensile incluso varia in base al modello.
Per la maggior parte dei modelli, ci riusciamo grazie a sconti sui volumi e capacità GPU riservata. Ti facciamo quindi beneficiare di questi risparmi offrendo un utilizzo mensile maggiore.
@@ -309,7 +405,7 @@ Per questi modelli, ottieni comunque un po’ più di utilizzo rispetto a quanto
Puoi anche accedere ai modelli Go tramite i seguenti endpoint API.
| Modello | ID Modello | Endpoint | Pacchetto AI SDK |
| Modello | ID modello | Endpoint | Pacchetto AI SDK |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -318,11 +414,11 @@ Puoi anche accedere ai modelli Go tramite i seguenti endpoint API.
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -333,23 +429,20 @@ Puoi anche accedere ai modelli Go tramite i seguenti endpoint API.
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
Il [model id](/docs/config/#models) nella tua OpenCode config
Il [model id](/docs/config/#models) nella tua configurazione OpenCode
utilizza il formato `opencode-go/<model-id>`. Ad esempio, per Kimi K3, useresti
`opencode-go/kimi-k3` nella tua configurazione.
---
### Modelli
@@ -364,47 +457,44 @@ https://opencode.ai/zen/go/v1/models
## Privacy
| Modello | Addestramento del modello | Conservazione dei dati |
| ---------------------------- | ------------------------- | ---------------------- |
| Grok 4.7 | Non utilizzato | 30 giorni |
| Grok 4.6 | Non utilizzato | 30 giorni |
| GPT 6 Luna | Non utilizzato | 30 giorni |
| GPT 5.6 Luna | Non utilizzato | 30 giorni |
| GLM-5.3-Flash | Non utilizzato | 0 giorni |
| GLM-5.3 | Non utilizzato | 0 giorni |
| GLM-5.2 | Non utilizzato | 0 giorni |
| GLM-5.1 | Non utilizzato | 0 giorni |
| Kimi K3 | Non utilizzato | 0 giorni |
| Kimi K2.7 Code | Non utilizzato | 0 giorni |
| Kimi K2.6 | Non utilizzato | 0 giorni |
| LongCat-2.0 | Non utilizzato | 0 giorni |
| MiMo-V2.6-Pro | Non utilizzato | 0 giorni |
| MiMo-V2.6-Flash | Non utilizzato | 0 giorni |
| MiMo-V2.5-Pro | Non utilizzato | 0 giorni |
| MiMo-V2.5 | Non utilizzato | 0 giorni |
| Qwen3.8 Max | Non utilizzato | 0 giorni |
| Qwen3.8 Flash | Non utilizzato | 0 giorni |
| Qwen3.7 Max | Non utilizzato | 0 giorni |
| Qwen3.7 Plus | Non utilizzato | 0 giorni |
| Qwen3.6 Plus | Non utilizzato | 0 giorni |
| MiniMax M3 | Non utilizzato | 0 giorni |
| MiniMax M2.7 | Non utilizzato | 0 giorni |
| Muse Spark 1.3 Contributor | Sì | Non ZDR |
| Muse Spark 1.2 Contributor | Sì | Non ZDR |
| DeepSeek V4.1 Flash | Non utilizzato | 0 giorni |
| DeepSeek V4 Pro | Non utilizzato | 0 giorni |
| DeepSeek V4 Flash | Non utilizzato | 0 giorni |
| DeepSeek V4 Flash Vision Exp | Non utilizzato | 0 giorni |
| Hy4 preview | Non utilizzato | 0 giorni |
| Hy3 | Non utilizzato | 0 giorni |
| Space Bunny Free | Non utilizzato | 0 giorni |
| LongCat 2.5 Preview Free | Non utilizzato | 0 giorni |
| Modello | Addestramento del modello | Conservazione dei dati |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Non utilizzato | 30 giorni |
| Grok 4.6 | Non utilizzato | 30 giorni |
| GPT 6 Luna | Non utilizzato | 30 giorni |
| GPT 5.6 Luna | Non utilizzato | 30 giorni |
| GLM-5.3-Flash | Non utilizzato | 0 giorni |
| GLM-5.3 | Non utilizzato | 0 giorni |
| GLM-5.2 | Non utilizzato | 0 giorni |
| Kimi K3 | Non utilizzato | 0 giorni |
| Kimi K2.7 Code | Non utilizzato | 0 giorni |
| Kimi K2.6 | Non utilizzato | 0 giorni |
| LongCat-2.0 | Non utilizzato | 0 giorni |
| MiMo-V2.6-Pro | Non utilizzato | 0 giorni |
| MiMo-V2.6-Flash | Non utilizzato | 0 giorni |
| MiMo-V2.5-Pro | Non utilizzato | 0 giorni |
| MiMo-V2.5 | Non utilizzato | 0 giorni |
| Qwen3.8 Max | Non utilizzato | 0 giorni |
| Qwen3.8 Flash | Non utilizzato | 0 giorni |
| Qwen3.7 Plus | Non utilizzato | 0 giorni |
| MiniMax M3 | Non utilizzato | 0 giorni |
| MiniMax M2.7 | Non utilizzato | 0 giorni |
| Muse Spark 1.3 Contributor | Sì | Non ZDR |
| Muse Spark 1.2 Contributor | Sì | Non ZDR |
| DeepSeek V4.1 Flash | Non utilizzato | 0 giorni\* |
| DeepSeek V4 Pro | Non utilizzato | 0 giorni\* |
| DeepSeek V4 Flash | Non utilizzato | 0 giorni\* |
| DeepSeek V4 Flash Vision Exp | Non utilizzato | 0 giorni\* |
| Hy4 preview | Non utilizzato | 0 giorni |
| Hy3 | Non utilizzato | 0 giorni |
| Space Bunny Free | Non utilizzato | 0 giorni |
| LongCat 2.5 Preview Free | Non utilizzato | 0 giorni |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Prezzi dei token fortemente scontati in cambio dell'autorizzazione a utilizzare i tuoi prompt e completamenti per addestrare futuri modelli Meta. La disponibilità è limitata alle regioni consentite dalla [Politica sull'uso geografico](https://ai.developer.meta.com/legal/geographic-use-policy) di Meta. [Scopri di più](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Prezzi dei token fortemente scontati in cambio dell'autorizzazione a utilizzare i tuoi prompt e completamenti per addestrare futuri modelli Meta. La disponibilità è limitata alle regioni consentite dalla [Politica sull'uso geografico](https://ai.developer.meta.com/legal/geographic-use-policy) di Meta. [Scopri di più](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** L'accordo ZDR viene rinnovato mensilmente. L'accordo attuale è valido fino al 30 settembre 2026.
- **DeepSeek:** L'accordo ZDR viene rinnovato mensilmente. L'accordo attuale è valido fino al 31 ottobre 2026.
---
packages/web/src/content/docs/ja/go.mdx
+266 -176
View File
@@ -1,17 +1,25 @@
---
title: Go
description: オープンなコーディングモデルを利用するための低価格サブスクリプション。
description: 2つの利用プランでオープンなコーディングモデルに安定してアクセスできます。
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Goは、人気のオープンなコーディングモデルに安定してアクセスできる、低価格の**月額10ドルのサブスクリプション**です。
OpenCode Goでは、人気のオープンなコーディングモデルに安定してアクセスできる2つの月額プランを提供しています。
GoはOpenCodeの他のプロバイダーと同様に機能します。OpenCode GoをサブスクライブしてAPIキーを取得します。これは**完全に任意**であり、OpenCodeを使用するために必須ではありません。
| プラン | 料金 | 含まれる利用枠 |
| ------ | ---- | -------------- |
| **Go** | **月額$10** | 以下のモデルを低コストで利用可能 |
| **Go Plus** | **月額$40** | 以下のモデルをより多く利用可能 |
主に海外ユーザー向けに設計されており、世界中から安定してアクセスできます。
GoはOpenCodeの他のプロバイダーと同様に機能します。OpenCode Goをサブスクライブして
APIキーを取得します。これは**完全に任意**であり、OpenCodeを使用するために
必須ではありません。
このサービスは主に海外ユーザー向けに設計されており、世界中から安定してアクセスできます。
---
@@ -31,7 +39,7 @@ OpenCodeでうまく動作する一部のモデルとプロバイダーをテス
2. 次に、これらが正しく提供されていることを確認するために、いくつかのプロバイダーと協力しました。
3. 最後に、モデルとプロバイダーの組み合わせをベンチマークし、自信を持ってお勧めできるリストを作成しました。
OpenCode Goを使用すると、これらのモデルに**月額10ドル**でアクセスできます。
GoとGo Plusのどちらでもこれらのモデルを利用できます。利用量に合ったプランを選択してください。
---
@@ -39,12 +47,12 @@ OpenCode Goを使用すると、これらのモデルに**月額10ドル**でア
OpenCode Goは、OpenCodeの他のプロバイダーと同様に機能します。
1. **<a href={console}>OpenCode Zen</a>**にサインインし、GoをサブスクライブしてAPIキーをコピーします。
1. **<a href={console}>OpenCode Console</a>**にサインインし、GoまたはGo PlusをサブスクライブしてAPIキーをコピーします。
2. TUIで`/connect`コマンドを実行し、`OpenCode Go`を選択して、APIキーを貼り付けます。
3. TUIで`/models`を実行すると、Goを通じて利用可能なモデルのリストが表示されます。
:::note
OpenCode Goをサブスクライブできるのは、1つのワークスペースにつき1メンバーのみです。
OpenCode GoまたはGo Plusをサブスクライブできるのは、1つのワークスペースにつき1メンバーのみです。
:::
現在のモデルリストには以下が含まれます：
@@ -54,13 +62,13 @@ OpenCode Goをサブスクライブできるのは、1つのワークスペー
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (期間限定)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,9 +79,7 @@ OpenCode Goをサブスクライブできるのは、1つのワークスペー
- **Muse Spark 1.2 Contributor** ([一部の地域に限定](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -81,7 +87,6 @@ OpenCode Goをサブスクライブできるのは、1つのワークスペー
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (期間限定)
- **LongCat 2.5 Preview Free** (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。
@@ -127,142 +132,231 @@ OpenCodeに加えて、以下のクライアントがOpenCode Goで正常に動
## 利用制限
利用制限は月額（ドル）で定義されています。以下の表は、各モデルの月間上限とトークン単価を示しています。
利用制限は月額（ドル）で定義されています。以下の表は、各プランの
月間上限と各モデルのトークン単価を示しています。トークン単価はGoとGo Plusで同じです。
各モデルの利用制限は、5時間で月間上限の20%、週間で50%、月間で100%です。
たとえば、月間上限が$60のモデルでは、最大で以下の金額を利用できます。
たとえば、あるモデルの月間上限がGoでは$60、Go Plusでは$120の場合、最大で以下の金額を利用できます。
- **5時間の制限** — $12の利用
- **週間の制限** — $30の利用
- **月間の制限** — $60の利用
- **5時間の制限** — Goでは$12、Go Plusでは$24
- **週間の制限** — Goでは$30、Go Plusでは$60
- **月間の制限** — Goでは$60、Go Plusでは$120
全モデルを通じて、Goの利用枠は5時間で$12、週間で$30、月間で$60です。
Go Plusの利用枠は5時間で$48、週間で$120、月間で$240です。以下に示す各モデルの
月間上限によって、その利用量がこれらの利用枠に対してどのように計上されるかが決まります。
トークン単価は100万トークンあたりです。
| Model | Input | Output | Cached Read | Cached Write | 月間上限 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | --------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **無制限**<br /><small>期間限定</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **無制限**<br /><small>期間限定</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| モデル | 入力 | 出力 | キャッシュ読み取り | キャッシュ書き込み | 月間上限 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | 無料 | 無料 | 無料 | - | **無制限**<br /><small>期間限定</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | 無料 | 無料 | 無料 | - | **無制限**<br /><small>期間限定</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| モデル | 入力 | 出力 | キャッシュ読み取り | キャッシュ書き込み | 月間上限 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | 無料 | 無料 | 無料 | - | **無制限**<br /><small>期間限定</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | 無料 | 無料 | 無料 | - | **無制限**<br /><small>期間限定</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** 期間限定で無料です。
**LongCat 2.5 Preview Free:** 期間限定で無料です。
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak時間は月曜日から金曜日の01:00-04:00と06:00-10:00 UTCで、週末を含むそれ以外の時間はすべてOff-Peakです。[詳しく見る](https://api-docs.deepseek.com/quick_start/pricing/)。
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak時間は月曜日から金曜日の01:00-04:00と06:00-10:00 UTCで、週末を含むそれ以外の時間はすべてOff-Peakです。 [詳しく見る](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** 画像はサイズに基づいてトークンに変換され、テキストトークンと合わせて入力トークンとして課金されます。 [詳しく見る](https://api-docs.deepseek.com/quick_start/pricing/)。
**DeepSeek V4 Flash Vision Exp:** 画像はサイズに基づいてトークンに変換され、テキストトークンと合わせて入力トークンとして課金されます。 [詳しく見る](https://api-docs.deepseek.com/quick_start/pricing/).
### 推定リクエスト数
以下の表は、一般的なGoの利用パターンに基づく推定リクエスト数を示しています。
以下の表は、一般的なGoの利用パターンに基づく推定リクエスト数を示しています。Go
Plusの推定値は、各モデルのより高い利用上限に応じて増加します。
| Model | 5時間あたりのリクエスト数 | 週間リクエスト数 | 月間リクエスト数 |
| ---------------------------- | ------------------------- | ---------------- | ---------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 無制限 | 無制限 | 無制限 |
| LongCat 2.5 Preview Free | 無制限 | 無制限 | 無制限 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| モデル | 5時間あたりのリクエスト数 | 週間リクエスト数 | 月間リクエスト数 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | 無制限 | 無制限 | 無制限 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 無制限 | 無制限 | 無制限 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| モデル | 5時間あたりのリクエスト数 | 週間リクエスト数 | 月間リクエスト数 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | 無制限 | 無制限 | 無制限 |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | 無制限 | 無制限 | 無制限 |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
推定値には、リクエストあたり以下のトークン数を使用しています。実際の使用量は異なります。
- Grok 4.7/4.6 — リクエストあたり 入力 390トークン、キャッシュ 32,500トークン、出力 120トークン
- GLM-5.3-Flash — リクエストあたり 入力 1,000トークン、キャッシュ 55,000トークン、出力 200トークン
- GLM-5.3/5.2/5.1 — リクエストあたり 入力 700トークン、キャッシュ 52,000トークン、出力 150トークン
- GPT 6 Luna — リクエストあたり 入力 1,000トークン、キャッシュ 50,000トークン、出力 220トークン
- GPT 5.6 Luna — リクエストあたり 入力 1,000トークン、キャッシュ 50,000トークン、出力 220トークン
- Kimi K3 — リクエストあたり 入力 1,050トークン、キャッシュ 76,500トークン、出力 300トークン
- Kimi K2.7/K2.6 — リクエストあたり 入力 870トークン、キャッシュ 55,000トークン、出力 200トークン
- LongCat-2.0 — リクエストあたり 入力 920トークン、キャッシュ 88,900トークン、出力 200トークン
- DeepSeek V4.1 Flash — リクエストあたり 入力 410トークン、キャッシュ 71,300トークン、出力 310トークン
- DeepSeek V4 Pro — リクエストあたり 入力 750トークン、キャッシュ 82,000トークン、出力 290トークン
- DeepSeek V4 Flash — リクエストあたり 入力 410トークン、キャッシュ 71,300トークン、出力 310トークン
- DeepSeek V4 Flash Vision Exp — リクエストあたり 入力 410トークン、キャッシュ 71,300トークン、出力 310トークン
- MiniMax M3 — リクエストあたり 入力 510トークン、キャッシュ 56,000トークン、出力 190トークン
- MiniMax M2.7 — リクエストあたり 入力 300トークン、キャッシュ 55,000トークン、出力 125トークン
- Muse Spark 1.3 Contributor — リクエストあたり 入力 620トークン、キャッシュ 71,400トークン、出力 300トークン
- Muse Spark 1.2 Contributor — リクエストあたり 入力 620トークン、キャッシュ 71,400トークン、出力 300トークン
- Qwen3.8 Max — リクエストあたり 入力 420トークン、キャッシュ 66,000トークン、出力 200トークン
- Qwen3.8 Flash — リクエストあたり 入力 600トークン、キャッシュ 58,000トークン、出力 200トークン
- Qwen3.7 Max — リクエストあたり 入力 420トークン、キャッシュ 66,000トークン、出力 200トークン
- Qwen3.7 Plus — リクエストあたり 入力 500トークン、キャッシュ 57,000トークン、出力 190トークン
- Qwen3.6 Plus — リクエストあたり 入力 500トークン、キャッシュ 57,000トークン、出力 190トークン
- Hy4 preview — リクエストあたり 入力 830トークン、キャッシュ 71,500トークン、出力 295トークン
- Hy3 — リクエストあたり 入力 830トークン、キャッシュ 71,500トークン、出力 295トークン
- MiMo-V2.6-Flash — リクエストあたり 入力 830トークン、キャッシュ 71,500トークン、出力 295トークン
- MiMo-V2.6-Pro — リクエストあたり 入力 790トークン、キャッシュ 86,000トークン、出力 305トークン
- MiMo-V2.5 — リクエストあたり 入力 830トークン、キャッシュ 71,500トークン、出力 295トークン
- MiMo-V2.5-Pro — リクエストあたり 入力 790トークン、キャッシュ 86,000トークン、出力 305トークン
- Grok 4.7/4.6 — 390 入力, 32,500 キャッシュ, 120 出力トークン（リクエストあたり）
- GLM-5.3-Flash — 1,000 入力, 55,000 キャッシュ, 200 出力トークン（リクエストあたり）
- GLM-5.3/5.2 — 700 入力, 52,000 キャッシュ, 150 出力トークン（リクエストあたり）
- GPT 6 Luna — 1,000 入力, 50,000 キャッシュ, 220 出力トークン（リクエストあたり）
- GPT 5.6 Luna — 1,000 入力, 50,000 キャッシュ, 220 出力トークン（リクエストあたり）
- Kimi K3 — 1,050 入力, 76,500 キャッシュ, 300 出力トークン（リクエストあたり）
- Kimi K2.7/K2.6 — 870 入力, 55,000 キャッシュ, 200 出力トークン（リクエストあたり）
- LongCat-2.0 — 920 入力, 88,900 キャッシュ, 200 出力トークン（リクエストあたり）
- DeepSeek V4.1 Flash — 410 入力, 71,300 キャッシュ, 310 出力トークン（リクエストあたり）
- DeepSeek V4 Pro — 750 入力, 82,000 キャッシュ, 290 出力トークン（リクエストあたり）
- DeepSeek V4 Flash — 410 入力, 71,300 キャッシュ, 310 出力トークン（リクエストあたり）
- DeepSeek V4 Flash Vision Exp — 410 入力, 71,300 キャッシュ, 310 出力トークン（リクエストあたり）
- MiniMax M3 — 510 入力, 56,000 キャッシュ, 190 出力トークン（リクエストあたり）
- MiniMax M2.7 — 300 入力, 55,000 キャッシュ, 125 出力トークン（リクエストあたり）
- Muse Spark 1.3 Contributor — 620 入力, 71,400 キャッシュ, 300 出力トークン（リクエストあたり）
- Muse Spark 1.2 Contributor — 620 入力, 71,400 キャッシュ, 300 出力トークン（リクエストあたり）
- MiMo-V2.6-Flash — 830 入力, 71,500 キャッシュ, 295 出力トークン（リクエストあたり）
- MiMo-V2.6-Pro — 790 入力, 86,000 キャッシュ, 305 出力トークン（リクエストあたり）
- MiMo-V2.5 — 830 入力, 71,500 キャッシュ, 295 出力トークン（リクエストあたり）
- MiMo-V2.5-Pro — 790 入力, 86,000 キャッシュ, 305 出力トークン（リクエストあたり）
- Qwen3.8 Max — 420 入力, 66,000 キャッシュ, 200 出力トークン（リクエストあたり）
- Qwen3.8 Flash — 600 入力, 58,000 キャッシュ, 200 出力トークン（リクエストあたり）
- Qwen3.7 Plus — 500 入力, 57,000 キャッシュ, 190 出力トークン（リクエストあたり）
- Hy4 preview — 830 入力, 71,500 キャッシュ, 295 出力トークン（リクエストあたり）
- Hy3 — 830 入力, 71,500 キャッシュ, 295 出力トークン（リクエストあたり）
現在の利用状況は**<a href={console}>コンソール</a>**で追跡できます。
@@ -276,13 +370,14 @@ OpenCodeに加えて、以下のクライアントがOpenCode Goで正常に動
### 制限を超えた利用
Zen残高にクレジットがある場合は、コンソールで**Use balance**オプションを有効にすることができます。有効にすると、利用制限に達した後、リクエストをブロックする代わりに、GoはZen残高から利用するようになります。
Zen残高にクレジットがある場合は、コンソールで**Use balance**オプションを有効にできます。有効にすると、利用制限に達した後、リクエストをブロックする代わりにGoはZen残高から利用するようになります。
---
### 一部のモデルの利用枠が少ない理由
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て異なります。
Goでは、含まれる月間利用枠がモデルによって異なります。
ほとんどのモデルでは、ボリュームディスカウントと予約済みのGPUキャパシティによってこれを実現しています。そして、その節約分を月間利用枠の増加という形で還元しています。
@@ -296,7 +391,7 @@ 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
以下のAPIエンドポイントを通じて、Goモデルにアクセスすることもできます。
| Model | Model ID | Endpoint | AI SDK Package |
| モデル | モデル ID | エンドポイント | AI SDKパッケージ |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -305,11 +400,11 @@ 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
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -320,20 +415,18 @@ 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
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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。
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。Kimi K3の場合は、設定で
`opencode-go/kimi-k3`を使用します。
---
@@ -349,47 +442,44 @@ https://opencode.ai/zen/go/v1/models
## プライバシー
| モデル | モデルのトレーニング | データ保持 |
| ---------------------------- | -------------------- | ----------- |
| Grok 4.7 | 使用なし | 30日 |
| Grok 4.6 | 使用なし | 30日 |
| GPT 6 Luna | 使用なし | 30日 |
| GPT 5.6 Luna | 使用なし | 30日 |
| GLM-5.3-Flash | 使用なし | 0日 |
| GLM-5.3 | 使用なし | 0日 |
| GLM-5.2 | 使用なし | 0日 |
| GLM-5.1 | 使用なし | 0日 |
| Kimi K3 | 使用なし | 0日 |
| Kimi K2.7 Code | 使用なし | 0日 |
| Kimi K2.6 | 使用なし | 0日 |
| LongCat-2.0 | 使用なし | 0日 |
| MiMo-V2.6-Pro | 使用なし | 0日 |
| MiMo-V2.6-Flash | 使用なし | 0日 |
| MiMo-V2.5-Pro | 使用なし | 0日 |
| MiMo-V2.5 | 使用なし | 0日 |
| Qwen3.8 Max | 使用なし | 0日 |
| Qwen3.8 Flash | 使用なし | 0日 |
| Qwen3.7 Max | 使用なし | 0日 |
| Qwen3.7 Plus | 使用なし | 0日 |
| Qwen3.6 Plus | 使用なし | 0日 |
| MiniMax M3 | 使用なし | 0日 |
| MiniMax M2.7 | 使用なし | 0日 |
| Muse Spark 1.3 Contributor | はい | ZDRではない |
| Muse Spark 1.2 Contributor | はい | ZDRではない |
| DeepSeek V4.1 Flash | 使用なし | 0日 |
| DeepSeek V4 Pro | 使用なし | 0日 |
| DeepSeek V4 Flash | 使用なし | 0日 |
| 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 |
| Space Bunny Free | 使用なし | 0日 |
| LongCat 2.5 Preview Free | 使用なし | 0日 |
| モデル | モデルのトレーニング | データ保持 |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | 使用なし | 30日 |
| Grok 4.6 | 使用なし | 30日 |
| GPT 6 Luna | 使用なし | 30日 |
| GPT 5.6 Luna | 使用なし | 30日 |
| GLM-5.3-Flash | 使用なし | 0日 |
| GLM-5.3 | 使用なし | 0日 |
| GLM-5.2 | 使用なし | 0日 |
| Kimi K3 | 使用なし | 0日 |
| Kimi K2.7 Code | 使用なし | 0日 |
| Kimi K2.6 | 使用なし | 0日 |
| LongCat-2.0 | 使用なし | 0日 |
| MiMo-V2.6-Pro | 使用なし | 0日 |
| MiMo-V2.6-Flash | 使用なし | 0日 |
| MiMo-V2.5-Pro | 使用なし | 0日 |
| MiMo-V2.5 | 使用なし | 0日 |
| Qwen3.8 Max | 使用なし | 0日 |
| Qwen3.8 Flash | 使用なし | 0日 |
| Qwen3.7 Plus | 使用なし | 0日 |
| MiniMax M3 | 使用なし | 0日 |
| MiniMax M2.7 | 使用なし | 0日 |
| Muse Spark 1.3 Contributor | はい | ZDRではない |
| Muse Spark 1.2 Contributor | はい | ZDRではない |
| DeepSeek V4.1 Flash | 使用なし | 0日\* |
| DeepSeek V4 Pro | 使用なし | 0日\* |
| DeepSeek V4 Flash | 使用なし | 0日\* |
| 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 |
| Space Bunny Free | 使用なし | 0日 |
| LongCat 2.5 Preview Free | 使用なし | 0日 |
- **Grok 4.7/4.6:** 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 6 Luna / 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)。
- **Muse Spark 1.3 Contributor:** 将来のMetaモデルのトレーニングにプロンプトと生成結果を使用する許可と引き換えに、トークン料金が大幅に割引されます。利用できるのは、Metaの[地域別利用ポリシー](https://ai.developer.meta.com/legal/geographic-use-policy)で許可されている地域に限られます。[詳しく見る](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)。
- **Muse Spark 1.2 Contributor:** 将来のMetaモデルのトレーニングにプロンプトと生成結果を使用する許可と引き換えに、トークン料金が大幅に割引されます。利用できるのは、Metaの[地域別利用ポリシー](https://ai.developer.meta.com/legal/geographic-use-policy)で許可されている地域に限られます。[詳しく見る](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)。
- **DeepSeek:** ZDR契約は毎月更新されます。現在の契約は2026年9月30日まで有効です。
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** 将来のMetaモデルのトレーニングにプロンプトと生成結果を使用する許可と引き換えに、トークン料金が大幅に割引されます。利用できるのは、Metaの[地域別利用ポリシー](https://ai.developer.meta.com/legal/geographic-use-policy)で許可されている地域に限られます。 [詳しく見る](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** 将来のMetaモデルのトレーニングにプロンプトと生成結果を使用する許可と引き換えに、トークン料金が大幅に割引されます。利用できるのは、Metaの[地域別利用ポリシー](https://ai.developer.meta.com/legal/geographic-use-policy)で許可されている地域に限られます。 [詳しく見る](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR契約は毎月更新されます。現在の契約は2026年10月31日まで有効です。
---
packages/web/src/content/docs/ko/go.mdx
+263 -173
View File
@@ -1,17 +1,25 @@
---
title: Go
description: 오픈 코딩 모델을 위한 저비용 구독 서비스입니다.
description: 두 가지 사용량 요금제로 오픈 코딩 모델에 안정적으로 액세스하세요.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go는 인기 있는 오픈 코딩 모델에 안정적으로 액세스할 수 있게 해주는 **월 $10**의 저비용 구독 서비스입니다.
OpenCode Go는 인기 있는 오픈 코딩 모델에 안정적으로 액세스할 수 있는 두 가지 월간 요금제를 제공합니다.
Go는 OpenCode의 다른 제공자와 똑같이 작동합니다. OpenCode Go를 구독하고 API 키를 발급받으면 됩니다. 이는 **완전히 선택 사항**이며, OpenCode를 사용하기 위해 꼭 필요하지는 않습니다.
| 요금제 | 가격 | 포함된 사용량 |
| ------ | ---- | ------------- |
| **Go** | **월 $10** | 아래 모델을 더 저렴하게 이용 |
| **Go Plus** | **월 $40** | 아래 모델을 더 높은 한도로 이용 |
주로 해외 사용자를 위해 설계되었으며, 전 세계에서 안정적으로 이용할 수 있습니다.
Go는 OpenCode의 다른 제공자와 똑같이 작동합니다. OpenCode Go를 구독하고
API 키를 발급받으면 됩니다. 이는 **완전히 선택 사항**이며, OpenCode를 사용하기 위해
꼭 필요하지는 않습니다.
이 서비스는 주로 해외 사용자를 위해 설계되었으며 전 세계에서 안정적으로 이용할 수 있습니다.
---
@@ -31,7 +39,7 @@ OpenCode와 잘 맞는 선별된 모델과 제공자 그룹을 테스트했습
2. 그런 다음 몇몇 제공자와 협력해, 이 모델들이 올바르게 서비스되도록 했습니다.
3. 마지막으로 모델/제공자 조합을 벤치마킹해, 자신 있게 추천할 수 있는 목록을 만들었습니다.
OpenCode Go를 사용하면 **월 $10**으로 이러한 모델에 액세스할 수 있습니다.
Go와 Go Plus 모두 이러한 모델을 이용할 수 있습니다. 사용량에 맞는 요금제를 선택하세요.
---
@@ -39,12 +47,12 @@ OpenCode Go를 사용하면 **월 $10**으로 이러한 모델에 액세스할
OpenCode Go는 OpenCode의 다른 제공자와 똑같이 작동합니다.
1. **<a href={console}>OpenCode Zen</a>**에 로그인해 Go를 구독하고 API 키를 복사합니다.
1. **<a href={console}>OpenCode Console</a>**에 로그인해 Go 또는 Go Plus를 구독하고 API 키를 복사합니다.
2. TUI에서 `/connect` 명령을 실행하고 `OpenCode Go`를 선택한 다음 API 키를 붙여넣습니다.
3. TUI에서 `/models`를 실행해 Go를 통해 사용할 수 있는 모델 목록을 확인합니다.
:::note
workspace당 한 명의 멤버만 OpenCode Go를 구독할 수 있습니다.
workspace당 한 명의 멤버만 OpenCode Go 또는 Go Plus를 구독할 수 있습니다.
:::
현재 모델 목록에는 다음이 포함됩니다.
@@ -54,13 +62,13 @@ workspace당 한 명의 멤버만 OpenCode Go를 구독할 수 있습니다.
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (한정 기간)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,17 +79,14 @@ workspace당 한 명의 멤버만 OpenCode Go를 구독할 수 있습니다.
- **Muse Spark 1.2 Contributor** ([일부 지역에서만 제공](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
- **DeepSeek V4 Flash Vision Exp**
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (한정된 기간)
- **LongCat 2.5 Preview Free** (한정된 기간)
- **Space Bunny Free** (한정 기간)
새로운 모델을 테스트하고 추가함에 따라 이 목록은 변경될 수 있습니다.
@@ -127,68 +132,119 @@ OpenCode 외에도 다음 클라이언트가 OpenCode Go에서 올바르게 작
## 사용 한도
사용 한도는 월간 달러 금액으로 정의됩니다. 아래 표는 각 모델의 월간 한도와 토큰 비용을 보여줍니다.
사용 한도는 월간 달러 금액으로 정의됩니다. 아래 표는 각 요금제의
월간 한도와 각 모델의 토큰 비용을 보여줍니다. 토큰 가격은 Go와 Go Plus에서 동일합니다.
각 모델의 사용 한도는 5시간 한도는 월간 한도의 20%, 주간 한도는 50%, 월간 한도는 100%입니다.
예를 들어 월간 한도가 $60인 모델은 다음 금액까지 사용할 수 있습니다.
예를 들어 어떤 모델의 월간 한도가 Go에서 $60, Go Plus에서 $120이라면 다음 금액까지 사용할 수 있습니다.
- **5시간 한도** — $12 사용
- **주간 한도** — $30 사용
- **월간 한도** — $60 사용
- **5시간 한도** — Go에서 $12 또는 Go Plus에서 $24
- **주간 한도** — Go에서 $30 또는 Go Plus에서 $60
- **월간 한도** — Go에서 $60 또는 Go Plus에서 $120
전체 모델에 걸쳐 Go는 5시간 $12, 주간 $30, 월간 $60의 사용량을 제공합니다.
Go Plus는 5시간 $48, 주간 $120, 월간 $240의 사용량을 제공합니다. 아래의 각 모델별
월간 한도에 따라 해당 사용량이 이 한도에 어떻게 계산되는지가 결정됩니다.
토큰 가격은 1M tokens 기준입니다.
| Model | Input | Output | Cached Read | Cached Write | 월간 한도 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ------------------------------------------ |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **무제한**<br /><small>한정된 기간</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **무제한**<br /><small>한정된 기간</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
**Space Bunny Free:** 한정된 기간 동안 무료입니다.
| 모델 | 입력 | 출력 | 캐시 읽기 | 캐시 쓰기 | 월간 한도 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | 무료 | 무료 | 무료 | - | **무제한**<br /><small>한정 기간</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | 무료 | 무료 | 무료 | - | **무제한**<br /><small>한정 기간</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
**LongCat 2.5 Preview Free:** 한정된 기간 동안 무료입니다.
</TabItem>
<TabItem label="Go Plus">
| 모델 | 입력 | 출력 | 캐시 읽기 | 캐시 쓰기 | 월간 한도 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | 무료 | 무료 | 무료 | - | **무제한**<br /><small>한정 기간</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | 무료 | 무료 | 무료 | - | **무제한**<br /><small>한정 기간</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** 한정 기간 동안 무료입니다.
**LongCat 2.5 Preview Free:** 한정 기간 동안 무료입니다.
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak 시간은 월요일부터 금요일까지 01:00-04:00 및 06:00-10:00 UTC이며, 주말을 포함한 그 외 모든 시간은 Off-Peak입니다. [자세히 알아보기](https://api-docs.deepseek.com/quick_start/pricing/).
@@ -196,73 +252,111 @@ OpenCode 외에도 다음 클라이언트가 OpenCode Go에서 올바르게 작
### 예상 요청 횟수
아래 표는 일반적인 Go 사용 패턴을 기준으로 한 예상 요청 횟수를 보여줍니다.
아래 표는 일반적인 Go 사용 패턴을 기준으로 한 예상 요청 횟수를 보여줍니다. Go
Plus의 예상치는 각 모델의 더 높은 사용 한도에 맞춰 증가합니다.
| Model | 5시간당 요청 횟수 | 주간 요청 횟수 | 월간 요청 횟수 |
| ---------------------------- | ----------------- | -------------- | -------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 무제한 | 무제한 | 무제한 |
| LongCat 2.5 Preview Free | 무제한 | 무제한 | 무제한 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| 모델 | 5시간당 요청 횟수 | 주간 요청 횟수 | 월간 요청 횟수 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | 무제한 | 무제한 | 무제한 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 무제한 | 무제한 | 무제한 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| 모델 | 5시간당 요청 횟수 | 주간 요청 횟수 | 월간 요청 횟수 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | 무제한 | 무제한 | 무제한 |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | 무제한 | 무제한 | 무제한 |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
예상치에는 요청당 다음 토큰 수를 사용하며, 실제 사용량은 달라질 수 있습니다.
- Grok 4.7/4.6 — 요청당 입력 390, 캐시 32,500, 출력 토큰 120
- GLM-5.3-Flash — 요청당 입력 1,000, 캐시 55,000, 출력 토큰 200
- GLM-5.3/5.2/5.1 — 요청당 입력 700, 캐시 52,000, 출력 토큰 150
- GPT 6 Luna — 요청당 입력 토큰 1,000개, 캐시 토큰 50,000개, 출력 토큰 220개
- GPT 5.6 Luna — 요청당 입력 토큰 1,000개, 캐시 토큰 50,000개, 출력 토큰 220개
- Kimi K3 — 요청당 입력 1,050, 캐시 76,500, 출력 토큰 300
- Kimi K2.7/K2.6 — 요청당 입력 870, 캐시 55,000, 출력 토큰 200
- LongCat-2.0 — 요청당 입력 920, 캐시 88,900, 출력 토큰 200
- DeepSeek V4.1 Flash — 요청당 입력 410, 캐시 71,300, 출력 토큰 310
- DeepSeek V4 Pro — 요청당 입력 750, 캐시 82,000, 출력 토큰 290
- DeepSeek V4 Flash — 요청당 입력 410, 캐시 71,300, 출력 토큰 310
- DeepSeek V4 Flash Vision Exp — 요청당 입력 410, 캐시 71,300, 출력 토큰 310
- MiniMax M3 — 요청당 입력 510, 캐시 56,000, 출력 토큰 190
- MiniMax M2.7 — 요청당 입력 300, 캐시 55,000, 출력 토큰 125
- Muse Spark 1.3 Contributor — 요청당 입력 620, 캐시 71,400, 출력 토큰 300
- Muse Spark 1.2 Contributor — 요청당 입력 620, 캐시 71,400, 출력 토큰 300
- Qwen3.8 Max — 요청당 입력 420, 캐시 66,000, 출력 토큰 200
- Qwen3.8 Flash — 요청당 입력 600, 캐시 58,000, 출력 토큰 200
- Qwen3.7 Max — 요청당 입력 420, 캐시 66,000, 출력 토큰 200
- Qwen3.7 Plus — 요청당 입력 500, 캐시 57,000, 출력 토큰 190
- Qwen3.6 Plus — 요청당 입력 500, 캐시 57,000, 출력 토큰 190
- Hy4 preview — 요청당 입력 830, 캐시 71,500, 출력 토큰 295
- Hy3 — 요청당 입력 830, 캐시 71,500, 출력 토큰 295
- MiMo-V2.6-Flash — 요청당 입력 830, 캐시 71,500, 출력 토큰 295
- MiMo-V2.6-Pro — 요청당 입력 790, 캐시 86,000, 출력 토큰 305
- MiMo-V2.5 — 요청당 입력 830, 캐시 71,500, 출력 토큰 295
- MiMo-V2.5-Pro — 요청당 입력 790, 캐시 86,000, 출력 토큰 305
- Grok 4.7/4.6 — 390 입력, 32,500 캐시, 120 요청당 출력 토큰
- GLM-5.3-Flash — 1,000 입력, 55,000 캐시, 200 요청당 출력 토큰
- GLM-5.3/5.2 — 700 입력, 52,000 캐시, 150 요청당 출력 토큰
- GPT 6 Luna — 1,000 입력, 50,000 캐시, 220 요청당 출력 토큰
- GPT 5.6 Luna — 1,000 입력, 50,000 캐시, 220 요청당 출력 토큰
- Kimi K3 — 1,050 입력, 76,500 캐시, 300 요청당 출력 토큰
- Kimi K2.7/K2.6 — 870 입력, 55,000 캐시, 200 요청당 출력 토큰
- LongCat-2.0 — 920 입력, 88,900 캐시, 200 요청당 출력 토큰
- DeepSeek V4.1 Flash — 410 입력, 71,300 캐시, 310 요청당 출력 토큰
- DeepSeek V4 Pro — 750 입력, 82,000 캐시, 290 요청당 출력 토큰
- DeepSeek V4 Flash — 410 입력, 71,300 캐시, 310 요청당 출력 토큰
- DeepSeek V4 Flash Vision Exp — 410 입력, 71,300 캐시, 310 요청당 출력 토큰
- MiniMax M3 — 510 입력, 56,000 캐시, 190 요청당 출력 토큰
- MiniMax M2.7 — 300 입력, 55,000 캐시, 125 요청당 출력 토큰
- Muse Spark 1.3 Contributor — 620 입력, 71,400 캐시, 300 요청당 출력 토큰
- Muse Spark 1.2 Contributor — 620 입력, 71,400 캐시, 300 요청당 출력 토큰
- MiMo-V2.6-Flash — 830 입력, 71,500 캐시, 295 요청당 출력 토큰
- MiMo-V2.6-Pro — 790 입력, 86,000 캐시, 305 요청당 출력 토큰
- MiMo-V2.5 — 830 입력, 71,500 캐시, 295 요청당 출력 토큰
- MiMo-V2.5-Pro — 790 입력, 86,000 캐시, 305 요청당 출력 토큰
- Qwen3.8 Max — 420 입력, 66,000 캐시, 200 요청당 출력 토큰
- Qwen3.8 Flash — 600 입력, 58,000 캐시, 200 요청당 출력 토큰
- Qwen3.7 Plus — 500 입력, 57,000 캐시, 190 요청당 출력 토큰
- Hy4 preview — 830 입력, 71,500 캐시, 295 요청당 출력 토큰
- Hy3 — 830 입력, 71,500 캐시, 295 요청당 출력 토큰
현재 사용량은 **<a href={console}>console</a>**에서 확인할 수 있습니다.
@@ -276,13 +370,14 @@ OpenCode 외에도 다음 클라이언트가 OpenCode Go에서 올바르게 작
### 한도 초과 사용
Zen 잔액에 크레딧도 있다면, console에서 **Use balance** 옵션을 활성화할 수 있습니다. 이 옵션을 켜면, 사용 한도에 도달했을 때 요청을 차단하는 대신 Go가 Zen 잔액으로 자동 전환됩니다.
Zen 잔액에 크레딧도 있다면 console에서 **Use balance** 옵션을 활성화할 수 있습니다. 이 옵션을 켜면 사용 한도에 도달한 후 요청을 차단하는 대신 Go가 Zen 잔액으로 자동 전환됩니다.
---
### 일부 모델의 사용량이 더 적은 이유
Go에서는 월 $10를 지불하며, 포함된 월간 사용량은 모델마다 다릅니다.
Go에 포함된 월간 사용량은 모델마다 다릅니다.
대부분의 모델은 대량 할인과 예약된 GPU 용량을 통해 이를 실현합니다. 그런 다음 더 많은 월간 사용량을 제공하는 방식으로 절감 혜택을 사용자에게 돌려드립니다.
@@ -296,7 +391,7 @@ Go에서는 월 $10를 지불하며, 포함된 월간 사용량은 모델마다
다음 API 엔드포인트를 통해서도 Go 모델에 액세스할 수 있습니다.
| 모델 | 모델 ID | 엔드포인트 | AI SDK 패키지 |
| 모델 | 모델 ID | 엔드포인트 | AI SDK 패키지 |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -305,11 +400,11 @@ Go에서는 월 $10를 지불하며, 포함된 월간 사용량은 모델마다
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -320,20 +415,18 @@ Go에서는 월 $10를 지불하며, 포함된 월간 사용량은 모델마다
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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.
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.
---
@@ -349,47 +442,44 @@ https://opencode.ai/zen/go/v1/models
## 개인정보 보호
| 모델 | 모델 학습 | 데이터 보존 |
| ---------------------------- | ------------- | ----------- |
| Grok 4.7 | 사용되지 않음 | 30일 |
| Grok 4.6 | 사용되지 않음 | 30일 |
| GPT 6 Luna | 사용되지 않음 | 30일 |
| GPT 5.6 Luna | 사용되지 않음 | 30일 |
| GLM-5.3-Flash | 사용되지 않음 | 0일 |
| GLM-5.3 | 사용되지 않음 | 0일 |
| GLM-5.2 | 사용되지 않음 | 0일 |
| GLM-5.1 | 사용되지 않음 | 0일 |
| Kimi K3 | 사용되지 않음 | 0일 |
| Kimi K2.7 Code | 사용되지 않음 | 0일 |
| Kimi K2.6 | 사용되지 않음 | 0일 |
| LongCat-2.0 | 사용되지 않음 | 0일 |
| MiMo-V2.6-Pro | 사용되지 않음 | 0일 |
| MiMo-V2.6-Flash | 사용되지 않음 | 0일 |
| MiMo-V2.5-Pro | 사용되지 않음 | 0일 |
| MiMo-V2.5 | 사용되지 않음 | 0일 |
| Qwen3.8 Max | 사용되지 않음 | 0일 |
| Qwen3.8 Flash | 사용되지 않음 | 0일 |
| Qwen3.7 Max | 사용되지 않음 | 0일 |
| Qwen3.7 Plus | 사용되지 않음 | 0일 |
| Qwen3.6 Plus | 사용되지 않음 | 0일 |
| MiniMax M3 | 사용되지 않음 | 0일 |
| MiniMax M2.7 | 사용되지 않음 | 0일 |
| Muse Spark 1.3 Contributor | 예 | ZDR 아님 |
| Muse Spark 1.2 Contributor | 예 | ZDR 아님 |
| DeepSeek V4.1 Flash | 사용되지 않음 | 0일 |
| DeepSeek V4 Pro | 사용되지 않음 | 0일 |
| DeepSeek V4 Flash | 사용되지 않음 | 0일 |
| DeepSeek V4 Flash Vision Exp | 사용되지 않음 | 0일 |
| Hy4 preview | 사용되지 않음 | 0일 |
| Hy3 | 사용되지 않음 | 0일 |
| Space Bunny Free | 사용되지 않음 | 0일 |
| LongCat 2.5 Preview Free | 사용되지 않음 | 0일 |
| 모델 | 모델 학습 | 데이터 보존 |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | 사용되지 않음 | 30일 |
| Grok 4.6 | 사용되지 않음 | 30일 |
| GPT 6 Luna | 사용되지 않음 | 30일 |
| GPT 5.6 Luna | 사용되지 않음 | 30일 |
| GLM-5.3-Flash | 사용되지 않음 | 0일 |
| GLM-5.3 | 사용되지 않음 | 0일 |
| GLM-5.2 | 사용되지 않음 | 0일 |
| Kimi K3 | 사용되지 않음 | 0일 |
| Kimi K2.7 Code | 사용되지 않음 | 0일 |
| Kimi K2.6 | 사용되지 않음 | 0일 |
| LongCat-2.0 | 사용되지 않음 | 0일 |
| MiMo-V2.6-Pro | 사용되지 않음 | 0일 |
| MiMo-V2.6-Flash | 사용되지 않음 | 0일 |
| MiMo-V2.5-Pro | 사용되지 않음 | 0일 |
| MiMo-V2.5 | 사용되지 않음 | 0일 |
| Qwen3.8 Max | 사용되지 않음 | 0일 |
| Qwen3.8 Flash | 사용되지 않음 | 0일 |
| Qwen3.7 Plus | 사용되지 않음 | 0일 |
| MiniMax M3 | 사용되지 않음 | 0일 |
| MiniMax M2.7 | 사용되지 않음 | 0일 |
| Muse Spark 1.3 Contributor | 예 | ZDR 아님 |
| Muse Spark 1.2 Contributor | 예 | ZDR 아님 |
| DeepSeek V4.1 Flash | 사용되지 않음 | 0일\* |
| DeepSeek V4 Pro | 사용되지 않음 | 0일\* |
| DeepSeek V4 Flash | 사용되지 않음 | 0일\* |
| DeepSeek V4 Flash Vision Exp | 사용되지 않음 | 0일\* |
| Hy4 preview | 사용되지 않음 | 0일 |
| Hy3 | 사용되지 않음 | 0일 |
| Space Bunny Free | 사용되지 않음 | 0일 |
| LongCat 2.5 Preview Free | 사용되지 않음 | 0일 |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** 향후 Meta 모델 학습에 사용자의 프롬프트와 생성 결과를 사용할 수 있도록 허용하는 대신 토큰 가격이 대폭 할인됩니다. Meta의 [지역별 사용 정책](https://ai.developer.meta.com/legal/geographic-use-policy)에서 허용하는 지역에서만 이용할 수 있습니다. [자세히 알아보기](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** 향후 Meta 모델 학습에 사용자의 프롬프트와 생성 결과를 사용할 수 있도록 허용하는 대신 토큰 가격이 대폭 할인됩니다. Meta의 [지역별 사용 정책](https://ai.developer.meta.com/legal/geographic-use-policy)에서 허용하는 지역에서만 이용할 수 있습니다. [자세히 알아보기](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR 계약은 매월 갱신됩니다. 현재 계약은 2026년 9월 30일까지 유효합니다.
- **DeepSeek:** ZDR 계약은 매월 갱신됩니다. 현재 계약은 2026년 10월 31일까지 유효합니다.
---
packages/web/src/content/docs/nb/go.mdx
+291 -201
View File
@@ -1,19 +1,25 @@
---
title: Go
description: Lavkostnadsabonnement for åpne kodemodeller.
description: Pålitelig tilgang til åpne kodemodeller med to bruksnivåer.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go er et lavkostnadsabonnement til **$10/måned** som gir deg pålitelig tilgang til populære åpne kodemodeller.
OpenCode Go gir deg pålitelig tilgang til populære åpne kodemodeller med to månedsabonnementer:
| Abonnement | Pris | Inkludert bruk |
| ---- | ----- | -------------- |
| **Go** | **$10/måned** | Rimeligere tilgang til modellene nedenfor |
| **Go Plus** | **$40/måned** | Høyere bruksgrenser for modellene nedenfor |
Go fungerer som enhver annen leverandør i OpenCode. Du abonnerer på OpenCode Go og
får din API-nøkkel. Det er **helt valgfritt**, og du trenger ikke å bruke det for å
får API-nøkkelen din. Det er **helt valgfritt**, og du trenger ikke å bruke det for å
bruke OpenCode.
Det er først og fremst utviklet for internasjonale brukere og gir stabil global tilgang.
Tjenesten er først og fremst utviklet for internasjonale brukere og gir stabil global tilgang.
---
@@ -23,23 +29,24 @@ Det er først og fremst utviklet for internasjonale brukere og gir stabil global
proprietære modeller for kodeoppgaver. Og fordi mange leverandører kan tilby dem
konkurransedyktig, er de vanligvis mye billigere.
Imidlertid kan det være vanskelig å få pålitelig tilgang med lav forsinkelse til dem. Leverandører
Det kan imidlertid være vanskelig å få pålitelig tilgang med lav forsinkelse. Leverandører
varierer i kvalitet og tilgjengelighet.
:::tip
Vi testet en utvalgt gruppe modeller og leverandører som fungerer godt med OpenCode.
:::
For å fikse dette, gjorde vi et par ting:
For å løse dette gjorde vi et par ting:
1. Vi testet en utvalgt gruppe åpne modeller og snakket med teamene deres om hvordan de
best kan kjøres.
2. Deretter samarbeidet vi med noen få leverandører for å sikre at disse ble levert
riktig.
3. Til slutt utførte vi ytelsestester på kombinasjonen av modell og leverandør, og kom frem
til en liste som vi trygt kan anbefale.
3. Til slutt ytelsestestet vi kombinasjonen av modell og leverandør og utarbeidet
en liste vi trygt kan anbefale.
OpenCode Go gir deg tilgang til disse modellene for **$10/måned**.
Både Go og Go Plus gir tilgang til disse modellene. Velg abonnementet som passer til
hvor mye du bruker dem.
---
@@ -47,14 +54,14 @@ OpenCode Go gir deg tilgang til disse modellene for **$10/måned**.
OpenCode Go fungerer som enhver annen leverandør i OpenCode.
1. Du logger inn på **<a href={console}>OpenCode Zen</a>**, abonnerer på Go, og
kopierer din API-nøkkel.
2. Du kjører kommandoen `/connect` i TUI-en, velger `OpenCode Go`, og limer inn
din API-nøkkel.
1. Du logger inn på **<a href={console}>OpenCode Console</a>**, abonnerer på Go eller Go Plus og
kopierer API-nøkkelen din.
2. Du kjører kommandoen `/connect` i TUI-en, velger `OpenCode Go` og limer inn
API-nøkkelen din.
3. Kjør `/models` i TUI-en for å se listen over modeller som er tilgjengelige gjennom Go.
:::note
Kun ett medlem per arbeidsområde kan abonnere på OpenCode Go.
Kun ett medlem per arbeidsområde kan abonnere på OpenCode Go eller Go Plus.
:::
Den nåværende listen over modeller inkluderer:
@@ -64,13 +71,13 @@ Den nåværende listen over modeller inkluderer:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (i en begrenset periode)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -81,9 +88,7 @@ Den nåværende listen over modeller inkluderer:
- **Muse Spark 1.2 Contributor** ([begrensede regioner](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -91,7 +96,6 @@ Den nåværende listen over modeller inkluderer:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (i en begrenset periode)
- **LongCat 2.5 Preview Free** (i en begrenset periode)
Listen over modeller kan endres etter hvert som vi tester og legger til nye.
@@ -105,7 +109,7 @@ forringer opplevelsen for andre brukere.
Klienten din skal:
1. Sende typisk trafikk fra en kodeagent.
1. Sende typisk trafikk fra en kodeagent
2. Identifisere seg med sin egen user agent, for eksempel `my-coding-agent/1.0`, i stedet
for et generisk navn på et SDK eller HTTP-bibliotek.
3. Sende en stabil sesjons-ID i `x-opencode-session` for hver samtale, slik at vi kan optimalisere ruting og
@@ -116,14 +120,14 @@ Klienten din skal:
I tillegg til OpenCode er følgende klienter validert for å fungere riktig
med OpenCode Go. Vi garanterer imidlertid ikke at de vil fortsette å fungere i fremtiden.
| Klient | Sesjonsstøtte |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Hermes** | Bygg som inneholder [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864), sender headeren i primære og sekundære OpenCode-forespørsler. Rettelsen ble slått sammen etter v0.21.0; den versjonen inneholder den ikke alene. |
| **Claude Code** | Go gjenkjenner den innebygde sesjonsheaderen. En wrapper for en egendefinert header er ikke nødvendig. |
| **Codex** | Go gjenkjenner den innebygde sesjonsheaderen. Noen versjoner og proxyoppsett utelater den fortsatt; behold sesjonsheaderen når forespørsler videresendes. |
| **ZCode** | Go gjenkjenner den innebygde sesjonsheaderen. Vår [forespørsel om `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) er fortsatt åpen, men det er ikke lenger nødvendig å sende akkurat denne headeren. |
| **Pi** | Gjeldende bygg sender sesjonsinformasjon for OpenCode. Oppdater eldre installasjoner. |
| **jcode** | Oppdater til **v0.81.6 eller nyere**, som inneholder [rettelsen for sesjonsheaderen](https://github.com/1jehuang/jcode/issues/1167). |
| Klient | Sesjonsstøtte |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | Bygg som inneholder [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864), sender headeren i primære og sekundære OpenCode-forespørsler. Rettelsen ble slått sammen etter v0.21.0; den versjonen inneholder den ikke alene. |
| **Claude Code** | Go gjenkjenner den innebygde sesjonsheaderen. En wrapper for en egendefinert header er ikke nødvendig. |
| **Codex** | Go gjenkjenner den innebygde sesjonsheaderen. Noen versjoner og proxyoppsett utelater den fortsatt; behold sesjonsheaderen når forespørsler videresendes. |
| **ZCode** | Go gjenkjenner den innebygde sesjonsheaderen. Vår [forespørsel om `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) er fortsatt åpen, men det er ikke lenger nødvendig å sende akkurat denne headeren. |
| **Pi** | Gjeldende bygg sender sesjonsinformasjon for OpenCode. Oppdater eldre installasjoner. |
| **jcode** | Oppdater til **v0.81.6 eller nyere**, som inneholder [rettelsen for sesjonsheaderen](https://github.com/1jehuang/jcode/issues/1167). |
| **Kilo Code CLI** | Bygg som inneholder [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752), gjenoppretter OpenCode-sesjonsheadere. Denne rettelsen dekker CLI-en, ikke VS Code-utvidelsen. Se [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
### Kjente problematiske klienter
@@ -131,153 +135,246 @@ med OpenCode Go. Vi garanterer imidlertid ikke at de vil fortsette å fungere i
Disse klientene mangler sesjonsstøtte eller har ufullstendig støtte i versjonene vi
undersøkte. De lenkede rapportene følger rettelser og midlertidige løsninger.
| Klient | Status og oppfølging |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Klient | Status og oppfølging |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | Sesjonsinformasjon mottas på noen modellbaner, men mangler på andre. Vi gjenkjenner den innebygde headeren; det gjenstående arbeidet er å sende den gjennom alle adaptere. [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
| **GitHub Copilot Chat** | Automatisk støtte for sesjonsheaderen er etterspurt i [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | Automatisk støtte for sesjonsheaderen er etterspurt i [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) har en foreslått rettelse i [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), som ennå ikke er slått sammen. |
| **GitHub Copilot Chat** | Automatisk støtte for sesjonsheaderen er etterspurt i [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | Automatisk støtte for sesjonsheaderen er etterspurt i [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) har en foreslått rettelse i [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), som ennå ikke er slått sammen. |
## Bruksgrenser
Bruksgrenser defineres som månedlige dollarbeløp. Tabellen nedenfor viser den månedlige grensen og tokenkostnadene for hver modell.
Bruksgrenser defineres som månedlige dollarbeløp. Tabellen nedenfor viser den
månedlige grensen for hvert abonnement og tokenkostnadene for hver modell. Tokenprisene er
de samme for Go og Go Plus.
Hver modell har følgende bruksgrenser: 5-timersgrense — 20 % av den månedlige grensen; ukentlig grense — 50 %; og månedlig grense — 100 %.
Hver modell har følgende bruksgrenser: 5 timer — 20 % av den månedlige grensen;
ukentlig — 50 %; og månedlig — 100 %.
Hvis en modell for eksempel har en månedlig grense på $60, kan du bruke opptil:
Hvis en modell for eksempel har en månedlig grense på $60 med Go og $120 med
Go Plus, kan du bruke opptil:
- **5-timers grense** — $12 i bruk
- **Ukentlig grense** — $30 i bruk
- **Månedlig grense** — $60 i bruk
- **5-timersgrense** — $12 med Go eller $24 med Go Plus
- **Ukentlig grense** — $30 med Go eller $60 med Go Plus
- **Månedlig grense** — $60 med Go eller $120 med Go Plus
På tvers av modeller har Go rammer på $12 per 5 timer, $30 per uke og $60 per måned.
Go Plus har rammer på $48 per 5 timer, $120 per uke og $240 per måned. Den månedlige
grensen for hver modell nedenfor avgjør hvordan bruken teller mot disse
rammene.
Tokenpriser er oppgitt per 1M tokens.
| Model | Input | Output | Cached Read | Cached Write | Månedlig grense |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | --------------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Ubegrenset**<br /><small>i en begrenset periode</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Ubegrenset**<br /><small>i en begrenset periode</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modell | Inndata | Utdata | Bufret lesing | Bufret skriving | Månedlig grense |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Ubegrenset**<br /><small>i en begrenset periode</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Ubegrenset**<br /><small>i en begrenset periode</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Modell | Inndata | Utdata | Bufret lesing | Bufret skriving | Månedlig grense |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Gratis | Gratis | Gratis | - | **Ubegrenset**<br /><small>i en begrenset periode</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Gratis | Gratis | Gratis | - | **Ubegrenset**<br /><small>i en begrenset periode</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Gratis i en begrenset periode.
**LongCat 2.5 Preview Free:** Gratis i en begrenset periode.
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak-tidene er 01:00-04:00 og 06:00-10:00 UTC fra mandag til fredag; alle andre tider, inkludert helger, er Off-Peak. [Les mer](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak-tidene er 01:00-04:00 og 06:00-10:00 UTC, fra mandag til fredag; alle andre tider, inkludert helger, er Off-Peak. [Les mer](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** Bilder konverteres til tokens basert på dimensjonene og faktureres som input-tokens sammen med tekst-tokens. [Les mer](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** Bilder konverteres til tokens basert på dimensjonene og faktureres som inndatatokens sammen med teksttokens. [Les mer](https://api-docs.deepseek.com/quick_start/pricing/).
### Estimerte forespørsler
Tabellen nedenfor viser et estimert antall forespørsler basert på typiske bruksmønstre for Go:
Tabellene nedenfor anslår antall forespørsler basert på typiske bruksmønstre for Go. Anslagene for
Go Plus skaleres etter den høyere bruksgrensen for hver modell.
| Model | forespørsler per 5 timer | forespørsler per uke | forespørsler per måned |
| ---------------------------- | ------------------------ | -------------------- | ---------------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ubegrenset | Ubegrenset | Ubegrenset |
| LongCat 2.5 Preview Free | Ubegrenset | Ubegrenset | Ubegrenset |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modell | Forespørsler per 5 timer | Forespørsler per uke | Forespørsler per måned |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Ubegrenset | Ubegrenset | Ubegrenset |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ubegrenset | Ubegrenset | Ubegrenset |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Modell | Forespørsler per 5 timer | Forespørsler per uke | Forespørsler per måned |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Ubegrenset | Ubegrenset | Ubegrenset |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Ubegrenset | Ubegrenset | Ubegrenset |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Estimatene bruker følgende antall tokens per forespørsel; faktisk bruk varierer.
- Grok 4.7/4.6 — 390 input, 32 500 bufret, 120 output-tokens per forespørsel
- GLM-5.3-Flash — 1 000 input, 55 000 bufret, 200 output-tokens per forespørsel
- GLM-5.3/5.2/5.1 — 700 input, 52 000 bufret, 150 output-tokens per forespørsel
- GPT 6 Luna — 1 000 input, 50 000 bufret, 220 output-tokens per forespørsel
- GPT 5.6 Luna — 1 000 input, 50 000 bufret, 220 output-tokens per forespørsel
- Kimi K3 — 1 050 input, 76 500 bufret, 300 output-tokens per forespørsel
- Kimi K2.7/K2.6 — 870 input, 55 000 bufret, 200 output-tokens per forespørsel
- LongCat-2.0 — 920 input, 88 900 bufret, 200 output-tokens per forespørsel
- DeepSeek V4.1 Flash — 410 input, 71 300 bufret, 310 output-tokens per forespørsel
- DeepSeek V4 Pro — 750 input, 82 000 bufret, 290 output-tokens per forespørsel
- DeepSeek V4 Flash — 410 input, 71 300 bufret, 310 output-tokens per forespørsel
- DeepSeek V4 Flash Vision Exp — 410 input, 71 300 bufret, 310 output-tokens per forespørsel
- MiniMax M3 — 510 input, 56 000 bufret, 190 output-tokens per forespørsel
- MiniMax M2.7 — 300 input, 55 000 bufret, 125 output-tokens per forespørsel
- Muse Spark 1.3 Contributor — 620 input, 71 400 bufret, 300 output-tokens per forespørsel
- Muse Spark 1.2 Contributor — 620 input, 71 400 bufret, 300 output-tokens per forespørsel
- Qwen3.8 Max — 420 input, 66 000 bufret, 200 output-tokens per forespørsel
- Qwen3.8 Flash — 600 input, 58 000 bufret, 200 output-tokens per forespørsel
- Qwen3.7 Max — 420 input, 66 000 bufret, 200 output-tokens per forespørsel
- Qwen3.7 Plus — 500 input, 57 000 bufret, 190 output-tokens per forespørsel
- Qwen3.6 Plus — 500 input, 57 000 bufret, 190 output-tokens per forespørsel
- Hy4 preview — 830 input, 71 500 bufret, 295 output-tokens per forespørsel
- Hy3 — 830 input, 71 500 bufret, 295 output-tokens per forespørsel
- MiMo-V2.6-Flash — 830 input, 71 500 bufret, 295 output-tokens per forespørsel
- MiMo-V2.6-Pro — 790 input, 86 000 bufret, 305 output-tokens per forespørsel
- MiMo-V2.5 — 830 input, 71 500 bufret, 295 output-tokens per forespørsel
- MiMo-V2.5-Pro — 790 input, 86 000 bufret, 305 output-tokens per forespørsel
- Grok 4.7/4.6 — 390 inndatatokens, 32,500 bufret, 120 utdatokens per forespørsel
- GLM-5.3-Flash — 1,000 inndatatokens, 55,000 bufret, 200 utdatokens per forespørsel
- GLM-5.3/5.2 — 700 inndatatokens, 52,000 bufret, 150 utdatokens per forespørsel
- GPT 6 Luna — 1,000 inndatatokens, 50,000 bufret, 220 utdatokens per forespørsel
- GPT 5.6 Luna — 1,000 inndatatokens, 50,000 bufret, 220 utdatokens per forespørsel
- Kimi K3 — 1,050 inndatatokens, 76,500 bufret, 300 utdatokens per forespørsel
- Kimi K2.7/K2.6 — 870 inndatatokens, 55,000 bufret, 200 utdatokens per forespørsel
- LongCat-2.0 — 920 inndatatokens, 88,900 bufret, 200 utdatokens per forespørsel
- DeepSeek V4.1 Flash — 410 inndatatokens, 71,300 bufret, 310 utdatokens per forespørsel
- DeepSeek V4 Pro — 750 inndatatokens, 82,000 bufret, 290 utdatokens per forespørsel
- DeepSeek V4 Flash — 410 inndatatokens, 71,300 bufret, 310 utdatokens per forespørsel
- DeepSeek V4 Flash Vision Exp — 410 inndatatokens, 71,300 bufret, 310 utdatokens per forespørsel
- MiniMax M3 — 510 inndatatokens, 56,000 bufret, 190 utdatokens per forespørsel
- MiniMax M2.7 — 300 inndatatokens, 55,000 bufret, 125 utdatokens per forespørsel
- Muse Spark 1.3 Contributor — 620 inndatatokens, 71,400 bufret, 300 utdatokens per forespørsel
- Muse Spark 1.2 Contributor — 620 inndatatokens, 71,400 bufret, 300 utdatokens per forespørsel
- MiMo-V2.6-Flash — 830 inndatatokens, 71,500 bufret, 295 utdatokens per forespørsel
- MiMo-V2.6-Pro — 790 inndatatokens, 86,000 bufret, 305 utdatokens per forespørsel
- MiMo-V2.5 — 830 inndatatokens, 71,500 bufret, 295 utdatokens per forespørsel
- MiMo-V2.5-Pro — 790 inndatatokens, 86,000 bufret, 305 utdatokens per forespørsel
- Qwen3.8 Max — 420 inndatatokens, 66,000 bufret, 200 utdatokens per forespørsel
- Qwen3.8 Flash — 600 inndatatokens, 58,000 bufret, 200 utdatokens per forespørsel
- Qwen3.7 Plus — 500 inndatatokens, 57,000 bufret, 190 utdatokens per forespørsel
- Hy4 preview — 830 inndatatokens, 71,500 bufret, 295 utdatokens per forespørsel
- Hy3 — 830 inndatatokens, 71,500 bufret, 295 utdatokens per forespørsel
Du kan spore din nåværende bruk i **<a href={console}>konsollen</a>**.
Du kan følge med på din nåværende bruk i **<a href={console}>konsollen</a>**.
:::tip
Hvis du når bruksgrensen, kan du fortsette å bruke gratismodellene.
@@ -289,21 +386,21 @@ Bruksgrenser kan endres etter hvert som vi lærer fra tidlig bruk og tilbakemeld
### Bruk utover grensene
Hvis du også har kreditt på din Zen-saldo, kan du aktivere alternativet **Bruk saldo**
i konsollen. Når dette er aktivert, vil Go falle tilbake på din Zen-saldo
etter at du har nådd bruksgrensene dine, i stedet for å blokkere forespørsler.
Hvis du også har kreditt på Zen-saldoen din, kan du aktivere alternativet **Bruk saldo**
i konsollen. Når dette er aktivert, bruker Go Zen-saldoen din
etter at du har nådd bruksgrensene, i stedet for å blokkere forespørsler.
---
### Hvorfor noen modeller har lavere bruk
Med Go betaler du $10/måned, og den inkluderte månedlige bruken varierer etter modell.
Med Go varierer den inkluderte månedlige bruken etter modell.
For de fleste modeller får vi dette til gjennom volumrabatter og reservert GPU-kapasitet. Deretter gir vi disse besparelsene videre til deg i form av mer månedlig bruk.
For de fleste modeller får vi dette til gjennom volumrabatter og reservert GPU-kapasitet. Deretter gir vi besparelsene videre til deg i form av mer månedlig bruk.
For noen modeller har vi ikke hatt muligheten til å forhandle frem en rabatt eller drifte dem til en lavere kostnad, enten fordi modellen er ny, eller fordi den offentlige prisen allerede er rabattert.
For disse modellene får du fortsatt litt mer enn om du betalte modellleverandørene direkte. Derfor er den inkluderte månedlige bruken deres lavere.
For disse modellene får du fortsatt litt mer enn om du betalte modellleverandørene direkte. Derfor er den inkluderte månedlige bruken lavere.
---
@@ -311,7 +408,7 @@ For disse modellene får du fortsatt litt mer enn om du betalte modellleverandø
Du kan også få tilgang til Go-modeller gjennom følgende API-endepunkter.
| Modell | Modell-ID | Endepunkt | AI SDK Package |
| Modell | Modell-ID | Endepunkt | AI SDK-pakke |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -320,11 +417,11 @@ Du kan også få tilgang til Go-modeller gjennom følgende API-endepunkter.
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -335,22 +432,18 @@ Du kan også få tilgang til Go-modeller gjennom følgende API-endepunkter.
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
[Modell-ID-en](/docs/config/#models) i din OpenCode-konfigurasjon
bruker formatet `opencode-go/<model-id>`. For eksempel, for Kimi K3, vil du
bruke `opencode-go/kimi-k3` i konfigurasjonen din.
[Modell-ID-en](/docs/config/#models) i OpenCode-konfigurasjonen din
bruker formatet `opencode-go/<model-id>`. For Kimi K3 bruker du for eksempel
`opencode-go/kimi-k3` i konfigurasjonen.
---
@@ -367,46 +460,43 @@ https://opencode.ai/zen/go/v1/models
## Personvern
| Modell | Modelltrening | Dataoppbevaring |
| ---------------------------- | ------------- | --------------- |
| Grok 4.7 | Brukes ikke | 30 dager |
| Grok 4.6 | Brukes ikke | 30 dager |
| GPT 6 Luna | Brukes ikke | 30 dager |
| GPT 5.6 Luna | Brukes ikke | 30 dager |
| GLM-5.3-Flash | Brukes ikke | 0 dager |
| GLM-5.3 | Brukes ikke | 0 dager |
| GLM-5.2 | Brukes ikke | 0 dager |
| GLM-5.1 | Brukes ikke | 0 dager |
| Kimi K3 | Brukes ikke | 0 dager |
| Kimi K2.7 Code | Brukes ikke | 0 dager |
| Kimi K2.6 | Brukes ikke | 0 dager |
| LongCat-2.0 | Brukes ikke | 0 dager |
| MiMo-V2.6-Pro | Brukes ikke | 0 dager |
| MiMo-V2.6-Flash | Brukes ikke | 0 dager |
| MiMo-V2.5-Pro | Brukes ikke | 0 dager |
| MiMo-V2.5 | Brukes ikke | 0 dager |
| Qwen3.8 Max | Brukes ikke | 0 dager |
| Qwen3.8 Flash | Brukes ikke | 0 dager |
| Qwen3.7 Max | Brukes ikke | 0 dager |
| Qwen3.7 Plus | Brukes ikke | 0 dager |
| Qwen3.6 Plus | Brukes ikke | 0 dager |
| MiniMax M3 | Brukes ikke | 0 dager |
| MiniMax M2.7 | Brukes ikke | 0 dager |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Brukes ikke | 30 dager |
| Grok 4.6 | Brukes ikke | 30 dager |
| GPT 6 Luna | Brukes ikke | 30 dager |
| GPT 5.6 Luna | Brukes ikke | 30 dager |
| GLM-5.3-Flash | Brukes ikke | 0 dager |
| GLM-5.3 | Brukes ikke | 0 dager |
| GLM-5.2 | Brukes ikke | 0 dager |
| Kimi K3 | Brukes ikke | 0 dager |
| Kimi K2.7 Code | Brukes ikke | 0 dager |
| Kimi K2.6 | Brukes ikke | 0 dager |
| LongCat-2.0 | Brukes ikke | 0 dager |
| MiMo-V2.6-Pro | Brukes ikke | 0 dager |
| MiMo-V2.6-Flash | Brukes ikke | 0 dager |
| MiMo-V2.5-Pro | Brukes ikke | 0 dager |
| MiMo-V2.5 | Brukes ikke | 0 dager |
| Qwen3.8 Max | Brukes ikke | 0 dager |
| Qwen3.8 Flash | Brukes ikke | 0 dager |
| Qwen3.7 Plus | Brukes ikke | 0 dager |
| MiniMax M3 | Brukes ikke | 0 dager |
| MiniMax M2.7 | Brukes ikke | 0 dager |
| Muse Spark 1.3 Contributor | Ja | Ikke ZDR |
| Muse Spark 1.2 Contributor | Ja | Ikke ZDR |
| DeepSeek V4.1 Flash | Brukes ikke | 0 dager |
| DeepSeek V4 Pro | Brukes ikke | 0 dager |
| DeepSeek V4 Flash | Brukes ikke | 0 dager |
| DeepSeek V4 Flash Vision Exp | Brukes ikke | 0 dager |
| Hy4 preview | Brukes ikke | 0 dager |
| Hy3 | Brukes ikke | 0 dager |
| Space Bunny Free | Brukes ikke | 0 dager |
| LongCat 2.5 Preview Free | Brukes ikke | 0 dager |
| DeepSeek V4.1 Flash | Brukes ikke | 0 dager\* |
| DeepSeek V4 Pro | Brukes ikke | 0 dager\* |
| DeepSeek V4 Flash | Brukes ikke | 0 dager\* |
| DeepSeek V4 Flash Vision Exp | Brukes ikke | 0 dager\* |
| Hy4 preview | Brukes ikke | 0 dager |
| Hy3 | Brukes ikke | 0 dager |
| Space Bunny Free | Brukes ikke | 0 dager |
| LongCat 2.5 Preview Free | Brukes ikke | 0 dager |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Kraftig rabatterte tokenpriser i bytte mot tillatelse til å bruke ledetekstene og fullføringene dine til å trene fremtidige Meta-modeller. Tilgjengeligheten er begrenset til regioner som er tillatt i henhold til [retningslinjene for geografisk bruk](https://ai.developer.meta.com/legal/geographic-use-policy) fra Meta. [Les mer](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Kraftig rabatterte tokenpriser i bytte mot tillatelse til å bruke ledetekstene og fullføringene dine til å trene fremtidige Meta-modeller. Tilgjengeligheten er begrenset til regioner som er tillatt i henhold til [retningslinjene for geografisk bruk](https://ai.developer.meta.com/legal/geographic-use-policy) fra Meta. [Les mer](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR-avtalen fornyes månedlig. Den gjeldende avtalen er gyldig til og med 30. september 2026.
- **Muse Spark 1.3 Contributor:** Kraftig rabatterte tokenpriser i bytte mot tillatelse til å bruke ledetekstene og fullføringene dine til å trene fremtidige Meta-modeller. Tilgjengeligheten er begrenset til regioner som er tillatt i henhold til Metas [retningslinjer for geografisk bruk](https://ai.developer.meta.com/legal/geographic-use-policy). [Les mer](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Kraftig rabatterte tokenpriser i bytte mot tillatelse til å bruke ledetekstene og fullføringene dine til å trene fremtidige Meta-modeller. Tilgjengeligheten er begrenset til regioner som er tillatt i henhold til Metas [retningslinjer for geografisk bruk](https://ai.developer.meta.com/legal/geographic-use-policy). [Les mer](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR-avtalen fornyes månedlig. Den gjeldende avtalen er gyldig til og med 31. oktober 2026.
---
@@ -417,4 +507,4 @@ Vi opprettet OpenCode Go for å:
1. Gjøre AI-koding **tilgjengelig** for flere mennesker med et lavkostnadsabonnement.
2. Gi **pålitelig** tilgang til de beste åpne kodemodellene.
3. Kuratere modeller som er **testet og ytelsesmålt** for bruk av kodeagenter.
4. Ha **ingen innelåsing** ved å la deg bruke en hvilken som helst annen leverandør med OpenCode også.
4. Ha **ingen innelåsing** ved også å la deg bruke enhver annen leverandør med OpenCode.
packages/web/src/content/docs/pl/go.mdx
+300 -202
View File
@@ -1,39 +1,52 @@
---
title: Go
description: Niskokosztowa subskrypcja na otwarte modele do kodowania.
description: Niezawodny dostęp do otwartych modeli do kodowania w dwóch planach użycia.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go to niskokosztowa subskrypcja za **10 $/miesiąc**, która zapewnia niezawodny dostęp do popularnych otwartych modeli do kodowania.
OpenCode Go zapewnia niezawodny dostęp do popularnych otwartych modeli do kodowania w ramach dwóch planów miesięcznych:
| Plan | Cena | Użycie w cenie |
| ---- | ----- | -------------- |
| **Go** | **$10/miesiąc** | Tańszy dostęp do poniższych modeli |
| **Go Plus** | **$40/miesiąc** | Wyższe limity użycia poniższych modeli |
Go działa jak każdy inny dostawca w OpenCode. Subskrybujesz OpenCode Go i
otrzymujesz swój klucz API. Jest to **całkowicie opcjonalne** i nie musisz z tego korzystać, aby
używać OpenCode.
Jest przeznaczony przede wszystkim dla użytkowników z całego świata i zapewnia stabilny dostęp globalny.
Usługa jest przeznaczona przede wszystkim dla użytkowników z całego świata i zapewnia stabilny dostęp globalny.
---
## Tło
Otwarte modele stały się naprawdę dobre. Obecnie osiągają wydajność zbliżoną do modeli własnościowych w zadaniach związanych z kodowaniem. A ponieważ wielu dostawców może je oferować konkurencyjnie, są one zazwyczaj znacznie tańsze.
Otwarte modele stały się naprawdę dobre. Obecnie osiągają wydajność zbliżoną do
modeli własnościowych w zadaniach związanych z kodowaniem. Ponieważ wielu dostawców może oferować je
konkurencyjnie, są zazwyczaj znacznie tańsze.
Jednak uzyskanie do nich niezawodnego dostępu o niskich opóźnieniach może być trudne. Dostawcy różnią się pod względem jakości i dostępności.
Jednak uzyskanie do nich niezawodnego dostępu o niskich opóźnieniach może być trudne. Dostawcy
różnią się pod względem jakości i dostępności.
:::tip
Przetestowaliśmy wybraną grupę modeli i dostawców, którzy dobrze współpracują z OpenCode.
:::
Aby to naprawić, zrobiliśmy kilka rzeczy:
Aby rozwiązać ten problem, zrobiliśmy kilka rzeczy:
1. Przetestowaliśmy wybraną grupę otwartych modeli i porozmawialiśmy z ich zespołami na temat najlepszych sposobów ich uruchamiania.
2. Następnie nawiązaliśmy współpracę z kilkoma dostawcami, aby upewnić się, że są one obsługiwane poprawnie.
3. Na koniec przetestowaliśmy kombinację modelu/dostawcy i stworzyliśmy listę, którą możemy z przekonaniem polecić.
1. Przetestowaliśmy wybraną grupę otwartych modeli i porozmawialiśmy z ich zespołami o tym, jak
najlepiej je uruchamiać.
2. Następnie nawiązaliśmy współpracę z kilkoma dostawcami, aby upewnić się, że modele są obsługiwane
prawidłowo.
3. Na koniec przetestowaliśmy wydajność kombinacji modelu i dostawcy oraz utworzyliśmy
listę, którą możemy z przekonaniem polecić.
OpenCode Go daje Ci dostęp do tych modeli za **10 $/miesiąc**.
Zarówno Go, jak i Go Plus zapewniają dostęp do tych modeli. Wybierz plan odpowiedni do
intensywności korzystania z nich.
---
@@ -41,14 +54,14 @@ OpenCode Go daje Ci dostęp do tych modeli za **10 $/miesiąc**.
OpenCode Go działa jak każdy inny dostawca w OpenCode.
1. Logujesz się do **<a href={console}>OpenCode Zen</a>**, subskrybujesz Go i
kopiujesz swój klucz API.
2. Uruchamiasz komendę `/connect` w TUI, wybierasz `OpenCode Go` i wklejasz
1. Zaloguj się do **<a href={console}>OpenCode Console</a>**, zasubskrybuj Go lub Go Plus i
skopiuj swój klucz API.
2. Uruchom polecenie `/connect` w TUI, wybierz `OpenCode Go` i wklej
swój klucz API.
3. Uruchom `/models` w TUI, aby zobaczyć listę modeli dostępnych w ramach Go.
:::note
Tylko jeden członek na obszar roboczy (workspace) może zasubskrybować OpenCode Go.
Tylko jeden członek obszaru roboczego może zasubskrybować OpenCode Go lub Go Plus.
:::
Obecna lista modeli obejmuje:
@@ -58,13 +71,13 @@ Obecna lista modeli obejmuje:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (przez ograniczony czas)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -75,9 +88,7 @@ Obecna lista modeli obejmuje:
- **Muse Spark 1.2 Contributor** ([ograniczone regiony](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -85,7 +96,6 @@ Obecna lista modeli obejmuje:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (przez ograniczony czas)
- **LongCat 2.5 Preview Free** (przez ograniczony czas)
Lista modeli może ulec zmianie w miarę testowania i dodawania nowych.
@@ -95,14 +105,14 @@ Lista modeli może ulec zmianie w miarę testowania i dodawania nowych.
OpenCode Go jest przeznaczony dla [OpenCode](https://opencode.ai) i innych agentów kodujących,
którzy wysyłają podobne rodzaje żądań. Ruch jest monitorowany pod kątem nadużyć,
które pogarszają komfort korzystania z usługi przez innych użytkowników.
które pogarszają komfort innych użytkowników.
Twój klient powinien:
1. Wysyłać ruch typowy dla agenta kodującego.
1. Wysyłać ruch typowy dla agenta kodującego
2. Identyfikować się za pomocą własnego user agenta, na przykład `my-coding-agent/1.0`, zamiast
ogólnej nazwy SDK lub biblioteki HTTP.
3. Wysyłać stabilny identyfikator sesji w nagłówku `x-opencode-session` dla każdej rozmowy, aby umożliwić optymalizację routingu i
3. Wysyłać stabilny identyfikator sesji w `x-opencode-session` dla każdej rozmowy, aby umożliwić optymalizację routingu i
buforowania promptów.
### Zweryfikowane klienty
@@ -110,14 +120,14 @@ Twój klient powinien:
Poza OpenCode zweryfikowano, że poniżsi klienci działają prawidłowo
z OpenCode Go. Nie gwarantujemy jednak, że będą nadal działać w przyszłości.
| Klient | Obsługa sesji |
| ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | Kompilacje zawierające [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) wysyłają nagłówek w głównych i pomocniczych żądaniach OpenCode. Poprawkę scalono po wersji v0.21.0; samo to wydanie jej nie zawiera. |
| **Claude Code** | Go rozpoznaje jego natywny nagłówek sesji. Wrapper dodający niestandardowy nagłówek nie jest potrzebny. |
| **Codex** | Go rozpoznaje jego natywny nagłówek sesji. Niektóre wersje i konfiguracje proxy nadal go pomijają; podczas przekazywania żądań należy zachować nagłówek sesji. |
| **ZCode** | Go rozpoznaje jego natywny nagłówek sesji. Nasza [prośba o `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) pozostaje otwarta, ale wysyłanie tego konkretnego nagłówka nie jest już konieczne. |
| **Pi** | Aktualne kompilacje wysyłają informacje o sesji dla OpenCode. Zaktualizuj starsze instalacje. |
| **jcode** | Zaktualizuj do wersji **v0.81.6 lub nowszej**, która zawiera [poprawkę nagłówka sesji](https://github.com/1jehuang/jcode/issues/1167). |
| Klient | Obsługa sesji |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | Kompilacje zawierające [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) wysyłają nagłówek w głównych i pomocniczych żądaniach OpenCode. Poprawkę scalono po wersji v0.21.0; samo to wydanie jej nie zawiera. |
| **Claude Code** | Go rozpoznaje jego natywny nagłówek sesji. Wrapper dodający niestandardowy nagłówek nie jest potrzebny. |
| **Codex** | Go rozpoznaje jego natywny nagłówek sesji. Niektóre wersje i konfiguracje proxy nadal go pomijają; podczas przekazywania żądań należy zachować nagłówek sesji. |
| **ZCode** | Go rozpoznaje jego natywny nagłówek sesji. Nasza [prośba o `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) pozostaje otwarta, ale wysyłanie tego konkretnego nagłówka nie jest już konieczne. |
| **Pi** | Aktualne kompilacje wysyłają informacje o sesji dla OpenCode. Zaktualizuj starsze instalacje. |
| **jcode** | Zaktualizuj do wersji **v0.81.6 lub nowszej**, która zawiera [poprawkę nagłówka sesji](https://github.com/1jehuang/jcode/issues/1167). |
| **Kilo Code CLI** | Kompilacje zawierające [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) przywracają nagłówki sesji OpenCode. Ta poprawka obejmuje CLI, ale nie rozszerzenie VS Code. Zobacz [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
### Klienty ze znanymi problemami
@@ -125,73 +135,128 @@ z OpenCode Go. Nie gwarantujemy jednak, że będą nadal działać w przyszłoś
W badanych przez nas wersjach tych klientów obsługa sesji jest niepełna lub jej brakuje.
Raporty pod podanymi linkami służą do śledzenia poprawek i obejść.
| Klient | Stan i śledzenie |
| ----------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Klient | Stan i śledzenie |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | Informacje o sesji docierają w niektórych ścieżkach modeli, ale brakuje ich w innych. Rozpoznajemy jego natywny nagłówek; pozostaje zapewnić jego wysyłanie przez wszystkie adaptery. [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
| **GitHub Copilot Chat** | Prośbę o automatyczną obsługę nagłówka sesji zgłoszono w [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | Prośbę o automatyczną obsługę nagłówka sesji zgłoszono w [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | Dla [issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) zaproponowano poprawkę w [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), który nie został jeszcze scalony. |
| **GitHub Copilot Chat** | Prośbę o automatyczną obsługę nagłówka sesji zgłoszono w [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | Prośbę o automatyczną obsługę nagłówka sesji zgłoszono w [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | Dla [issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) zaproponowano poprawkę w [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), który nie został jeszcze scalony. |
## Limity użycia
Limity użycia są określane jako miesięczne kwoty w dolarach. Poniższa tabela przedstawia miesięczny limit i koszty tokenów dla każdego modelu.
Limity użycia są określane jako miesięczne kwoty w dolarach. Poniższa tabela przedstawia
miesięczny limit każdego planu oraz koszty tokenów dla każdego modelu. Ceny tokenów są
takie same w Go i Go Plus.
Każdy model ma następujące limity użycia: 5-godzinny — 20% miesięcznego limitu; tygodniowy — 50%; miesięczny — 100%.
Każdy model ma następujące limity użycia: 5-godzinny — 20% limitu miesięcznego;
tygodniowy — 50%; miesięczny — 100%.
Na przykład, jeśli model ma miesięczny limit $60, możesz wykorzystać do:
Na przykład, jeśli model ma miesięczny limit $60 w Go i $120
w Go Plus, możesz wykorzystać do:
- **Limit 5-godzinny** — użycie o wartości $12
- **Limit tygodniowy** — użycie o wartości $30
- **Limit miesięczny** — użycie o wartości $60
- **Limit 5-godzinny** — $12 w Go lub $24 w Go Plus
- **Limit tygodniowy** — $30 w Go lub $60 w Go Plus
- **Limit miesięczny** — $60 w Go lub $120 w Go Plus
Łącznie dla wszystkich modeli Go ma limity $12 na 5 godzin, $30 tygodniowo i $60 miesięcznie;
Go Plus ma limity $48 na 5 godzin, $120 tygodniowo i $240 miesięcznie. Poniższy miesięczny
limit każdego modelu określa, jak jego użycie jest zaliczane do tych
limitów.
Ceny tokenów podano za 1M tokenów.
| Model | Wejście | Wyjście | Odczyt z cache | Zapis do cache | Limit miesięczny |
| --------------------------------------- | ------- | ------- | -------------- | -------------- | --------------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Bez limitu**<br /><small>przez ograniczony czas</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Bez limitu**<br /><small>przez ograniczony czas</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Wejście | Wyjście | Odczyt z cache | Zapis do cache | Limit miesięczny |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Bezpłatne | Bezpłatne | Bezpłatne | - | **Bez limitu**<br /><small>przez ograniczony czas</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Bezpłatne | Bezpłatne | Bezpłatne | - | **Bez limitu**<br /><small>przez ograniczony czas</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Model | Wejście | Wyjście | Odczyt z cache | Zapis do cache | Limit miesięczny |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Bezpłatne | Bezpłatne | Bezpłatne | - | **Bez limitu**<br /><small>przez ograniczony czas</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Bezpłatne | Bezpłatne | Bezpłatne | - | **Bez limitu**<br /><small>przez ograniczony czas</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Bezpłatny przez ograniczony czas.
@@ -203,99 +268,139 @@ Ceny tokenów podano za 1M tokenów.
### Szacunkowa liczba żądań
Poniższa tabela przedstawia szacunkową liczbę żądań na podstawie typowych wzorców korzystania z Go:
Poniższe tabele przedstawiają szacunkową liczbę żądań na podstawie typowych wzorców korzystania z Go. Szacunki dla Go
Plus są skalowane zgodnie z wyższym limitem użycia każdego modelu.
| Model | żądania na 5 godzin | żądania na tydzień | żądania na miesiąc |
| ---------------------------- | ------------------- | ------------------ | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Bez limitu | Bez limitu | Bez limitu |
| LongCat 2.5 Preview Free | Bez limitu | Bez limitu | Bez limitu |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Żądania na 5 godzin | Żądania na tydzień | Żądania na miesiąc |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Bez limitu | Bez limitu | Bez limitu |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Bez limitu | Bez limitu | Bez limitu |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Model | Żądania na 5 godzin | Żądania na tydzień | Żądania na miesiąc |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Bez limitu | Bez limitu | Bez limitu |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Bez limitu | Bez limitu | Bez limitu |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Szacunki wykorzystują następującą liczbę tokenów na żądanie; rzeczywiste użycie jest zmienne.
- Grok 4.7/4.6 — 390 tokenów wejściowych, 32 500 w pamięci podręcznej, 120 tokenów wyjściowych na żądanie
- GLM-5.3-Flash — 1 000 tokenów wejściowych, 55 000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- GLM-5.3/5.2/5.1 — 700 tokenów wejściowych, 52 000 w pamięci podręcznej, 150 tokenów wyjściowych na żądanie
- GPT 6 Luna — 1 000 tokenów wejściowych, 50 000 w pamięci podręcznej, 220 tokenów wyjściowych na żądanie
- GPT 5.6 Luna — 1 000 tokenów wejściowych, 50 000 w pamięci podręcznej, 220 tokenów wyjściowych na żądanie
- Kimi K3 — 1 050 tokenów wejściowych, 76 500 w pamięci podręcznej, 300 tokenów wyjściowych na żądanie
- Kimi K2.7/K2.6 — 870 tokenów wejściowych, 55 000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- LongCat-2.0 — 920 tokenów wejściowych, 88 900 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- DeepSeek V4.1 Flash — 410 tokenów wejściowych, 71 300 w pamięci podręcznej, 310 tokenów wyjściowych na żądanie
- DeepSeek V4 Pro — 750 tokenów wejściowych, 82 000 w pamięci podręcznej, 290 tokenów wyjściowych na żądanie
- DeepSeek V4 Flash — 410 tokenów wejściowych, 71 300 w pamięci podręcznej, 310 tokenów wyjściowych na żądanie
- DeepSeek V4 Flash Vision Exp — 410 tokenów wejściowych, 71 300 w pamięci podręcznej, 310 tokenów wyjściowych na żądanie
- MiniMax M3 — 510 tokenów wejściowych, 56 000 w pamięci podręcznej, 190 tokenów wyjściowych na żądanie
- MiniMax M2.7 — 300 tokenów wejściowych, 55 000 w pamięci podręcznej, 125 tokenów wyjściowych na żądanie
- Muse Spark 1.3 Contributor — 620 tokenów wejściowych, 71 400 w pamięci podręcznej, 300 tokenów wyjściowych na żądanie
- Muse Spark 1.2 Contributor — 620 tokenów wejściowych, 71 400 w pamięci podręcznej, 300 tokenów wyjściowych na żądanie
- Qwen3.8 Max — 420 tokenów wejściowych, 66 000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- Qwen3.8 Flash — 600 tokenów wejściowych, 58 000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- Qwen3.7 Max — 420 tokenów wejściowych, 66 000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- Qwen3.7 Plus — 500 tokenów wejściowych, 57 000 w pamięci podręcznej, 190 tokenów wyjściowych na żądanie
- Qwen3.6 Plus — 500 tokenów wejściowych, 57 000 w pamięci podręcznej, 190 tokenów wyjściowych na żądanie
- Hy4 preview — 830 tokenów wejściowych, 71 500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
- Hy3 — 830 tokenów wejściowych, 71 500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
- MiMo-V2.6-Flash — 830 tokenów wejściowych, 71 500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
- MiMo-V2.6-Pro — 790 tokenów wejściowych, 86 000 w pamięci podręcznej, 305 tokenów wyjściowych na żądanie
- MiMo-V2.5 — 830 tokenów wejściowych, 71 500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
- MiMo-V2.5-Pro — 790 tokenów wejściowych, 86 000 w pamięci podręcznej, 305 tokenów wyjściowych na żądanie
- Grok 4.7/4.6 — 390 tokenów wejściowych, 32,500 w pamięci podręcznej, 120 tokenów wyjściowych na żądanie
- GLM-5.3-Flash — 1,000 tokenów wejściowych, 55,000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- GLM-5.3/5.2 — 700 tokenów wejściowych, 52,000 w pamięci podręcznej, 150 tokenów wyjściowych na żądanie
- GPT 6 Luna — 1,000 tokenów wejściowych, 50,000 w pamięci podręcznej, 220 tokenów wyjściowych na żądanie
- GPT 5.6 Luna — 1,000 tokenów wejściowych, 50,000 w pamięci podręcznej, 220 tokenów wyjściowych na żądanie
- Kimi K3 — 1,050 tokenów wejściowych, 76,500 w pamięci podręcznej, 300 tokenów wyjściowych na żądanie
- Kimi K2.7/K2.6 — 870 tokenów wejściowych, 55,000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- LongCat-2.0 — 920 tokenów wejściowych, 88,900 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- DeepSeek V4.1 Flash — 410 tokenów wejściowych, 71,300 w pamięci podręcznej, 310 tokenów wyjściowych na żądanie
- DeepSeek V4 Pro — 750 tokenów wejściowych, 82,000 w pamięci podręcznej, 290 tokenów wyjściowych na żądanie
- DeepSeek V4 Flash — 410 tokenów wejściowych, 71,300 w pamięci podręcznej, 310 tokenów wyjściowych na żądanie
- DeepSeek V4 Flash Vision Exp — 410 tokenów wejściowych, 71,300 w pamięci podręcznej, 310 tokenów wyjściowych na żądanie
- MiniMax M3 — 510 tokenów wejściowych, 56,000 w pamięci podręcznej, 190 tokenów wyjściowych na żądanie
- MiniMax M2.7 — 300 tokenów wejściowych, 55,000 w pamięci podręcznej, 125 tokenów wyjściowych na żądanie
- Muse Spark 1.3 Contributor — 620 tokenów wejściowych, 71,400 w pamięci podręcznej, 300 tokenów wyjściowych na żądanie
- Muse Spark 1.2 Contributor — 620 tokenów wejściowych, 71,400 w pamięci podręcznej, 300 tokenów wyjściowych na żądanie
- MiMo-V2.6-Flash — 830 tokenów wejściowych, 71,500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
- MiMo-V2.6-Pro — 790 tokenów wejściowych, 86,000 w pamięci podręcznej, 305 tokenów wyjściowych na żądanie
- MiMo-V2.5 — 830 tokenów wejściowych, 71,500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
- MiMo-V2.5-Pro — 790 tokenów wejściowych, 86,000 w pamięci podręcznej, 305 tokenów wyjściowych na żądanie
- Qwen3.8 Max — 420 tokenów wejściowych, 66,000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- Qwen3.8 Flash — 600 tokenów wejściowych, 58,000 w pamięci podręcznej, 200 tokenów wyjściowych na żądanie
- Qwen3.7 Plus — 500 tokenów wejściowych, 57,000 w pamięci podręcznej, 190 tokenów wyjściowych na żądanie
- Hy4 preview — 830 tokenów wejściowych, 71,500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
- Hy3 — 830 tokenów wejściowych, 71,500 w pamięci podręcznej, 295 tokenów wyjściowych na żądanie
Możesz śledzić swoje bieżące zużycie w **<a href={console}>konsoli</a>**.
:::tip
Jeśli osiągniesz limit użycia, możesz nadal korzystać z darmowych modeli.
Jeśli osiągniesz limit użycia, możesz nadal korzystać z bezpłatnych modeli.
:::
Limity użycia mogą ulec zmianie w miarę wyciągania wniosków z wczesnego użytkowania i opinii.
Limity użycia mogą ulec zmianie w miarę wyciągania wniosków z początkowego użytkowania i opinii.
---
### Użycie ponad limity
Jeśli masz również środki na swoim saldzie Zen, możesz włączyć opcję **Użyj salda** (Use balance) w konsoli. Po włączeniu Go będzie korzystać z Twojego salda Zen po osiągnięciu limitów użycia zamiast blokować żądania.
Jeśli masz również środki na saldzie Zen, możesz włączyć opcję **Użyj salda**
w konsoli. Po jej włączeniu Go zacznie korzystać z salda Zen
po osiągnięciu limitów użycia zamiast blokować żądania.
---
### Dlaczego niektóre modele mają niższe limity użycia
Go kosztuje $10/miesiąc, a miesięczne użycie w ramach subskrypcji różni się w zależności od modelu.
W planie Go miesięczne użycie w cenie różni się w zależności od modelu.
W przypadku większości modeli jest to możliwe dzięki rabatom hurtowym i zarezerwowanej mocy obliczeniowej GPU. Uzyskane w ten sposób oszczędności przekazujemy Tobie w postaci większego miesięcznego użycia.
W przypadku większości modeli jest to możliwe dzięki rabatom hurtowym i zarezerwowanej mocy obliczeniowej GPU. Uzyskane oszczędności przekazujemy Tobie w postaci większego miesięcznego użycia.
W przypadku niektórych modeli nie mieliśmy jeszcze możliwości wynegocjowania rabatu ani hostowania ich po niższym koszcie, ponieważ model jest nowy lub jego publiczny cennik już uwzględnia rabat.
W przypadku tych modeli nadal otrzymujesz nieco więcej, niż płacąc bezpośrednio ich dostawcom. Dlatego ich miesięczne użycie w ramach subskrypcji jest niższe.
W przypadku tych modeli nadal otrzymujesz nieco więcej, niż płacąc bezpośrednio ich dostawcom. Dlatego ich miesięczne użycie w ramach planu jest niższe.
---
@@ -303,7 +408,7 @@ W przypadku tych modeli nadal otrzymujesz nieco więcej, niż płacąc bezpośre
Możesz również uzyskać dostęp do modeli Go za pośrednictwem następujących punktów końcowych API.
| Model | ID modelu | Punkt końcowy | Pakiet AI SDK |
| Model | ID modelu | Punkt końcowy | Pakiet AI SDK |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -312,11 +417,11 @@ Możesz również uzyskać dostęp do modeli Go za pośrednictwem następującyc
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -327,22 +432,18 @@ Możesz również uzyskać dostęp do modeli Go za pośrednictwem następującyc
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
[ID modelu](/docs/config/#models) w Twojej konfiguracji OpenCode
używa formatu `opencode-go/<model-id>`. Na przykład dla Kimi K3 należy użyć
`opencode-go/kimi-k3` w swojej konfiguracji.
[ID modelu](/docs/config/#models) w konfiguracji OpenCode
ma format `opencode-go/<model-id>`. Na przykład dla Kimi K3 należy użyć
`opencode-go/kimi-k3` w konfiguracji.
---
@@ -359,46 +460,43 @@ https://opencode.ai/zen/go/v1/models
## Prywatność
| Model | Trenowanie modelu | Retencja danych |
| ---------------------------- | ----------------- | --------------- |
| Grok 4.7 | Niewykorzystywane | 30 dni |
| Grok 4.6 | Niewykorzystywane | 30 dni |
| GPT 6 Luna | Niewykorzystywane | 30 dni |
| GPT 5.6 Luna | Niewykorzystywane | 30 dni |
| GLM-5.3-Flash | Niewykorzystywane | 0 dni |
| GLM-5.3 | Niewykorzystywane | 0 dni |
| GLM-5.2 | Niewykorzystywane | 0 dni |
| GLM-5.1 | Niewykorzystywane | 0 dni |
| Kimi K3 | Niewykorzystywane | 0 dni |
| Kimi K2.7 Code | Niewykorzystywane | 0 dni |
| Kimi K2.6 | Niewykorzystywane | 0 dni |
| LongCat-2.0 | Niewykorzystywane | 0 dni |
| MiMo-V2.6-Pro | Niewykorzystywane | 0 dni |
| MiMo-V2.6-Flash | Niewykorzystywane | 0 dni |
| MiMo-V2.5-Pro | Niewykorzystywane | 0 dni |
| MiMo-V2.5 | Niewykorzystywane | 0 dni |
| Qwen3.8 Max | Niewykorzystywane | 0 dni |
| Qwen3.8 Flash | Niewykorzystywane | 0 dni |
| Qwen3.7 Max | Niewykorzystywane | 0 dni |
| Qwen3.7 Plus | Niewykorzystywane | 0 dni |
| Qwen3.6 Plus | Niewykorzystywane | 0 dni |
| MiniMax M3 | Niewykorzystywane | 0 dni |
| MiniMax M2.7 | Niewykorzystywane | 0 dni |
| Muse Spark 1.3 Contributor | Tak | Nie ZDR |
| Muse Spark 1.2 Contributor | Tak | Nie ZDR |
| DeepSeek V4.1 Flash | Niewykorzystywane | 0 dni |
| DeepSeek V4 Pro | Niewykorzystywane | 0 dni |
| DeepSeek V4 Flash | Niewykorzystywane | 0 dni |
| DeepSeek V4 Flash Vision Exp | Niewykorzystywane | 0 dni |
| Hy4 preview | Niewykorzystywane | 0 dni |
| Hy3 | Niewykorzystywane | 0 dni |
| Space Bunny Free | Niewykorzystywane | 0 dni |
| LongCat 2.5 Preview Free | Niewykorzystywane | 0 dni |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Niewykorzystywane | 30 dni |
| Grok 4.6 | Niewykorzystywane | 30 dni |
| GPT 6 Luna | Niewykorzystywane | 30 dni |
| GPT 5.6 Luna | Niewykorzystywane | 30 dni |
| GLM-5.3-Flash | Niewykorzystywane | 0 dni |
| GLM-5.3 | Niewykorzystywane | 0 dni |
| GLM-5.2 | Niewykorzystywane | 0 dni |
| Kimi K3 | Niewykorzystywane | 0 dni |
| Kimi K2.7 Code | Niewykorzystywane | 0 dni |
| Kimi K2.6 | Niewykorzystywane | 0 dni |
| LongCat-2.0 | Niewykorzystywane | 0 dni |
| MiMo-V2.6-Pro | Niewykorzystywane | 0 dni |
| MiMo-V2.6-Flash | Niewykorzystywane | 0 dni |
| MiMo-V2.5-Pro | Niewykorzystywane | 0 dni |
| MiMo-V2.5 | Niewykorzystywane | 0 dni |
| Qwen3.8 Max | Niewykorzystywane | 0 dni |
| Qwen3.8 Flash | Niewykorzystywane | 0 dni |
| Qwen3.7 Plus | Niewykorzystywane | 0 dni |
| MiniMax M3 | Niewykorzystywane | 0 dni |
| MiniMax M2.7 | Niewykorzystywane | 0 dni |
| Muse Spark 1.3 Contributor | Tak | Nie ZDR |
| Muse Spark 1.2 Contributor | Tak | Nie ZDR |
| DeepSeek V4.1 Flash | Niewykorzystywane | 0 dni\* |
| DeepSeek V4 Pro | Niewykorzystywane | 0 dni\* |
| DeepSeek V4 Flash | Niewykorzystywane | 0 dni\* |
| DeepSeek V4 Flash Vision Exp | Niewykorzystywane | 0 dni\* |
| Hy4 preview | Niewykorzystywane | 0 dni |
| Hy3 | Niewykorzystywane | 0 dni |
| Space Bunny Free | Niewykorzystywane | 0 dni |
| LongCat 2.5 Preview Free | Niewykorzystywane | 0 dni |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Znacznie obniżone ceny tokenów w zamian za zgodę na wykorzystanie Twoich promptów i odpowiedzi do trenowania przyszłych modeli Meta. Dostępność jest ograniczona do regionów dozwolonych przez [Zasady korzystania w poszczególnych regionach geograficznych](https://ai.developer.meta.com/legal/geographic-use-policy) firmy Meta. [Dowiedz się więcej](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Znacznie obniżone ceny tokenów w zamian za zgodę na wykorzystanie Twoich promptów i odpowiedzi do trenowania przyszłych modeli Meta. Dostępność jest ograniczona do regionów dozwolonych przez [Zasady korzystania w poszczególnych regionach geograficznych](https://ai.developer.meta.com/legal/geographic-use-policy) firmy Meta. [Dowiedz się więcej](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** Umowa ZDR jest odnawiana co miesiąc. Obecna umowa obowiązuje do 30 września 2026 r.
- **Muse Spark 1.3 Contributor:** Znacznie obniżone ceny tokenów w zamian za zgodę na wykorzystanie Twoich promptów i odpowiedzi do trenowania przyszłych modeli Meta. Dostępność jest ograniczona do regionów dozwolonych przez [Zasady korzystania w poszczególnych regionach geograficznych] firmy Meta(https://ai.developer.meta.com/legal/geographic-use-policy). [Dowiedz się więcej](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Znacznie obniżone ceny tokenów w zamian za zgodę na wykorzystanie Twoich promptów i odpowiedzi do trenowania przyszłych modeli Meta. Dostępność jest ograniczona do regionów dozwolonych przez [Zasady korzystania w poszczególnych regionach geograficznych] firmy Meta(https://ai.developer.meta.com/legal/geographic-use-policy). [Dowiedz się więcej](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** Umowa ZDR jest odnawiana co miesiąc. Obecna umowa obowiązuje do 31 października 2026 r.
---
@@ -409,4 +507,4 @@ Stworzyliśmy OpenCode Go, aby:
1. Uczynić kodowanie z pomocą sztucznej inteligencji **dostępnym** dla większej liczby osób dzięki niskokosztowej subskrypcji.
2. Zapewnić **niezawodny** dostęp do najlepszych otwartych modeli do kodowania.
3. Wybierać modele, które są **przetestowane i sprawdzone w testach wydajności** do użytku przez agentów kodujących.
4. Zapewnić **brak ograniczeń (no lock-in)**, pozwalając na korzystanie z dowolnego innego dostawcy wraz z OpenCode.
4. Zapewnić **brak uzależnienia od dostawcy**, umożliwiając korzystanie z dowolnego innego dostawcy wraz z OpenCode.
packages/web/src/content/docs/pt-br/go.mdx
+288 -198
View File
@@ -1,29 +1,35 @@
---
title: Go
description: Assinatura de baixo custo para modelos abertos de programação.
description: Acesso confiável a modelos abertos de programação com dois níveis de uso.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
O OpenCode Go é uma assinatura de baixo custo de **US$ 10/mês** que oferece acesso confiável a modelos abertos de programação populares.
O OpenCode Go oferece acesso confiável a modelos abertos de programação populares, com dois planos mensais:
| Plano | Preço | Uso incluído |
| ---- | ----- | -------------- |
| **Go** | **$10/mês** | Acesso de menor custo aos modelos abaixo |
| **Go Plus** | **$40/mês** | Limites de uso mais altos para os modelos abaixo |
O Go funciona como qualquer outro provedor no OpenCode. Você assina o OpenCode Go e
obtém a sua chave de API. Ele é **totalmente opcional** e você não precisa usá-lo para
usar o OpenCode.
Ele foi projetado principalmente para usuários internacionais e oferece acesso global estável.
O serviço foi projetado principalmente para usuários internacionais e oferece acesso global estável.
---
## Contexto
Os modelos abertos ficaram muito bons. Eles agora alcançam um desempenho próximo aos
Os modelos abertos ficaram muito bons. Eles agora alcançam desempenho próximo aos
modelos proprietários para tarefas de programação. E como muitos provedores podem servi-los
de forma competitiva, eles geralmente são muito mais baratos.
No entanto, obter um acesso confiável e de baixa latência a eles pode ser difícil. Os provedores
No entanto, obter acesso confiável e de baixa latência a eles pode ser difícil. Os provedores
variam em qualidade e disponibilidade.
:::tip
@@ -34,12 +40,13 @@ Para resolver isso, fizemos algumas coisas:
1. Testamos um grupo selecionado de modelos abertos e conversamos com suas equipes sobre a
melhor forma de executá-los.
2. Em seguida, trabalhamos com alguns provedores para garantir que eles estivessem sendo servidos
2. Em seguida, trabalhamos com alguns provedores para garantir que fossem servidos
corretamente.
3. Por fim, avaliamos por benchmark a combinação de modelo/provedor e elaboramos
uma lista que nos sentimos confortáveis em recomendar.
3. Por fim, avaliamos por benchmark a combinação de modelo e provedor e elaboramos
uma lista que recomendamos com confiança.
O OpenCode Go lhe dá acesso a esses modelos por **US$ 10/mês**.
Tanto o Go quanto o Go Plus dão acesso a esses modelos; escolha o plano adequado
à frequência com que você os usa.
---
@@ -47,14 +54,14 @@ O OpenCode Go lhe dá acesso a esses modelos por **US$ 10/mês**.
O OpenCode Go funciona como qualquer outro provedor no OpenCode.
1. Você entra no **<a href={console}>OpenCode Zen</a>**, assina o Go e
copia a sua chave de API.
2. Você executa o comando `/connect` na TUI, seleciona `OpenCode Go` e cola
1. Entre no **<a href={console}>OpenCode Console</a>**, assine o Go ou o Go Plus e
copie a sua chave de API.
2. Execute o comando `/connect` na TUI, selecione `OpenCode Go` e cole
a sua chave de API.
3. Execute `/models` na TUI para ver a lista de modelos disponíveis através do Go.
:::note
Apenas um membro por workspace pode assinar o OpenCode Go.
Apenas um membro por workspace pode assinar o OpenCode Go ou o Go Plus.
:::
A lista atual de modelos inclui:
@@ -64,13 +71,13 @@ A lista atual de modelos inclui:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (por tempo limitado)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -81,9 +88,7 @@ A lista atual de modelos inclui:
- **Muse Spark 1.2 Contributor** ([regiões limitadas](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -91,7 +96,6 @@ A lista atual de modelos inclui:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (por tempo limitado)
- **LongCat 2.5 Preview Free** (por tempo limitado)
A lista de modelos pode mudar conforme testamos e adicionamos novos.
@@ -116,88 +120,143 @@ Seu cliente deve:
Além do OpenCode, os clientes a seguir foram validados para funcionar corretamente
com o OpenCode Go. No entanto, não garantimos que continuarão funcionando no futuro.
| Cliente | Suporte a sessões |
| ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | As builds que contêm o [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) enviam o header nas requisições principais e auxiliares do OpenCode. A correção foi incorporada após a v0.21.0; essa versão por si só não a inclui. |
| **Claude Code** | O Go reconhece seu header de sessão nativo. Não é necessário usar um wrapper para headers personalizados. |
| **Codex** | O Go reconhece seu header de sessão nativo. Algumas versões e configurações de proxy ainda o omitem; preserve o header de sessão ao encaminhar requisições. |
| **ZCode** | O Go reconhece seu header de sessão nativo. Nossa [solicitação de `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) continua aberta, mas não é mais necessário enviar especificamente esse header. |
| **Pi** | As builds atuais enviam informações de sessão para o OpenCode. Atualize instalações mais antigas. |
| **jcode** | Atualize para a versão **v0.81.6 ou posterior**, que inclui a [correção do header de sessão](https://github.com/1jehuang/jcode/issues/1167). |
| **Kilo Code CLI** | As builds que contêm o [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) restauram os headers de sessão do OpenCode. Essa correção abrange a CLI, não a extensão do VS Code. Consulte a [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
| Cliente | Suporte a sessões |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | As builds que contêm [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) enviam o header nas requisições principais e auxiliares do OpenCode. A correção foi incorporada após a v0.21.0; essa versão por si só não a inclui. |
| **Claude Code** | O Go reconhece seu header de sessão nativo. Não é necessário usar um wrapper para headers personalizados. |
| **Codex** | O Go reconhece seu header de sessão nativo. Algumas versões e configurações de proxy ainda o omitem; preserve o header de sessão ao encaminhar requisições. |
| **ZCode** | O Go reconhece seu header de sessão nativo. Nossa [solicitação de `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) continua aberta, mas não é mais necessário enviar especificamente esse header. |
| **Pi** | As builds atuais enviam informações de sessão para o OpenCode. Atualize instalações mais antigas. |
| **jcode** | Atualize para a versão **v0.81.6 ou posterior**, que inclui a [correção do header de sessão](https://github.com/1jehuang/jcode/issues/1167). |
| **Kilo Code CLI** | As builds que contêm [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) restauram os headers de sessão do OpenCode. Essa correção abrange a CLI, não a extensão do VS Code. Consulte a [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
### Clientes com problemas conhecidos
Esses clientes não têm suporte a sessões ou apresentam suporte incompleto nas versões que
investigamos. Os relatórios vinculados acompanham correções e soluções alternativas.
| Cliente | Status e acompanhamento |
| ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Cliente | Status e acompanhamento |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | As informações de sessão chegam por alguns caminhos de modelos, mas não por outros. Reconhecemos seu header nativo; ainda é necessário enviá-lo por todos os adaptadores. [Discussão #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
| **GitHub Copilot Chat** | O suporte automático ao header de sessão foi solicitado na [issue #334186 do VS Code](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | O suporte automático ao header de sessão foi solicitado na [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | A [issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) tem uma correção proposta no [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), que ainda não foi incorporada. |
| **GitHub Copilot Chat** | O suporte automático ao header de sessão foi solicitado na [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | O suporte automático ao header de sessão foi solicitado na [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | A [issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) tem uma correção proposta no [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), que ainda não foi incorporada. |
## Limites de uso
Os limites de uso são definidos como valores mensais em dólares. A tabela abaixo mostra o limite mensal e os custos de tokens de cada modelo.
Os limites de uso são definidos como valores mensais em dólares. A tabela abaixo mostra o
limite mensal de cada plano e os custos de tokens de cada modelo. Os preços dos tokens são
os mesmos no Go e no Go Plus.
Cada modelo tem os seguintes limites de uso: 5 horas — 20% do limite mensal; semanal — 50%; e mensal — 100%.
Cada modelo tem os seguintes limites de uso: 5 horas — 20% do limite mensal;
semanal — 50%; e mensal — 100%.
Por exemplo, se um modelo tiver um limite mensal de $60, você poderá gastar até:
Por exemplo, se um modelo tiver um limite mensal de $60 no Go e de $120
no Go Plus, você poderá gastar até:
- **Limite de 5 horas** — $12 de uso
- **Limite semanal** — $30 de uso
- **Limite mensal** — $60 de uso
- **Limite de 5 horas** — $12 no Go ou $24 no Go Plus
- **Limite semanal** — $30 no Go ou $60 no Go Plus
- **Limite mensal** — $60 no Go ou $120 no Go Plus
Considerando todos os modelos, o Go tem limites de $12 em 5 horas, $30 por semana e $60 por mês;
o Go Plus tem limites de $48 em 5 horas, $120 por semana e $240 por mês. O limite mensal
de cada modelo abaixo determina como o uso é contabilizado nesses
limites.
Os preços de tokens são indicados por 1M tokens.
| Modelo | Entrada | Saída | Leitura em cache | Escrita em cache | Limite mensal |
| --------------------------------------- | ------- | ------ | ---------------- | ---------------- | ---------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Ilimitado**<br /><small>por tempo limitado</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Ilimitado**<br /><small>por tempo limitado</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modelo | Entrada | Saída | Leitura em cache | Escrita em cache | Limite mensal |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Grátis | Grátis | Grátis | - | **Ilimitado**<br /><small>por tempo limitado</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Grátis | Grátis | Grátis | - | **Ilimitado**<br /><small>por tempo limitado</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Modelo | Entrada | Saída | Leitura em cache | Escrita em cache | Limite mensal |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Grátis | Grátis | Grátis | - | **Ilimitado**<br /><small>por tempo limitado</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Grátis | Grátis | Grátis | - | **Ilimitado**<br /><small>por tempo limitado</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Gratuito por tempo limitado.
@@ -209,73 +268,111 @@ Os preços de tokens são indicados por 1M tokens.
### Requisições estimadas
A tabela abaixo apresenta uma quantidade estimada de requisições com base nos padrões típicos de uso do Go:
As tabelas abaixo estimam a quantidade de requisições com base nos padrões típicos de uso do Go. As estimativas do Go
Plus são dimensionadas de acordo com o limite de uso mais alto de cada modelo.
| Model | requisições por 5 horas | requisições por semana | requisições por mês |
| ---------------------------- | ----------------------- | ---------------------- | ------------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ilimitado | Ilimitado | Ilimitado |
| LongCat 2.5 Preview Free | Ilimitado | Ilimitado | Ilimitado |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Modelo | Requisições por 5 horas | Requisições por semana | Requisições por mês |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Ilimitado | Ilimitado | Ilimitado |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Ilimitado | Ilimitado | Ilimitado |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Modelo | Requisições por 5 horas | Requisições por semana | Requisições por mês |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Ilimitado | Ilimitado | Ilimitado |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Ilimitado | Ilimitado | Ilimitado |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
As estimativas usam as seguintes quantidades de tokens por requisição; o uso real varia.
- Grok 4.7/4.6 — 390 tokens de entrada, 32.500 em cache, 120 tokens de saída por requisição
- GLM-5.3-Flash — 1.000 tokens de entrada, 55.000 em cache, 200 tokens de saída por requisição
- GLM-5.3/5.2/5.1 — 700 tokens de entrada, 52.000 em cache, 150 tokens de saída por requisição
- GPT 6 Luna — 1.000 tokens de entrada, 50.000 em cache, 220 tokens de saída por requisição
- GPT 5.6 Luna — 1.000 tokens de entrada, 50.000 em cache, 220 tokens de saída por requisição
- Kimi K3 — 1.050 tokens de entrada, 76.500 em cache, 300 tokens de saída por requisição
- Kimi K2.7/K2.6 — 870 tokens de entrada, 55.000 em cache, 200 tokens de saída por requisição
- LongCat-2.0 — 920 tokens de entrada, 88.900 em cache, 200 tokens de saída por requisição
- DeepSeek V4.1 Flash — 410 tokens de entrada, 71.300 em cache, 310 tokens de saída por requisição
- DeepSeek V4 Pro — 750 tokens de entrada, 82.000 em cache, 290 tokens de saída por requisição
- DeepSeek V4 Flash — 410 tokens de entrada, 71.300 em cache, 310 tokens de saída por requisição
- DeepSeek V4 Flash Vision Exp — 410 tokens de entrada, 71.300 em cache, 310 tokens de saída por requisição
- MiniMax M3 — 510 tokens de entrada, 56.000 em cache, 190 tokens de saída por requisição
- MiniMax M2.7 — 300 tokens de entrada, 55.000 em cache, 125 tokens de saída por requisição
- Muse Spark 1.3 Contributor — 620 tokens de entrada, 71.400 em cache, 300 tokens de saída por requisição
- Muse Spark 1.2 Contributor — 620 tokens de entrada, 71.400 em cache, 300 tokens de saída por requisição
- Qwen3.8 Max — 420 tokens de entrada, 66.000 em cache, 200 tokens de saída por requisição
- Qwen3.8 Flash — 600 tokens de entrada, 58.000 em cache, 200 tokens de saída por requisição
- Qwen3.7 Max — 420 tokens de entrada, 66.000 em cache, 200 tokens de saída por requisição
- Qwen3.7 Plus — 500 tokens de entrada, 57.000 em cache, 190 tokens de saída por requisição
- Qwen3.6 Plus — 500 tokens de entrada, 57.000 em cache, 190 tokens de saída por requisição
- Hy4 preview — 830 tokens de entrada, 71.500 em cache, 295 tokens de saída por requisição
- Hy3 — 830 tokens de entrada, 71.500 em cache, 295 tokens de saída por requisição
- MiMo-V2.6-Flash — 830 tokens de entrada, 71.500 em cache, 295 tokens de saída por requisição
- MiMo-V2.6-Pro — 790 tokens de entrada, 86.000 em cache, 305 tokens de saída por requisição
- MiMo-V2.5 — 830 tokens de entrada, 71.500 em cache, 295 tokens de saída por requisição
- MiMo-V2.5-Pro — 790 tokens de entrada, 86.000 em cache, 305 tokens de saída por requisição
- Grok 4.7/4.6 — 390 tokens de entrada, 32,500 em cache, 120 tokens de saída por requisição
- GLM-5.3-Flash — 1,000 tokens de entrada, 55,000 em cache, 200 tokens de saída por requisição
- GLM-5.3/5.2 — 700 tokens de entrada, 52,000 em cache, 150 tokens de saída por requisição
- GPT 6 Luna — 1,000 tokens de entrada, 50,000 em cache, 220 tokens de saída por requisição
- GPT 5.6 Luna — 1,000 tokens de entrada, 50,000 em cache, 220 tokens de saída por requisição
- Kimi K3 — 1,050 tokens de entrada, 76,500 em cache, 300 tokens de saída por requisição
- Kimi K2.7/K2.6 — 870 tokens de entrada, 55,000 em cache, 200 tokens de saída por requisição
- LongCat-2.0 — 920 tokens de entrada, 88,900 em cache, 200 tokens de saída por requisição
- DeepSeek V4.1 Flash — 410 tokens de entrada, 71,300 em cache, 310 tokens de saída por requisição
- DeepSeek V4 Pro — 750 tokens de entrada, 82,000 em cache, 290 tokens de saída por requisição
- DeepSeek V4 Flash — 410 tokens de entrada, 71,300 em cache, 310 tokens de saída por requisição
- DeepSeek V4 Flash Vision Exp — 410 tokens de entrada, 71,300 em cache, 310 tokens de saída por requisição
- MiniMax M3 — 510 tokens de entrada, 56,000 em cache, 190 tokens de saída por requisição
- MiniMax M2.7 — 300 tokens de entrada, 55,000 em cache, 125 tokens de saída por requisição
- Muse Spark 1.3 Contributor — 620 tokens de entrada, 71,400 em cache, 300 tokens de saída por requisição
- Muse Spark 1.2 Contributor — 620 tokens de entrada, 71,400 em cache, 300 tokens de saída por requisição
- MiMo-V2.6-Flash — 830 tokens de entrada, 71,500 em cache, 295 tokens de saída por requisição
- MiMo-V2.6-Pro — 790 tokens de entrada, 86,000 em cache, 305 tokens de saída por requisição
- MiMo-V2.5 — 830 tokens de entrada, 71,500 em cache, 295 tokens de saída por requisição
- MiMo-V2.5-Pro — 790 tokens de entrada, 86,000 em cache, 305 tokens de saída por requisição
- Qwen3.8 Max — 420 tokens de entrada, 66,000 em cache, 200 tokens de saída por requisição
- Qwen3.8 Flash — 600 tokens de entrada, 58,000 em cache, 200 tokens de saída por requisição
- Qwen3.7 Plus — 500 tokens de entrada, 57,000 em cache, 190 tokens de saída por requisição
- Hy4 preview — 830 tokens de entrada, 71,500 em cache, 295 tokens de saída por requisição
- Hy3 — 830 tokens de entrada, 71,500 em cache, 295 tokens de saída por requisição
Você pode acompanhar o seu uso atual no **<a href={console}>console</a>**.
@@ -289,21 +386,21 @@ Os limites de uso podem mudar à medida que aprendemos com o uso inicial e o fee
### Uso além dos limites
Se você também tiver créditos no seu saldo do Zen, pode habilitar a opção **Use balance**
no console. Quando habilitada, o Go usará o seu saldo do Zen como alternativa
após você atingir os seus limites de uso em vez de bloquear as requisições.
Se você também tiver créditos no saldo do Zen, pode habilitar a opção **Usar saldo**
no console. Quando habilitada, o Go usará o saldo do Zen como alternativa
após você atingir os limites de uso, em vez de bloquear as requisições.
---
### Por que alguns modelos têm um uso menor
Com o Go, você paga $10/mês, e o uso mensal incluído varia conforme o modelo.
Com o Go, o uso mensal incluído varia conforme o modelo.
Para a maioria dos modelos, conseguimos fazer isso por meio de descontos por volume e capacidade reservada de GPU. Repassamos essa economia a você na forma de um uso mensal maior.
Para alguns modelos, ainda não tivemos a oportunidade de negociar um desconto ou hospedá-los a um custo menor, seja porque o modelo é novo ou porque o preço público já tem desconto.
Para esses modelos, você ainda recebe um pouco mais do que receberia se pagasse diretamente aos provedores dos modelos; por isso, o uso mensal incluído com eles é menor.
Para esses modelos, você ainda recebe um pouco mais do que receberia se pagasse diretamente aos provedores dos modelos; por isso, o uso mensal incluído é menor.
---
@@ -311,7 +408,7 @@ Para esses modelos, você ainda recebe um pouco mais do que receberia se pagasse
Você também pode acessar os modelos do Go através dos seguintes endpoints de API.
| Modelo | ID do Modelo | Endpoint | Pacote do AI SDK |
| Modelo | ID do modelo | Endpoint | Pacote do AI SDK |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -320,11 +417,11 @@ Você também pode acessar os modelos do Go através dos seguintes endpoints de
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -335,22 +432,18 @@ Você também pode acessar os modelos do Go através dos seguintes endpoints de
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
O [ID do modelo](/docs/config/#models) na sua configuração do OpenCode
O [ID do modelo](/docs/config/#models) na configuração do OpenCode
usa o formato `opencode-go/<model-id>`. Por exemplo, para o Kimi K3, você usaria
`opencode-go/kimi-k3` na sua configuração.
`opencode-go/kimi-k3` na configuração.
---
@@ -367,46 +460,43 @@ https://opencode.ai/zen/go/v1/models
## Privacidade
| Modelo | Treinamento de modelos | Retenção de dados |
| ---------------------------- | ---------------------- | ----------------- |
| Grok 4.7 | Não usado | 30 dias |
| Grok 4.6 | Não usado | 30 dias |
| GPT 6 Luna | Não usado | 30 dias |
| GPT 5.6 Luna | Não usado | 30 dias |
| GLM-5.3-Flash | Não usado | 0 dias |
| GLM-5.3 | Não usado | 0 dias |
| GLM-5.2 | Não usado | 0 dias |
| GLM-5.1 | Não usado | 0 dias |
| Kimi K3 | Não usado | 0 dias |
| Kimi K2.7 Code | Não usado | 0 dias |
| Kimi K2.6 | Não usado | 0 dias |
| LongCat-2.0 | Não usado | 0 dias |
| MiMo-V2.6-Pro | Não usado | 0 dias |
| MiMo-V2.6-Flash | Não usado | 0 dias |
| MiMo-V2.5-Pro | Não usado | 0 dias |
| MiMo-V2.5 | Não usado | 0 dias |
| Qwen3.8 Max | Não usado | 0 dias |
| Qwen3.8 Flash | Não usado | 0 dias |
| Qwen3.7 Max | Não usado | 0 dias |
| Qwen3.7 Plus | Não usado | 0 dias |
| Qwen3.6 Plus | Não usado | 0 dias |
| MiniMax M3 | Não usado | 0 dias |
| MiniMax M2.7 | Não usado | 0 dias |
| Muse Spark 1.3 Contributor | Sim | Não é ZDR |
| Muse Spark 1.2 Contributor | Sim | Não é ZDR |
| DeepSeek V4.1 Flash | Não usado | 0 dias |
| DeepSeek V4 Pro | Não usado | 0 dias |
| DeepSeek V4 Flash | Não usado | 0 dias |
| DeepSeek V4 Flash Vision Exp | Não usado | 0 dias |
| Hy4 preview | Não usado | 0 dias |
| Hy3 | Não usado | 0 dias |
| Space Bunny Free | Não usado | 0 dias |
| LongCat 2.5 Preview Free | Não usado | 0 dias |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Não usado | 30 dias |
| Grok 4.6 | Não usado | 30 dias |
| GPT 6 Luna | Não usado | 30 dias |
| GPT 5.6 Luna | Não usado | 30 dias |
| GLM-5.3-Flash | Não usado | 0 dias |
| GLM-5.3 | Não usado | 0 dias |
| GLM-5.2 | Não usado | 0 dias |
| Kimi K3 | Não usado | 0 dias |
| Kimi K2.7 Code | Não usado | 0 dias |
| Kimi K2.6 | Não usado | 0 dias |
| LongCat-2.0 | Não usado | 0 dias |
| MiMo-V2.6-Pro | Não usado | 0 dias |
| MiMo-V2.6-Flash | Não usado | 0 dias |
| MiMo-V2.5-Pro | Não usado | 0 dias |
| MiMo-V2.5 | Não usado | 0 dias |
| Qwen3.8 Max | Não usado | 0 dias |
| Qwen3.8 Flash | Não usado | 0 dias |
| Qwen3.7 Plus | Não usado | 0 dias |
| MiniMax M3 | Não usado | 0 dias |
| MiniMax M2.7 | Não usado | 0 dias |
| Muse Spark 1.3 Contributor | Sim | Não é ZDR |
| Muse Spark 1.2 Contributor | Sim | Não é ZDR |
| DeepSeek V4.1 Flash | Não usado | 0 dias\* |
| DeepSeek V4 Pro | Não usado | 0 dias\* |
| DeepSeek V4 Flash | Não usado | 0 dias\* |
| DeepSeek V4 Flash Vision Exp | Não usado | 0 dias\* |
| Hy4 preview | Não usado | 0 dias |
| Hy3 | Não usado | 0 dias |
| Space Bunny Free | Não usado | 0 dias |
| LongCat 2.5 Preview Free | Não usado | 0 dias |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Preços de tokens com grandes descontos em troca da permissão para usar seus prompts e respostas geradas para treinar futuros modelos da Meta. A disponibilidade é limitada às regiões permitidas pela [Política de Uso Geográfico](https://ai.developer.meta.com/legal/geographic-use-policy) da Meta. [Saiba mais](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Preços de tokens com grandes descontos em troca da permissão para usar seus prompts e respostas geradas para treinar futuros modelos da Meta. A disponibilidade é limitada às regiões permitidas pela [Política de Uso Geográfico](https://ai.developer.meta.com/legal/geographic-use-policy) da Meta. [Saiba mais](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** O acordo de ZDR é renovado mensalmente. O acordo atual é válido até 30 de setembro de 2026.
- **Muse Spark 1.3 Contributor:** Preços de tokens com grandes descontos em troca da permissão para usar seus prompts e respostas geradas para treinar futuros modelos da Meta. A disponibilidade é limitada às regiões permitidas pela [Política de Uso Geográfico] da Meta(https://ai.developer.meta.com/legal/geographic-use-policy). [Saiba mais](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Preços de tokens com grandes descontos em troca da permissão para usar seus prompts e respostas geradas para treinar futuros modelos da Meta. A disponibilidade é limitada às regiões permitidas pela [Política de Uso Geográfico] da Meta(https://ai.developer.meta.com/legal/geographic-use-policy). [Saiba mais](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** O acordo de ZDR é renovado mensalmente. O acordo atual é válido até 31 de outubro de 2026.
---
@@ -416,5 +506,5 @@ Criamos o OpenCode Go para:
1. Tornar a programação com IA **acessível** a mais pessoas com uma assinatura de baixo custo.
2. Fornecer acesso **confiável** aos melhores modelos abertos de programação.
3. Ter modelos sob curadoria que são **testados e avaliados (benchmarked)** para o uso por agentes de programação.
4. Não ter **nenhuma restrição de fornecedor (lock-in)**, permitindo que você use qualquer outro provedor com o OpenCode também.
3. Selecionar modelos **testados e avaliados por benchmark** para uso por agentes de programação.
4. Evitar **dependência de fornecedor**, permitindo que você também use qualquer outro provedor com o OpenCode.
packages/web/src/content/docs/ru/go.mdx
+303 -213
View File
@@ -1,60 +1,67 @@
---
title: Go
description: Недорогая подписка на открытые модели для программирования.
description: Надёжный доступ к открытым моделям для программирования с двумя уровнями использования.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go — это недорогая подписка за **$10 в месяц**, которая предоставляет надежный доступ к популярным открытым моделям для программирования.
OpenCode Go предоставляет надёжный доступ к популярным открытым моделям для программирования по двум месячным тарифам:
Go работает так же, как и любой другой провайдер в OpenCode. Вы оформляете подписку на OpenCode Go и
получаете свой API-ключ. Использование Go **абсолютно необязательно**, и вам не нужно использовать его, чтобы
пользоваться OpenCode.
| Тариф | Цена | Включённый объём использования |
| ---- | ----- | -------------- |
| **Go** | **$10/месяц** | Более доступный доступ к перечисленным ниже моделям |
| **Go Plus** | **$40/месяц** | Более высокие лимиты для перечисленных ниже моделей |
Она предназначена прежде всего для международных пользователей и обеспечивает стабильный доступ по всему миру.
Go работает так же, как любой другой провайдер в OpenCode. Вы подписываетесь на OpenCode Go и
получаете API-ключ. Это **совершенно необязательно**: OpenCode можно использовать
и без Go.
Сервис предназначен прежде всего для международных пользователей и обеспечивает стабильный доступ по всему миру.
---
## Предпосылки
Открытые модели стали действительно хороши. Сейчас они достигают производительности, близкой к
проприетарным моделям для задач программирования. И поскольку многие провайдеры могут предоставлять к ним доступ
на конкурентных условиях, они, как правило, обходятся гораздо дешевле.
Открытые модели стали действительно хороши. В задачах программирования их производительность уже близка к
проприетарным моделям. А поскольку многие провайдеры могут предоставлять их
на конкурентных условиях, обычно они гораздо дешевле.
Однако получить к ним надежный доступ с низкой задержкой может быть непросто. Провайдеры
Однако получить к ним надёжный доступ с низкой задержкой бывает непросто. Провайдеры
различаются по качеству и доступности.
:::tip
Мы протестировали выбранную группу моделей и провайдеров, которые хорошо работают с OpenCode.
Мы протестировали отобранную группу моделей и провайдеров, которые хорошо работают с OpenCode.
:::
Чтобы исправить это, мы сделали пару вещей:
Чтобы решить эту проблему, мы сделали следующее:
1. Мы протестировали выбранную группу открытых моделей и поговорили с их командами о том, как
1. Мы протестировали отобранную группу открытых моделей и обсудили с их командами, как
лучше всего их запускать.
2. Затем мы поработали с несколькими провайдерами, чтобы убедиться, что они предоставляются
2. Затем мы поработали с несколькими провайдерами, чтобы убедиться, что модели предоставляются
корректно.
3. Наконец, мы провели бенчмаркинг комбинаций модель/провайдер и составили
список, который мы смело можем рекомендовать.
3. Наконец, мы сравнили комбинации моделей и провайдеров и составили
список, который можем уверенно рекомендовать.
OpenCode Go дает вам доступ к этим моделям за **$10 в месяц**.
И Go, и Go Plus предоставляют доступ к этим моделям; выберите тариф в соответствии
с необходимым объёмом использования.
---
## Как это работает
OpenCode Go работает так же, как и любой другой провайдер в OpenCode.
OpenCode Go работает так же, как любой другой провайдер в OpenCode.
1. Вы входите в **<a href={console}>OpenCode Zen</a>**, подписываетесь на Go и
копируете свой API-ключ.
2. Вы выполняете команду `/connect` в TUI, выбираете `OpenCode Go` и вставляете
свой API-ключ.
3. Запустите `/models` в TUI, чтобы увидеть список моделей, доступных через Go.
1. Войдите в **<a href={console}>OpenCode Console</a>**, подпишитесь на Go или Go Plus и
скопируйте API-ключ.
2. Выполните команду `/connect` в TUI, выберите `OpenCode Go` и вставьте
API-ключ.
3. Выполните `/models` в TUI, чтобы увидеть список моделей, доступных через Go.
:::note
Только один участник рабочего пространства может подписаться на OpenCode Go.
Только один участник рабочего пространства может подписаться на OpenCode Go или Go Plus.
:::
Текущий список моделей включает:
@@ -64,13 +71,13 @@ OpenCode Go работает так же, как и любой другой пр
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (ограниченное время)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -81,9 +88,7 @@ OpenCode Go работает так же, как и любой другой пр
- **Muse Spark 1.2 Contributor** ([доступно в отдельных регионах](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -91,167 +96,261 @@ OpenCode Go работает так же, как и любой другой пр
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (ограниченное время)
- **LongCat 2.5 Preview Free** (ограниченное время)
Список моделей может меняться по мере того, как мы тестируем и добавляем новые.
Список моделей может меняться по мере тестирования и добавления новых.
---
## Где можно использовать OpenCode Go?
OpenCode Go предназначен для [OpenCode](https://opencode.ai) и других агентов для программирования,
OpenCode Go предназначен для [OpenCode](https://opencode.ai) и других агентов программирования,
которые отправляют запросы схожих типов. Трафик отслеживается для выявления злоупотреблений,
ухудшающих работу сервиса для других пользователей.
Ваш клиент должен:
1. Отправлять трафик, типичный для агента программирования.
2. Идентифицировать себя с помощью собственного user agent, например `my-coding-agent/1.0`, а не
универсального названия SDK или HTTP-библиотеки.
3. Отправлять стабильный идентификатор сессии в заголовке `x-opencode-session` для каждого диалога, чтобы мы могли оптимизировать маршрутизацию и
2. Идентифицировать себя собственным user agent, например `my-coding-agent/1.0`, а не
универсальным названием SDK или HTTP-библиотеки.
3. Отправлять стабильный идентификатор сессии в `x-opencode-session` для каждого диалога, чтобы мы могли оптимизировать маршрутизацию и
кеширование промптов.
### Проверенные клиенты
Помимо OpenCode, корректная работа с OpenCode Go подтверждена для следующих клиентов.
Однако мы не гарантируем, что они продолжат работать в будущем.
Помимо OpenCode, корректная работа следующих клиентов была проверена
с OpenCode Go. Однако мы не гарантируем, что они продолжат работать в будущем.
| Клиент | Поддержка сессий |
| ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | Сборки, содержащие [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864), отправляют заголовок в основных и вспомогательных запросах OpenCode. Исправление было объединено после v0.21.0; само это издание его не содержит. |
| **Claude Code** | Go распознает его нативный заголовок сессии. Обертка для добавления пользовательского заголовка не требуется. |
| **Codex** | Go распознает его нативный заголовок сессии. Некоторые версии и конфигурации прокси по-прежнему его не передают; сохраняйте заголовок сессии при пересылке запросов. |
| **ZCode** | Go распознает его нативный заголовок сессии. Наш [запрос на `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) остается открытым, но отправлять именно этот заголовок больше не требуется. |
| **Pi** | Текущие сборки отправляют информацию о сессии для OpenCode. Обновите более старые установки. |
| **jcode** | Обновитесь до версии **v0.81.6 или новее**, которая содержит [исправление заголовка сессии](https://github.com/1jehuang/jcode/issues/1167). |
| **Kilo Code CLI** | Сборки, содержащие [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752), восстанавливают заголовки сессии OpenCode. Это исправление относится к CLI, но не к расширению VS Code. См. [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
| Клиент | Поддержка сессий |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | Сборки с [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) отправляют заголовок в основных и вспомогательных запросах OpenCode. Исправление объединено после v0.21.0; сам этот выпуск его не содержит. |
| **Claude Code** | Go распознаёт его собственный заголовок сессии. Обёртка для пользовательского заголовка не нужна. |
| **Codex** | Go распознаёт его собственный заголовок сессии. Некоторые версии и настройки прокси всё ещё его пропускают; сохраняйте заголовок при пересылке запросов. |
| **ZCode** | Go распознаёт его собственный заголовок сессии. Наш [запрос на `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) остаётся открытым, но отправлять именно этот заголовок больше не требуется. |
| **Pi** | Текущие сборки отправляют информацию о сессии для OpenCode. Обновите старые установки. |
| **jcode** | Обновитесь до **v0.81.6 или новее**, где есть [исправление заголовка сессии](https://github.com/1jehuang/jcode/issues/1167). |
| **Kilo Code CLI** | Сборки с [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) восстанавливают заголовки сессии OpenCode. Исправление относится к CLI, но не к расширению VS Code. См. [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
### Клиенты с известными проблемами
В исследованных нами версиях этих клиентов поддержка сессий отсутствует или реализована
не полностью. По ссылкам можно отслеживать исправления и обходные решения.
| Клиент | Статус и отслеживание |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **DeepSeek Harness** | Информация о сессии поступает для некоторых путей моделей, но отсутствует для других. Мы распознаем его нативный заголовок; остается обеспечить его отправку через все адаптеры. [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
| **GitHub Copilot Chat** | Запрос на автоматическую поддержку заголовка сессии создан в [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | Запрос на автоматическую поддержку заголовка сессии создан в [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | Для [issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) предложено исправление в [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), который еще не объединен. |
| Клиент | Статус и отслеживание |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | Информация о сессии поступает для одних путей моделей, но отсутствует для других. Мы распознаём собственный заголовок клиента; осталось обеспечить его отправку через все адаптеры. [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
| **GitHub Copilot Chat** | Автоматическая поддержка заголовка сессии запрошена в [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
| **Kimi Code** | Автоматическая поддержка заголовка сессии запрошена в [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
| **MiMo Code** | Для [issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) предложено исправление в [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), которое ещё не объединено. |
## Лимиты использования
Лимиты использования определяются как месячные суммы в долларах. В таблице ниже указаны месячный лимит и стоимость токенов для каждой модели.
Лимиты использования определяются как месячные суммы в долларах. В таблице ниже указаны
месячные лимиты каждого тарифа и стоимость токенов для каждой модели. Цены на токены
одинаковы для Go и Go Plus.
Для каждой модели действуют следующие лимиты использования: на 5 часов — 20% месячного лимита; на неделю — 50%; на месяц — 100%.
Для каждой модели действуют следующие лимиты: за 5 часов — 20% месячного лимита;
за неделю — 50%; за месяц — 100%.
Например, если месячный лимит модели составляет $60, вы можете потратить до:
Например, если месячный лимит модели составляет $60 на Go и $120
на Go Plus, можно потратить до:
- **Лимит на 5 часов** — использование на сумму $12
- **Недельный лимит** — использование на сумму $30
- **Месячный лимит** — использование на сумму $60
- **Лимит за 5 часов** — $12 на Go или $24 на Go Plus
- **Недельный лимит** — $30 на Go или $60 на Go Plus
- **Месячный лимит** — $60 на Go или $120 на Go Plus
Для всех моделей Go предоставляет лимиты $12 за 5 часов, $30 за неделю и $60 за месяц;
Go Plus — $48 за 5 часов, $120 за неделю и $240 за месяц. Указанный ниже
месячный лимит каждой модели определяет, как её использование учитывается в этих
лимитах.
Цены на токены указаны за 1M токенов.
| Model | Input | Output | Cached Read | Cached Write | Месячный лимит |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Без ограничений**<br /><small>ограниченное время</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Без ограничений**<br /><small>ограниченное время</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Модель | Ввод | Вывод | Чтение кеша | Запись кеша | Месячный лимит |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Бесплатно | Бесплатно | Бесплатно | - | **Без ограничений**<br /><small>ограниченное время</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Бесплатно | Бесплатно | Бесплатно | - | **Без ограничений**<br /><small>ограниченное время</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Модель | Ввод | Вывод | Чтение кеша | Запись кеша | Месячный лимит |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Бесплатно | Бесплатно | Бесплатно | - | **Без ограничений**<br /><small>ограниченное время</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Бесплатно | Бесплатно | Бесплатно | - | **Без ограничений**<br /><small>ограниченное время</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Бесплатно в течение ограниченного времени.
**LongCat 2.5 Preview Free:** Бесплатно в течение ограниченного времени.
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Часы Peak с понедельника по пятницу: 01:00-04:00 и 06:00-10:00 UTC; все остальные часы, включая выходные, относятся к Off-Peak. [Подробнее](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Часы Peak: 01:00-04:00 and 06:00-10:00 UTC, с понедельника по пятницу; все остальные часы, включая выходные, относятся к Off-Peak. [Подробнее](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** Изображения преобразуются в токены с учётом их размеров и оплачиваются как входные токены вместе с текстовыми токенами. [Подробнее](https://api-docs.deepseek.com/quick_start/pricing/).
### Примерное число запросов
В таблице ниже приведено примерное число запросов на основе типичных сценариев использования Go:
В таблицах ниже приведено примерное число запросов для типичных сценариев использования Go. Оценки для Go
Plus увеличены в соответствии с более высоким лимитом каждой модели.
| Model | запросов за 5 часов | запросов в неделю | запросов в месяц |
| ---------------------------- | ------------------- | ----------------- | ---------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Без ограничений | Без ограничений | Без ограничений |
| LongCat 2.5 Preview Free | Без ограничений | Без ограничений | Без ограничений |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Модель | Запросов за 5 часов | Запросов в неделю | Запросов в месяц |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Без ограничений | Без ограничений | Без ограничений |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Без ограничений | Без ограничений | Без ограничений |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| Модель | Запросов за 5 часов | Запросов в неделю | Запросов в месяц |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Без ограничений | Без ограничений | Без ограничений |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Без ограничений | Без ограничений | Без ограничений |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
В оценках используются следующие количества токенов на запрос; фактическое использование может отличаться.
- Grok 4.7/4.6 — 390 входных, 32,500 кешированных, 120 выходных токенов на запрос
- GLM-5.3-Flash — 1,000 входных, 55,000 кешированных, 200 выходных токенов на запрос
- GLM-5.3/5.2/5.1 — 700 входных, 52,000 кешированных, 150 выходных токенов на запрос
- GLM-5.3/5.2 — 700 входных, 52,000 кешированных, 150 выходных токенов на запрос
- GPT 6 Luna — 1,000 входных, 50,000 кешированных, 220 выходных токенов на запрос
- GPT 5.6 Luna — 1,000 входных, 50,000 кешированных, 220 выходных токенов на запрос
- Kimi K3 — 1,050 входных, 76,500 кешированных, 300 выходных токенов на запрос
@@ -265,53 +364,51 @@ OpenCode Go предназначен для [OpenCode](https://opencode.ai) и
- MiniMax M2.7 — 300 входных, 55,000 кешированных, 125 выходных токенов на запрос
- Muse Spark 1.3 Contributor — 620 входных, 71,400 кешированных, 300 выходных токенов на запрос
- Muse Spark 1.2 Contributor — 620 входных, 71,400 кешированных, 300 выходных токенов на запрос
- Qwen3.8 Max — 420 входных, 66,000 кешированных, 200 выходных токенов на запрос
- Qwen3.8 Flash — 600 входных, 58,000 кешированных, 200 выходных токенов на запрос
- Qwen3.7 Max — 420 входных, 66,000 кешированных, 200 выходных токенов на запрос
- Qwen3.7 Plus — 500 входных, 57,000 кешированных, 190 выходных токенов на запрос
- Qwen3.6 Plus — 500 входных, 57,000 кешированных, 190 выходных токенов на запрос
- Hy4 preview — 830 входных, 71,500 кешированных, 295 выходных токенов на запрос
- Hy3 — 830 входных, 71,500 кешированных, 295 выходных токенов на запрос
- MiMo-V2.6-Flash — 830 входных, 71,500 кешированных, 295 выходных токенов на запрос
- MiMo-V2.6-Pro — 790 входных, 86,000 кешированных, 305 выходных токенов на запрос
- MiMo-V2.5 — 830 входных, 71,500 кешированных, 295 выходных токенов на запрос
- MiMo-V2.5-Pro — 790 входных, 86,000 кешированных, 305 выходных токенов на запрос
- Qwen3.8 Max — 420 входных, 66,000 кешированных, 200 выходных токенов на запрос
- Qwen3.8 Flash — 600 входных, 58,000 кешированных, 200 выходных токенов на запрос
- Qwen3.7 Plus — 500 входных, 57,000 кешированных, 190 выходных токенов на запрос
- Hy4 preview — 830 входных, 71,500 кешированных, 295 выходных токенов на запрос
- Hy3 — 830 входных, 71,500 кешированных, 295 выходных токенов на запрос
Вы можете отслеживать текущее использование в **<a href={console}>консоли</a>**.
Текущее использование можно отслеживать в **<a href={console}>консоли</a>**.
:::tip
Если вы достигнете лимита использования, вы можете продолжить использовать бесплатные модели.
При достижении лимита можно продолжить использовать бесплатные модели.
:::
Лимиты использования могут измениться по мере того, как мы будем собирать данные о раннем использовании и отзывы.
Лимиты использования могут меняться по мере изучения раннего использования и отзывов.
---
### Использование сверх лимитов
Если у вас также есть средства на балансе Zen, вы можете включить опцию **Use balance**
в консоли. Если она включена, Go будет использовать ваш баланс Zen
после достижения лимитов использования вместо того, чтобы блокировать запросы.
Если на вашем балансе Zen есть средства, можно включить опцию **Use balance**
в консоли. Тогда после достижения лимитов Go будет использовать баланс Zen,
а не блокировать запросы.
---
### Почему для некоторых моделей доступен меньший объем использования
### Почему для некоторых моделей доступен меньший объём использования
С Go вы платите $10 в месяц, а включённый объём использования за месяц зависит от модели.
В Go включённый месячный объём использования зависит от модели.
Для большинства моделей это возможно благодаря оптовым скидкам и зарезервированным мощностям GPU. Полученную экономию мы передаем вам в виде большего объёма использования за месяц.
Для большинства моделей это возможно благодаря оптовым скидкам и зарезервированным мощностям GPU. Эту экономию мы передаём вам в виде большего месячного объёма использования.
Для некоторых моделей у нас еще не было возможности договориться о скидке или развернуть их с меньшими затратами: либо модель новая, либо ее публичные тарифы уже включают скидку.
Для некоторых моделей мы пока не смогли договориться о скидке или разместить их дешевле: модель может быть новой, либо её публичная цена уже снижена.
Для этих моделей вы все равно получаете немного больше, чем при прямой оплате их провайдерам; именно поэтому включённый для них объём использования за месяц меньше.
Для таких моделей вы всё равно получаете немного больше, чем при прямой оплате провайдерам; поэтому включённый месячный объём у них ниже.
---
## Эндпоинты
Вы также можете получить доступ к моделям Go через следующие API-эндпоинты.
Доступ к моделям Go также можно получить через следующие API-эндпоинты.
| Модель | ID модели | Эндпоинт | Пакет AI SDK |
| Модель | ID модели | Эндпоинт | Пакет AI SDK |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -320,11 +417,11 @@ OpenCode Go предназначен для [OpenCode](https://opencode.ai) и
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -335,28 +432,24 @@ OpenCode Go предназначен для [OpenCode](https://opencode.ai) и
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
[ID модели](/docs/config/#models) в вашем конфиге OpenCode
использует формат `opencode-go/<model-id>`. Например, для Kimi K3 вам нужно
использовать `opencode-go/kimi-k3` в вашем конфиге.
[ID модели](/docs/config/#models) в конфигурации OpenCode
имеет формат `opencode-go/<model-id>`. Например, для Kimi K3
используйте `opencode-go/kimi-k3` в конфигурации.
---
### Модели
Вы можете получить полный список доступных моделей и их метаданных по адресу:
Полный список доступных моделей и их метаданные можно получить по адресу:
```
https://opencode.ai/zen/go/v1/models
@@ -366,47 +459,44 @@ https://opencode.ai/zen/go/v1/models
## Конфиденциальность
| Модель | Обучение моделей | Хранение данных |
| ---------------------------- | ---------------- | --------------- |
| Grok 4.7 | Не используется | 30 дней |
| Grok 4.6 | Не используется | 30 дней |
| GPT 6 Luna | Не используется | 30 дней |
| GPT 5.6 Luna | Не используется | 30 дней |
| GLM-5.3-Flash | Не используется | 0 дней |
| GLM-5.3 | Не используется | 0 дней |
| GLM-5.2 | Не используется | 0 дней |
| GLM-5.1 | Не используется | 0 дней |
| Kimi K3 | Не используется | 0 дней |
| Kimi K2.7 Code | Не используется | 0 дней |
| Kimi K2.6 | Не используется | 0 дней |
| LongCat-2.0 | Не используется | 0 дней |
| MiMo-V2.6-Pro | Не используется | 0 дней |
| MiMo-V2.6-Flash | Не используется | 0 дней |
| MiMo-V2.5-Pro | Не используется | 0 дней |
| MiMo-V2.5 | Не используется | 0 дней |
| Qwen3.8 Max | Не используется | 0 дней |
| Qwen3.8 Flash | Не используется | 0 дней |
| Qwen3.7 Max | Не используется | 0 дней |
| Qwen3.7 Plus | Не используется | 0 дней |
| Qwen3.6 Plus | Не используется | 0 дней |
| MiniMax M3 | Не используется | 0 дней |
| MiniMax M2.7 | Не используется | 0 дней |
| Muse Spark 1.3 Contributor | Да | Не ZDR |
| Muse Spark 1.2 Contributor | Да | Не ZDR |
| DeepSeek V4.1 Flash | Не используется | 0 дней |
| DeepSeek V4 Pro | Не используется | 0 дней |
| DeepSeek V4 Flash | Не используется | 0 дней |
| DeepSeek V4 Flash Vision Exp | Не используется | 0 дней |
| Hy4 preview | Не используется | 0 дней |
| Hy3 | Не используется | 0 дней |
| Space Bunny Free | Не используется | 0 дней |
| LongCat 2.5 Preview Free | Не используется | 0 дней |
| Модель | Обучение модели | Хранение данных |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Не используется | 30 дней |
| Grok 4.6 | Не используется | 30 дней |
| GPT 6 Luna | Не используется | 30 дней |
| GPT 5.6 Luna | Не используется | 30 дней |
| GLM-5.3-Flash | Не используется | 0 дней |
| GLM-5.3 | Не используется | 0 дней |
| GLM-5.2 | Не используется | 0 дней |
| Kimi K3 | Не используется | 0 дней |
| Kimi K2.7 Code | Не используется | 0 дней |
| Kimi K2.6 | Не используется | 0 дней |
| LongCat-2.0 | Не используется | 0 дней |
| MiMo-V2.6-Pro | Не используется | 0 дней |
| MiMo-V2.6-Flash | Не используется | 0 дней |
| MiMo-V2.5-Pro | Не используется | 0 дней |
| MiMo-V2.5 | Не используется | 0 дней |
| Qwen3.8 Max | Не используется | 0 дней |
| Qwen3.8 Flash | Не используется | 0 дней |
| Qwen3.7 Plus | Не используется | 0 дней |
| MiniMax M3 | Не используется | 0 дней |
| MiniMax M2.7 | Не используется | 0 дней |
| Muse Spark 1.3 Contributor | Да | Не ZDR |
| Muse Spark 1.2 Contributor | Да | Не ZDR |
| DeepSeek V4.1 Flash | Не используется | 0 дней\* |
| DeepSeek V4 Pro | Не используется | 0 дней\* |
| DeepSeek V4 Flash | Не используется | 0 дней\* |
| DeepSeek V4 Flash Vision Exp | Не используется | 0 дней\* |
| Hy4 preview | Не используется | 0 дней |
| Hy3 | Не используется | 0 дней |
| Space Bunny Free | Не используется | 0 дней |
| LongCat 2.5 Preview Free | Не используется | 0 дней |
- **Grok 4.7/4.6:** 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** Значительно сниженная стоимость токенов в обмен на разрешение использовать ваши промпты и ответы для обучения будущих моделей Meta. Доступность ограничена регионами, разрешёнными [Политикой географического использования](https://ai.developer.meta.com/legal/geographic-use-policy) компании Meta. [Подробнее](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Значительно сниженная стоимость токенов в обмен на разрешение использовать ваши промпты и ответы для обучения будущих моделей Meta. Доступность ограничена регионами, разрешёнными [Политикой географического использования](https://ai.developer.meta.com/legal/geographic-use-policy) компании Meta. [Подробнее](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** Соглашение ZDR продлевается ежемесячно. Текущее соглашение действует до 30 сентября 2026 года.
- **Grok 4.7/4.6:** ZDR отключает важные функции API, зависящие от сохранённых данных, включая Responses API с состоянием, Files and Collections и Batch API. [Подробнее](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr).
- **GPT 6 Luna / GPT 5.6 Luna:** Для всех функций API создаются журналы мониторинга злоупотреблений, которые хранятся до 30 дней. [Подробнее](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
- **Muse Spark 1.3 Contributor:** Значительно сниженная цена токенов в обмен на разрешение использовать ваши промпты и ответы для обучения будущих моделей Meta. Доступность ограничена регионами, разрешёнными [Политикой географического использования](https://ai.developer.meta.com/legal/geographic-use-policy) Meta. [Подробнее](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** Значительно сниженная цена токенов в обмен на разрешение использовать ваши промпты и ответы для обучения будущих моделей Meta. Доступность ограничена регионами, разрешёнными [Политикой географического использования](https://ai.developer.meta.com/legal/geographic-use-policy) Meta. [Подробнее](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** Соглашение ZDR продлевается ежемесячно. Текущее соглашение действует до 31 октября 2026 года.
---
@@ -414,7 +504,7 @@ https://opencode.ai/zen/go/v1/models
Мы создали OpenCode Go, чтобы:
1. Сделать программирование с ИИ **доступным** для большего числа людей с помощью недорогой подписки.
2. Обеспечить **надежный** доступ к лучшим открытым моделям для программирования.
3. Отбирать модели, которые **протестированы и проверены** для использования в качестве агентов-программистов.
4. Избежать **привязки к провайдеру**, позволяя вам также использовать любого другого провайдера вместе с OpenCode.
1. Сделать программирование с ИИ **доступным** большему числу людей благодаря недорогой подписке.
2. Обеспечить **надёжный** доступ к лучшим открытым моделям для программирования.
3. Отбирать модели, **протестированные и проверенные** для агентов программирования.
4. Обеспечить **отсутствие привязки**, позволяя использовать с OpenCode любого другого провайдера.
packages/web/src/content/docs/th/go.mdx
+339 -232
View File
@@ -1,66 +1,83 @@
---
title: Go
description: การสมัครสมาชิกราคาประหยัดสำหรับโมเดลโอเพนซอร์สเพื่อการเขียนโค้ด
description: การเข้าถึงโมเดลแบบเปิดสำหรับการเขียนโค้ดอย่างเสถียร พร้อมระดับการใช้งานสองระดับ
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go คือการสมัครสมาชิกในราคาประหยัด **$10/เดือน** ซึ่งให้คุณเข้าถึงโมเดลโอเพนซอร์สยอดนิยมสำหรับการเขียนโค้ดได้อย่างเสถียร
OpenCode Go ให้คุณเข้าถึงโมเดลแบบเปิดยอดนิยมสำหรับการเขียนโค้ดได้อย่างเสถียร โดยมีแพ็กรายเดือนสองแบบ:
Go ทำงานเหมือนกับผู้ให้บริการ (provider) รายอื่นๆ ใน OpenCode คุณสามารถสมัครสมาชิก OpenCode Go และรับ API key ของคุณ บริการนี้เป็น**ทางเลือกเพิ่มเติม** และคุณไม่จำเป็นต้องใช้มันเพื่อใช้งาน OpenCode
| แพ็ก | ราคา | ปริมาณการใช้งานที่รวมอยู่ |
| ---- | ----- | -------------- |
| **Go** | **$10/เดือน** | เข้าถึงโมเดลด้านล่างในราคาที่ประหยัดกว่า |
| **Go Plus** | **$40/เดือน** | ขีดจำกัดการใช้งานที่สูงกว่าสำหรับโมเดลด้านล่าง |
บริการนี้ออกแบบมาโดยเน้นผู้ใช้ในต่างประเทศเป็นหลัก และให้บริการได้อย่างเสถียรทั่วโลก
Go ทำงานเหมือนผู้ให้บริการรายอื่นใน OpenCode คุณสมัคร OpenCode Go และ
รับ API key บริการนี้เป็น**ทางเลือกโดยสมบูรณ์** และไม่จำเป็นต้องใช้บริการนี้เพื่อ
ใช้งาน OpenCode
บริการนี้ออกแบบมาโดยเน้นผู้ใช้ทั่วโลกเป็นหลัก และให้การเข้าถึงที่เสถียรทั่วโลก
---
## Background
## ความเป็นมา
โมเดลแบบเปิด (Open models) ได้รับการพัฒนาจนมีประสิทธิภาพดีมาก ตอนนี้ประสิทธิภาพในการเขียนโค้ดใกล้เคียงกับโมเดลแบบปิด (proprietary models) แล้ว และเนื่องจากมีผู้ให้บริการหลายรายสามารถให้บริการแข่งขันกันได้ จึงทำให้มีราคาถูกกว่ามาก
โมเดลแบบเปิดพัฒนาจนมีประสิทธิภาพดีมาก ปัจจุบันมีประสิทธิภาพสำหรับงานเขียนโค้ดใกล้เคียงกับ
โมเดลแบบปิด และเนื่องจากผู้ให้บริการหลายรายสามารถแข่งขันกันให้บริการได้
จึงมักมีราคาถูกกว่ามาก
อย่างไรก็ตาม การเข้าถึงโมเดลเหล่านี้อย่างเสถียรและมีค่า Latency ต่ำนั้นอาจเป็นเรื่องยาก ผู้ให้บริการแต่ละรายมีคุณภาพและความพร้อมในการให้บริการแตกต่างกันไป
อย่างไรก็ตาม การเข้าถึงโมเดลเหล่านี้อย่างเสถียรและมี latency ต่ำอาจทำได้ยาก ผู้ให้บริการ
แต่ละรายมีคุณภาพและความพร้อมแตกต่างกัน
:::tip
เราได้ทดสอบกลุ่มโมเดลและผู้ให้บริการที่คัดเลือกมาเพื่อให้ทำงานร่วมกับ OpenCode ได้เป็นอย่างดี
เราได้ทดสอบกลุ่มโมเดลและผู้ให้บริการที่คัดสรรแล้วว่าทำงานร่วมกับ OpenCode ได้ดี
:::
เพื่อแก้ปัญหานี้ เราได้ดำเนินการดังต่อไปนี้:
เพื่อแก้ปัญหานี้ เราได้ดำเนินการดังนี้:
1. เราทดสอบกลุ่มโมเดลแบบเปิดที่คัดเลือกมาและพูดคุยกับทีมผู้พัฒนาเกี่ยวกับวิธีการรันโมเดลเหล่านี้ให้ดีที่สุด
2. จากนั้นเราได้ทำงานร่วมกับผู้ให้บริการบางรายเพื่อให้แน่ใจว่าการให้บริการเป็นไปอย่างถูกต้อง
3. สุดท้าย เราได้ทำการวัดประสิทธิภาพ (benchmark) ของการทำงานร่วมกันระหว่างโมเดลและผู้ให้บริการ จนได้รายชื่อที่เรามั่นใจในการแนะนำ
1. เราทดสอบกลุ่มโมเดลแบบเปิดที่คัดสรรและพูดคุยกับทีมของโมเดลเกี่ยวกับวิธี
รันโมเดลให้ดีที่สุด
2. จากนั้นเราทำงานร่วมกับผู้ให้บริการบางรายเพื่อให้แน่ใจว่าโมเดลเหล่านี้ได้รับการให้บริการ
อย่างถูกต้อง
3. สุดท้าย เราวัดประสิทธิภาพของโมเดลและผู้ให้บริการแต่ละคู่ แล้วจัดทำ
รายการที่เรามั่นใจว่าจะแนะนำได้
OpenCode Go ให้คุณเข้าถึงโมเดลเหล่านี้ได้ในราคา **$10/เดือน**
ทั้ง Go และ Go Plus ให้สิทธิ์เข้าถึงโมเดลเหล่านี้ เลือกแพ็กที่เหมาะกับ
ปริมาณการใช้งานของคุณ
---
## How it works
## วิธีการทำงาน
OpenCode Go ทำงานเหมือนกับผู้ให้บริการรายอื่นๆ ใน OpenCode
OpenCode Go ทำงานเหมือนผู้ให้บริการรายอื่นใน OpenCode
1. ลงชื่อเข้าใช้ที่ **<a href={console}>OpenCode Zen</a>**, สมัครสมาชิก Go และคัดลอก API key ของคุณ
2. รันคำสั่ง `/connect` ใน TUI, เลือก `OpenCode Go`, และวาง API key ของคุณ
3. รัน `/models` ใน TUI เพื่อดูรายชื่อโมเดลที่ใช้งานได้ผ่าน Go
1. ลงชื่อเข้าใช้ **<a href={console}>OpenCode Console</a>** สมัคร Go หรือ Go Plus แล้ว
คัดลอก API key
2. รันคำสั่ง `/connect` ใน TUI เลือก `OpenCode Go` แล้ววาง
API key
3. รัน `/models` ใน TUI เพื่อดูรายการโมเดลที่ใช้ได้ผ่าน Go
:::note
มีเพียงสมาชิกหนึ่งคนต่อ workspace เท่านั้นที่สามารถสมัครสมาชิก OpenCode Go ได้
สมาชิกเพียงหนึ่งคนต่อ workspace เท่านั้นที่สมัคร OpenCode Go หรือ Go Plus ได้
:::
รายชื่อโมเดลในปัจจุบันประกอบด้วย:
รายการโมเดลปัจจุบันประกอบด้วย:
- **Grok 4.7**
- **Grok 4.6**
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (ในช่วงเวลาจำกัด)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,9 +88,7 @@ OpenCode Go ทำงานเหมือนกับผู้ให้บร
- **Muse Spark 1.2 Contributor** ([เฉพาะบางภูมิภาค](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -81,222 +96,319 @@ OpenCode Go ทำงานเหมือนกับผู้ให้บร
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (ในช่วงเวลาจำกัด)
- **LongCat 2.5 Preview Free** (ในช่วงเวลาจำกัด)
รายชื่อโมเดลอาจมีการเปลี่ยนแปลงเมื่อเราทำการทดสอบและเพิ่มโมเดลใหม่ๆ
รายการโมเดลอาจเปลี่ยนแปลงเมื่อเราทดสอบและเพิ่มโมเดลใหม่
---
## ใช้งานได้ที่ไหน?
OpenCode Go ออกแบบมาสำหรับ [OpenCode](https://opencode.ai) และ coding agent อื่นๆ ที่สร้างคำขอประเภทเดียวกัน
ระบบจะตรวจสอบทราฟฟิกเพื่อหาการใช้งานในทางที่ผิดซึ่งทำให้ประสบการณ์ของผู้ใช้รายอื่นแย่ลง
OpenCode Go ออกแบบมาสำหรับ [OpenCode](https://opencode.ai) และ coding agent อื่นที่ส่งคำขอประเภทใกล้เคียงกัน
ระบบจะตรวจสอบทราฟฟิกเพื่อหาการใช้งานในทางที่ผิดซึ่งทำให้
ประสบการณ์ของผู้ใช้อื่นแย่ลง
ไคลเอนต์ของคุณควร:
1. ส่งทราฟฟิกตามปกติของ coding agent
2. ระบุตัวตนด้วย user agent ของตนเอง เช่น `my-coding-agent/1.0` แทนชื่อ SDK หรือไลบรารี HTTP แบบทั่วไป
3. ส่ง session ID ที่คงที่ใน `x-opencode-session` สำหรับแต่ละบทสนทนา เพื่อให้เราปรับ routing และ prompt caching ให้เหมาะสมได้
2. ระบุตัวตนด้วย user agent ของตนเอง เช่น `my-coding-agent/1.0` แทน
ชื่อ SDK หรือไลบรารี HTTP แบบทั่วไป
3. ส่ง session ID ที่คงที่ใน `x-opencode-session` สำหรับแต่ละบทสนทนา เพื่อให้เราปรับ routing และ
prompt caching ให้เหมาะสมได้
### ไคลเอนต์ที่ผ่านการตรวจสอบแล้ว
นอกจาก OpenCode แล้ว ไคลเอนต์ต่อไปนี้ได้รับการตรวจสอบแล้วว่าทำงานกับ OpenCode Go ได้อย่างถูกต้อง
อย่างไรก็ตาม เราไม่รับประกันว่าไคลเอนต์เหล่านี้จะยังคงทำงานได้ต่อไปในอนาคต
นอกจาก OpenCode แล้ว ไคลเอนต์ต่อไปนี้ได้รับการตรวจสอบแล้วว่าทำงานได้อย่างถูกต้อง
กับ OpenCode Go อย่างไรก็ตาม เราไม่รับประกันว่าจะยังคงทำงานได้ในอนาคต
| ไคลเอนต์ | การรองรับเซสชัน |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Hermes** | บิลด์ที่มี [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) จะส่งส่วนหัวในคำขอ OpenCode ทั้งคำขอหลักและคำขอเสริม การแก้ไขนี้ถูก merge หลัง v0.21.0 ดังนั้นตัวรีลีส v0.21.0 เองจึงยังไม่มีการแก้ไขนี้ |
| **Claude Code** | Go รู้จักส่วนหัวเซสชันแบบ native ของ Claude Code จึงไม่ต้องใช้ wrapper เพื่อเพิ่มส่วนหัวแบบกำหนดเอง |
| **Codex** | Go รู้จักส่วนหัวเซสชันแบบ native ของ Codex แต่บางเวอร์ชันและการตั้งค่า proxy ยังไม่ส่งส่วนหัวนี้ โปรดคงส่วนหัวเซสชันไว้เมื่อ forward คำขอ |
| **ZCode** | Go รู้จักส่วนหัวเซสชันแบบ native ของ ZCode [คำขอให้เพิ่ม `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) ของเรายังเปิดอยู่ แต่ไม่จำเป็นต้องส่งส่วนหัวเฉพาะนี้อีกต่อไป |
| **Pi** | บิลด์ปัจจุบันส่งข้อมูลเซสชันสำหรับ OpenCode โปรดอัปเดตการติดตั้งเวอร์ชันเก่า |
| **jcode** | อัปเดตเป็น **v0.81.6 หรือใหม่กว่า** ซึ่งมี[การแก้ไขส่วนหัวเซสชัน](https://github.com/1jehuang/jcode/issues/1167) |
| **Kilo Code CLI** | บิลด์ที่มี [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) จะทำให้ส่วนหัวเซสชันของ OpenCode กลับมาทำงาน การแก้ไขนี้ครอบคลุม CLI แต่ไม่ครอบคลุมส่วนขยาย VS Code ดู [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723) |
| ไคลเอนต์ | การรองรับเซสชัน |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | บิลด์ที่มี [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) จะส่ง header ในคำขอ OpenCode ทั้งหลักและเสริม การแก้ไข merge หลัง v0.21.0 ดังนั้นรีลีสนั้นเพียงอย่างเดียวจึงยังไม่มีการแก้ไขนี้ |
| **Claude Code** | Go รู้จัก session header แบบ native จึงไม่ต้องใช้ wrapper สำหรับ custom header |
| **Codex** | Go รู้จัก session header แบบ native บางเวอร์ชันและการตั้งค่า proxy ยังไม่ส่ง header นี้ โปรดคง session header ไว้เมื่อ forward คำขอ |
| **ZCode** | Go รู้จัก session header แบบ native [คำขอ `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) ของเรายังเปิดอยู่ แต่ไม่จำเป็นต้องส่ง header นี้โดยเฉพาะอีกต่อไป |
| **Pi** | บิลด์ปัจจุบันส่งข้อมูลเซสชันสำหรับ OpenCode โปรดอัปเดตการติดตั้งเวอร์ชันเก่า |
| **jcode** | อัปเดตเป็น **v0.81.6 หรือใหม่กว่า** ซึ่งมี[การแก้ไข session header](https://github.com/1jehuang/jcode/issues/1167) |
| **Kilo Code CLI** | บิลด์ที่มี [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) ทำให้ session header ของ OpenCode กลับมาทำงาน การแก้ไขนี้ครอบคลุม CLI แต่ไม่ครอบคลุมส่วนขยาย VS Code ดู [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723) |
### ไคลเอนต์ที่ทราบว่ามีปัญหา
ไคลเอนต์เหล่านี้ไม่รองรับเซสชันหรือรองรับไม่สมบูรณ์ในเวอร์ชันที่เราตรวจสอบ
รายงานที่ลิงก์ไว้ใช้ติดตามการแก้ไขและวิธีแก้ปัญหาชั่วคราว
| ไคลเอนต์ | สถานะและการติดตาม |
| ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **DeepSeek Harness** | ข้อมูลเซสชันส่งมาถึงใน model path บางรายการ แต่ขาดหายไปในรายการอื่น Go รู้จักส่วนหัวแบบ native ของ DeepSeek Harness งานที่เหลือคือการส่งส่วนหัวนี้ผ่าน adapter ทั้งหมด [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495) |
| **GitHub Copilot Chat** | มีการขอให้รองรับส่วนหัวเซสชันโดยอัตโนมัติใน [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) |
| **Kimi Code** | มีการขอให้รองรับส่วนหัวเซสชันโดยอัตโนมัติใน [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) มีการเสนอการแก้ไขใน [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327) ซึ่งยังไม่ได้ merge |
| ไคลเอนต์ | สถานะและการติดตาม |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | ข้อมูลเซสชันมาถึงใน model path บางรายการ แต่ขาดหายไปในรายการอื่น เรารู้จัก header แบบ native แล้ว งานที่เหลือคือส่งผ่าน adapter ทั้งหมด [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495) |
| **GitHub Copilot Chat** | มีการขอให้รองรับ session header โดยอัตโนมัติใน [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) |
| **Kimi Code** | มีการขอให้รองรับ session header โดยอัตโนมัติใน [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) มีการเสนอการแก้ไขใน [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327) ซึ่งยังไม่ได้ merge |
## Usage limits
## ขีดจำกัดการใช้งาน
ขีดจำกัดการใช้งานกำหนดเป็นจำนวนเงินดอลลาร์รายเดือน ตารางด้านล่างแสดงขีดจำกัดรายเดือนและค่า token ของแต่ละโมเดล
ขีดจำกัดการใช้งานกำหนดเป็นจำนวนเงินดอลลาร์รายเดือน ตารางด้านล่างแสดง
ขีดจำกัดรายเดือนของแต่ละแพ็กและค่า token ของแต่ละโมเดล ราคา token
ของ Go และ Go Plus เท่ากัน
แต่ละโมเดลมีขีดจำกัดการใช้งานดังนี้: 5 ชั่วโมง — 20% ของขีดจำกัดรายเดือน; รายสัปดาห์ — 50%; และรายเดือน — 100%
แต่ละโมเดลมีขีดจำกัดดังนี้: 5 ชั่วโมง — 20% ของขีดจำกัดรายเดือน;
รายสัปดาห์ — 50%; และรายเดือน — 100%
ตัวอย่างเช่น หากโมเดลมีขีดจำกัดรายเดือน $60 คุณสามารถใช้งานได้สูงสุด:
ตัวอย่างเช่น หากโมเดลมีขีดจำกัดรายเดือน $60 ใน Go และ $120
ใน Go Plus คุณสามารถใช้ได้สูงสุด:
- **ขีดจำกัดต่อ 5 ชั่วโมง** — การใช้งาน $12
- **ขีดจำกัดรายสัปดาห์** — การใช้งาน $30
- **ขีดจำกัดรายเดือน** — การใช้งาน $60
- **ขีดจำกัดต่อ 5 ชั่วโมง** — $12 ใน Go หรือ $24 ใน Go Plus
- **ขีดจำกัดรายสัปดาห์** — $30 ใน Go หรือ $60 ใน Go Plus
- **ขีดจำกัดรายเดือน** — $60 ใน Go หรือ $120 ใน Go Plus
เมื่อรวมทุกโมเดล Go มีโควตา $12 ต่อ 5 ชั่วโมง, $30 ต่อสัปดาห์ และ $60 ต่อเดือน;
Go Plus มีโควตา $48 ต่อ 5 ชั่วโมง, $120 ต่อสัปดาห์ และ $240 ต่อเดือน ขีดจำกัดรายเดือน
ของแต่ละโมเดลด้านล่างเป็นตัวกำหนดว่าการใช้งานจะนับรวมใน
โควตาเหล่านี้อย่างไร
ราคา token แสดงต่อ 1M tokens
| Model | Input | Output | Cached Read | Cached Write | ขีดจำกัดรายเดือน |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ------------------------------------------------ |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **ไม่จำกัด**<br /><small>ในช่วงเวลาจำกัด</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **ไม่จำกัด**<br /><small>ในช่วงเวลาจำกัด</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| โมเดล | อินพุต | เอาต์พุต | การอ่านแคช | การเขียนแคช | ขีดจำกัดรายเดือน |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | ฟรี | ฟรี | ฟรี | - | **ไม่จำกัด**<br /><small>ในช่วงเวลาจำกัด</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | ฟรี | ฟรี | ฟรี | - | **ไม่จำกัด**<br /><small>ในช่วงเวลาจำกัด</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| โมเดล | อินพุต | เอาต์พุต | การอ่านแคช | การเขียนแคช | ขีดจำกัดรายเดือน |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | ฟรี | ฟรี | ฟรี | - | **ไม่จำกัด**<br /><small>ในช่วงเวลาจำกัด</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | ฟรี | ฟรี | ฟรี | - | **ไม่จำกัด**<br /><small>ในช่วงเวลาจำกัด</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** ใช้งานฟรีในช่วงเวลาจำกัด
**LongCat 2.5 Preview Free:** ใช้งานฟรีในช่วงเวลาจำกัด
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** ช่วงเวลา Peak คือ 01:00-04:00 และ 06:00-10:00 UTC ตั้งแต่วันจันทร์ถึงวันศุกร์ ส่วนเวลาอื่นทั้งหมด รวมถึงวันหยุดสุดสัปดาห์ เป็น Off-Peak [ดูข้อมูลเพิ่มเติม](https://api-docs.deepseek.com/quick_start/pricing/)
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** ช่วงเวลา Peak คือ 01:00-04:00 and 06:00-10:00 UTC, ตั้งแต่วันจันทร์ถึงวันศุกร์ ส่วนเวลาอื่นทั้งหมด รวมถึงวันหยุดสุดสัปดาห์ เป็น Off-Peak [ดูข้อมูลเพิ่มเติม](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** รูปภาพจะถูกแปลงเป็น token ตามขนาด และคิดค่าบริการเป็น input token รวมกับ text token [ดูข้อมูลเพิ่มเติม](https://api-docs.deepseek.com/quick_start/pricing/)
**DeepSeek V4 Flash Vision Exp:** รูปภาพจะถูกแปลงเป็น token ตามขนาด และคิดค่าบริการเป็น input token รวมกับ text token [ดูข้อมูลเพิ่มเติม](https://api-docs.deepseek.com/quick_start/pricing/).
### requests โดยประมาณ
### จำนวนคำขอโดยประมาณ
ตารางด้านล่างแสดงจำนวน request โดยประมาณตามรูปแบบการใช้งานปกติของ Go:
ตารางด้านล่างประมาณจำนวนคำขอตามรูปแบบการใช้งานปกติของ Go การประมาณของ Go
Plus จะเพิ่มตามขีดจำกัดการใช้งานที่สูงขึ้นของแต่ละโมเดล
| Model | requests ต่อ 5 ชั่วโมง | requests ต่อสัปดาห์ | requests ต่อเดือน |
| ---------------------------- | ---------------------- | ------------------- | ----------------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | ไม่จำกัด | ไม่จำกัด | ไม่จำกัด |
| LongCat 2.5 Preview Free | ไม่จำกัด | ไม่จำกัด | ไม่จำกัด |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
การประมาณการใช้จำนวน token ต่อ request ดังต่อไปนี้ การใช้งานจริงอาจแตกต่างกัน
| โมเดล | คำขอต่อ 5 ชั่วโมง | คำขอต่อสัปดาห์ | คำขอต่อเดือน |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | ไม่จำกัด | ไม่จำกัด | ไม่จำกัด |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | ไม่จำกัด | ไม่จำกัด | ไม่จำกัด |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
- Grok 4.7/4.6 — 390 input, 32,500 cached, 120 output tokens ต่อ request
- GLM-5.3-Flash — 1,000 input, 55,000 cached, 200 output tokens ต่อ request
- GLM-5.3/5.2/5.1 — 700 input, 52,000 cached, 150 output tokens ต่อ request
- GPT 6 Luna — 1,000 input, 50,000 cached, 220 output tokens ต่อ request
- GPT 5.6 Luna — 1,000 input, 50,000 cached, 220 output tokens ต่อ request
- Kimi K3 — 1,050 input, 76,500 cached, 300 output tokens ต่อ request
- Kimi K2.7/K2.6 — 870 input, 55,000 cached, 200 output tokens ต่อ request
- LongCat-2.0 — 920 input, 88,900 cached, 200 output tokens ต่อ request
- DeepSeek V4.1 Flash — 410 input, 71,300 cached, 310 output tokens ต่อ request
- DeepSeek V4 Pro — 750 input, 82,000 cached, 290 output tokens ต่อ request
- DeepSeek V4 Flash — 410 input, 71,300 cached, 310 output tokens ต่อ request
- DeepSeek V4 Flash Vision Exp — 410 input, 71,300 cached, 310 output tokens ต่อ request
- MiniMax M3 — 510 input, 56,000 cached, 190 output tokens ต่อ request
- MiniMax M2.7 — 300 input, 55,000 cached, 125 output tokens ต่อ request
- Muse Spark 1.3 Contributor — 620 input, 71,400 cached, 300 output tokens ต่อ request
- Muse Spark 1.2 Contributor — 620 input, 71,400 cached, 300 output tokens ต่อ request
- Qwen3.8 Max — 420 input, 66,000 cached, 200 output tokens ต่อ request
- Qwen3.8 Flash — 600 input, 58,000 cached, 200 output tokens ต่อ request
- Qwen3.7 Max — 420 input, 66,000 cached, 200 output tokens ต่อ request
- Qwen3.7 Plus — 500 input, 57,000 cached, 190 output tokens ต่อ request
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens ต่อ request
- Hy4 preview — 830 input, 71,500 cached, 295 output tokens ต่อ request
- Hy3 — 830 input, 71,500 cached, 295 output tokens ต่อ request
- MiMo-V2.6-Flash — 830 input, 71,500 cached, 295 output tokens ต่อ request
- MiMo-V2.6-Pro — 790 input, 86,000 cached, 305 output tokens ต่อ request
- MiMo-V2.5 — 830 input, 71,500 cached, 295 output tokens ต่อ request
- MiMo-V2.5-Pro — 790 input, 86,000 cached, 305 output tokens ต่อ request
</TabItem>
<TabItem label="Go Plus">
คุณสามารถติดตามการใช้งานปัจจุบันของคุณได้ใน **<a href={console}>console</a>**
| โมเดล | คำขอต่อ 5 ชั่วโมง | คำขอต่อสัปดาห์ | คำขอต่อเดือน |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | ไม่จำกัด | ไม่จำกัด | ไม่จำกัด |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | ไม่จำกัด | ไม่จำกัด | ไม่จำกัด |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
การประมาณใช้จำนวน token ต่อคำขอดังต่อไปนี้ การใช้งานจริงอาจแตกต่างกัน
- Grok 4.7/4.6 — 390 input, 32,500 cached, 120 output tokens ต่อคำขอ
- GLM-5.3-Flash — 1,000 input, 55,000 cached, 200 output tokens ต่อคำขอ
- GLM-5.3/5.2 — 700 input, 52,000 cached, 150 output tokens ต่อคำขอ
- GPT 6 Luna — 1,000 input, 50,000 cached, 220 output tokens ต่อคำขอ
- GPT 5.6 Luna — 1,000 input, 50,000 cached, 220 output tokens ต่อคำขอ
- Kimi K3 — 1,050 input, 76,500 cached, 300 output tokens ต่อคำขอ
- Kimi K2.7/K2.6 — 870 input, 55,000 cached, 200 output tokens ต่อคำขอ
- LongCat-2.0 — 920 input, 88,900 cached, 200 output tokens ต่อคำขอ
- DeepSeek V4.1 Flash — 410 input, 71,300 cached, 310 output tokens ต่อคำขอ
- DeepSeek V4 Pro — 750 input, 82,000 cached, 290 output tokens ต่อคำขอ
- DeepSeek V4 Flash — 410 input, 71,300 cached, 310 output tokens ต่อคำขอ
- DeepSeek V4 Flash Vision Exp — 410 input, 71,300 cached, 310 output tokens ต่อคำขอ
- MiniMax M3 — 510 input, 56,000 cached, 190 output tokens ต่อคำขอ
- MiniMax M2.7 — 300 input, 55,000 cached, 125 output tokens ต่อคำขอ
- Muse Spark 1.3 Contributor — 620 input, 71,400 cached, 300 output tokens ต่อคำขอ
- Muse Spark 1.2 Contributor — 620 input, 71,400 cached, 300 output tokens ต่อคำขอ
- MiMo-V2.6-Flash — 830 input, 71,500 cached, 295 output tokens ต่อคำขอ
- MiMo-V2.6-Pro — 790 input, 86,000 cached, 305 output tokens ต่อคำขอ
- MiMo-V2.5 — 830 input, 71,500 cached, 295 output tokens ต่อคำขอ
- MiMo-V2.5-Pro — 790 input, 86,000 cached, 305 output tokens ต่อคำขอ
- Qwen3.8 Max — 420 input, 66,000 cached, 200 output tokens ต่อคำขอ
- Qwen3.8 Flash — 600 input, 58,000 cached, 200 output tokens ต่อคำขอ
- Qwen3.7 Plus — 500 input, 57,000 cached, 190 output tokens ต่อคำขอ
- Hy4 preview — 830 input, 71,500 cached, 295 output tokens ต่อคำขอ
- Hy3 — 830 input, 71,500 cached, 295 output tokens ต่อคำขอ
คุณสามารถติดตามการใช้งานปัจจุบันได้ใน **<a href={console}>console</a>**
:::tip
หากคุณใช้งานถึงขีดจำกัดแล้ว คุณยังสามารถใช้งานโมเดลฟรีต่อไปได้
หากใช้งานถึงขีดจำกัดแล้ว คุณยังใช้โมเดลฟรีต่อไปได้
:::
ขีดจำกัดการใช้งานอาจมีการเปลี่ยนแปลงเมื่อเราได้เรียนรู้จากการใช้งานในช่วงแรกและรับฟังข้อเสนอแนะ
ขีดจำกัดการใช้งานอาจเปลี่ยนแปลงเมื่อเราเรียนรู้จากการใช้งานช่วงแรกและข้อเสนอแนะ
---
### Usage beyond limits
### การใช้งานเกินขีดจำกัด
หากคุณมีเครดิตในยอดเงินคงเหลือของ Zen ด้วย คุณสามารถเปิดใช้งานตัวเลือก **Use balance** ใน console เมื่อเปิดใช้งาน Go จะหันไปใช้ยอดเงินคงเหลือใน Zen ของคุณหลังจากที่คุณใช้งานถึงขีดจำกัดแล้วแทนที่จะบล็อก request
หากคุณมีเครดิตในยอดคงเหลือ Zen คุณสามารถเปิดตัวเลือก **Use balance**
ใน console เมื่อเปิดแล้ว Go จะใช้ยอดคงเหลือ Zen
หลังจากถึงขีดจำกัดแทนการบล็อกคำขอ
---
### เหตุใดบางโมเดลจึงมีปริมาณการใช้งานต่ำกว่า
สำหรับ Go คุณจ่าย $10/เดือน และปริมาณการใช้งานรายเดือนที่รวมอยู่จะแตกต่างกันตามโมเดล
สำหรับ Go ปริมาณการใช้งานรายเดือนที่รวมอยู่จะแตกต่างกันตามโมเดล
สำหรับโมเดลส่วนใหญ่ เราทำเช่นนี้ได้ผ่านส่วนลดสำหรับการซื้อจำนวนมากและความจุ GPU ที่จองไว้ จากนั้นเราจะส่งต่อส่วนลดเหล่านั้นให้คุณในรูปของปริมาณการใช้งานรายเดือนที่มากขึ้น
สำหรับโมเดลส่วนใหญ่ เราทำได้ด้วยส่วนลดแบบจำนวนมากและความจุ GPU ที่จองไว้ แล้วส่งต่อส่วนลดเป็นปริมาณการใช้งานรายเดือนที่มากขึ้น
สำหรับบางโมเดล เรายังไม่มีโอกาสเจรจาส่วนลดหรือโฮสต์โมเดลเหล่านั้นด้วยต้นทุนที่ต่ำลง ไม่ว่าจะเป็นเพราะโมเดลนั้นใหม่หรือราคาที่ประกาศต่อสาธารณะมีส่วนลดอยู่แล้ว
สำหรับบางโมเดล เรายังไม่มีโอกาสเจรจาส่วนลดหรือโฮสต์ด้วยต้นทุนที่ต่ำลง เพราะโมเดลเพิ่งเปิดตัวหรือราคาสาธารณะมีส่วนลดอยู่แล้ว
สำหรับโมเดลเหล่านี้ คุณยังคงได้รับปริมาณการใช้งานมากกว่าการจ่ายให้ผู้ให้บริการโมเดลโดยตรงเล็กน้อย นี่คือเหตุผลที่ปริมาณการใช้งานรายเดือนที่รวมอยู่ของโมเดลเหล่านี้ต่ำกว่า
สำหรับโมเดลเหล่านี้ คุณยังได้ปริมาณการใช้งานมากกว่าการจ่ายให้ผู้ให้บริการโดยตรงเล็กน้อย จึงมีปริมาณรายเดือนที่รวมอยู่ต่ำกว่า
---
## Endpoints
## Endpoint
คุณสามารถเข้าถึงโมเดลของ Go ผ่าน API endpoints ต่อไปนี้ได้เช่นกัน
คุณยังเข้าถึงโมเดล Go ผ่าน API endpoint ต่อไปนี้ได้
| Model | Model ID | Endpoint | AI SDK Package |
| โมเดล | Model ID | Endpoint | แพ็กเกจ AI SDK |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -305,11 +417,11 @@ OpenCode Go ออกแบบมาสำหรับ [OpenCode](https://openco
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -320,26 +432,24 @@ OpenCode Go ออกแบบมาสำหรับ [OpenCode](https://openco
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
[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
[model id](/docs/config/#models) ใน OpenCode config
ใช้รูปแบบ `opencode-go/<model-id>` ตัวอย่างเช่น สำหรับ Kimi K3 ให้
ใช้ `opencode-go/kimi-k3` ใน config
---
### Models
### โมเดล
คุณสามารถดึงรายการโมเดลทั้งหมดที่พร้อมใช้งานและ metadata ของมันได้จาก:
คุณสามารถดึงรายการโมเดลทั้งหมดและ metadata ได้จาก:
```
https://opencode.ai/zen/go/v1/models
@@ -347,57 +457,54 @@ https://opencode.ai/zen/go/v1/models
---
## Privacy
## ความเป็นส่วนตัว
| โมเดล | การฝึกโมเดล | การเก็บรักษาข้อมูล |
| ---------------------------- | ----------- | ------------------ |
| Grok 4.7 | ไม่นำไปใช้ | 30 วัน |
| Grok 4.6 | ไม่นำไปใช้ | 30 วัน |
| GPT 6 Luna | ไม่นำไปใช้ | 30 วัน |
| GPT 5.6 Luna | ไม่นำไปใช้ | 30 วัน |
| GLM-5.3-Flash | ไม่นำไปใช้ | 0 วัน |
| GLM-5.3 | ไม่นำไปใช้ | 0 วัน |
| GLM-5.2 | ไม่นำไปใช้ | 0 วัน |
| GLM-5.1 | ไม่นำไปใช้ | 0 วัน |
| Kimi K3 | ไม่นำไปใช้ | 0 วัน |
| Kimi K2.7 Code | ไม่นำไปใช้ | 0 วัน |
| Kimi K2.6 | ไม่นำไปใช้ | 0 วัน |
| LongCat-2.0 | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.6-Pro | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.6-Flash | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.5-Pro | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.5 | ไม่นำไปใช้ | 0 วัน |
| Qwen3.8 Max | ไม่นำไปใช้ | 0 วัน |
| Qwen3.8 Flash | ไม่นำไปใช้ | 0 วัน |
| Qwen3.7 Max | ไม่นำไปใช้ | 0 วัน |
| Qwen3.7 Plus | ไม่นำไปใช้ | 0 วัน |
| Qwen3.6 Plus | ไม่นำไปใช้ | 0 วัน |
| MiniMax M3 | ไม่นำไปใช้ | 0 วัน |
| MiniMax M2.7 | ไม่นำไปใช้ | 0 วัน |
| Muse Spark 1.3 Contributor | ใช่ | ไม่ใช่ ZDR |
| Muse Spark 1.2 Contributor | ใช่ | ไม่ใช่ ZDR |
| DeepSeek V4.1 Flash | ไม่นำไปใช้ | 0 วัน |
| DeepSeek V4 Pro | ไม่นำไปใช้ | 0 วัน |
| DeepSeek V4 Flash | ไม่นำไปใช้ | 0 วัน |
| DeepSeek V4 Flash Vision Exp | ไม่นำไปใช้ | 0 วัน |
| Hy4 preview | ไม่นำไปใช้ | 0 วัน |
| Hy3 | ไม่นำไปใช้ | 0 วัน |
| Space Bunny Free | ไม่นำไปใช้ | 0 วัน |
| LongCat 2.5 Preview Free | ไม่นำไปใช้ | 0 วัน |
| โมเดล | การฝึกโมเดล | การเก็บรักษาข้อมูล |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | ไม่นำไปใช้ | 30 วัน |
| Grok 4.6 | ไม่นำไปใช้ | 30 วัน |
| GPT 6 Luna | ไม่นำไปใช้ | 30 วัน |
| GPT 5.6 Luna | ไม่นำไปใช้ | 30 วัน |
| GLM-5.3-Flash | ไม่นำไปใช้ | 0 วัน |
| GLM-5.3 | ไม่นำไปใช้ | 0 วัน |
| GLM-5.2 | ไม่นำไปใช้ | 0 วัน |
| Kimi K3 | ไม่นำไปใช้ | 0 วัน |
| Kimi K2.7 Code | ไม่นำไปใช้ | 0 วัน |
| Kimi K2.6 | ไม่นำไปใช้ | 0 วัน |
| LongCat-2.0 | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.6-Pro | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.6-Flash | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.5-Pro | ไม่นำไปใช้ | 0 วัน |
| MiMo-V2.5 | ไม่นำไปใช้ | 0 วัน |
| Qwen3.8 Max | ไม่นำไปใช้ | 0 วัน |
| Qwen3.8 Flash | ไม่นำไปใช้ | 0 วัน |
| Qwen3.7 Plus | ไม่นำไปใช้ | 0 วัน |
| MiniMax M3 | ไม่นำไปใช้ | 0 วัน |
| MiniMax M2.7 | ไม่นำไปใช้ | 0 วัน |
| Muse Spark 1.3 Contributor | ใช่ | ไม่ใช่ ZDR |
| Muse Spark 1.2 Contributor | ใช่ | ไม่ใช่ ZDR |
| DeepSeek V4.1 Flash | ไม่นำไปใช้ | 0 วัน\* |
| DeepSeek V4 Pro | ไม่นำไปใช้ | 0 วัน\* |
| DeepSeek V4 Flash | ไม่นำไปใช้ | 0 วัน\* |
| DeepSeek V4 Flash Vision Exp | ไม่นำไปใช้ | 0 วัน\* |
| Hy4 preview | ไม่นำไปใช้ | 0 วัน |
| Hy3 | ไม่นำไปใช้ | 0 วัน |
| Space Bunny Free | ไม่นำไปใช้ | 0 วัน |
| LongCat 2.5 Preview Free | ไม่นำไปใช้ | 0 วัน |
- **Grok 4.7/4.6:** 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 6 Luna / 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)
- **Muse Spark 1.3 Contributor:** ราคาของ token ลดลงอย่างมาก โดยแลกกับการอนุญาตให้นำพรอมต์และผลลัพธ์ที่สร้างขึ้นของคุณไปใช้ฝึกโมเดล Meta ในอนาคต การให้บริการจำกัดเฉพาะภูมิภาคที่ได้รับอนุญาตตาม[นโยบายการใช้งานตามพื้นที่ทางภูมิศาสตร์](https://ai.developer.meta.com/legal/geographic-use-policy)ของ Meta [ดูข้อมูลเพิ่มเติม](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)
- **Muse Spark 1.2 Contributor:** ราคาของ token ลดลงอย่างมาก โดยแลกกับการอนุญาตให้นำพรอมต์และผลลัพธ์ที่สร้างขึ้นของคุณไปใช้ฝึกโมเดล Meta ในอนาคต การให้บริการจำกัดเฉพาะภูมิภาคที่ได้รับอนุญาตตาม[นโยบายการใช้งานตามพื้นที่ทางภูมิศาสตร์](https://ai.developer.meta.com/legal/geographic-use-policy)ของ Meta [ดูข้อมูลเพิ่มเติม](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)
- **DeepSeek:** ข้อตกลง ZDR จะต่ออายุทุกเดือน ข้อตกลงปัจจุบันมีผลใช้ถึงวันที่ 30 กันยายน 2026
- **Grok 4.7/4.6:** ZDR ปิดใช้ฟีเจอร์ API สำคัญที่ต้องอาศัยข้อมูลที่จัดเก็บไว้ รวมถึง Responses API แบบมีสถานะ, Files and Collections และ Batch API [ดูข้อมูลเพิ่มเติม](https://docs.x.ai/developers/faq/security#what-is-zero-data-retention-zdr)
- **GPT 6 Luna / GPT 5.6 Luna:** ระบบสร้างบันทึกการตรวจสอบการใช้งานในทางที่ผิดสำหรับฟีเจอร์ API ทั้งหมด และเก็บไว้นานสูงสุด 30 วัน [ดูข้อมูลเพิ่มเติม](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring)
- **Muse Spark 1.3 Contributor:** ราคา token ลดลงอย่างมาก โดยแลกกับการอนุญาตให้นำ prompt และ completion ของคุณไปฝึกโมเดล Meta ในอนาคต การให้บริการจำกัดเฉพาะภูมิภาคที่ได้รับอนุญาตตาม[นโยบายการใช้งานตามพื้นที่ทางภูมิศาสตร์](https://ai.developer.meta.com/legal/geographic-use-policy)ของ Meta [ดูข้อมูลเพิ่มเติม](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)
- **Muse Spark 1.2 Contributor:** ราคา token ลดลงอย่างมาก โดยแลกกับการอนุญาตให้นำ prompt และ completion ของคุณไปฝึกโมเดล Meta ในอนาคต การให้บริการจำกัดเฉพาะภูมิภาคที่ได้รับอนุญาตตาม[นโยบายการใช้งานตามพื้นที่ทางภูมิศาสตร์](https://ai.developer.meta.com/legal/geographic-use-policy)ของ Meta [ดูข้อมูลเพิ่มเติม](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)
- **DeepSeek:** ข้อตกลง ZDR ต่ออายุทุกเดือน ข้อตกลงปัจจุบันมีผลถึงวันที่ 31 ตุลาคม 2026
---
## Goals
## เป้าหมาย
เราสร้าง OpenCode Go เพื่อ:
1. ทำให้การเขียนโค้ดด้วย AI **เข้าถึงได้** สำหรับผู้คนจำนวนมากขึ้นด้วยการสมัครสมาชิกในราคาประหยัด
2. มอบการเข้าถึงโมเดลโอเพนซอร์สสำหรับการเขียนโค้ดที่ดีที่สุดได้อย่าง**เสถียร**
3. คัดสรรโมเดลที่ผ่าน**การทดสอบและวัดประสิทธิภาพ**สำหรับการใช้งาน coding agent แล้ว
4. **ไม่ผูกขาดการใช้งาน (no lock-in)** โดยอนุญาตให้คุณใช้งานผู้ให้บริการรายอื่นๆ ร่วมกับ OpenCode ได้เช่นกัน
1. ทำให้การเขียนโค้ดด้วย AI **เข้าถึงได้** สำหรับคนจำนวนมากขึ้นด้วยการสมัครราคาประหยัด
2. มอบการเข้าถึงโมเดลแบบเปิดที่ดีที่สุดสำหรับการเขียนโค้ดอย่าง**เสถียร**
3. คัดสรรโมเดลที่**ผ่านการทดสอบและวัดประสิทธิภาพ**สำหรับ coding agent
4. **ไม่ผูกขาดการใช้งาน** โดยให้คุณใช้ผู้ให้บริการอื่นร่วมกับ OpenCode ได้
packages/web/src/content/docs/tr/go.mdx
+323 -217
View File
@@ -1,25 +1,36 @@
---
title: Go
description: Açık kodlama modelleri için düşük maliyetli abonelik.
description: İki kullanım katmanıyla açık kodlama modellerine güvenilir erişim.
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go, popüler açık kodlama modellerine güvenilir erişim sağlayan düşük maliyetli **aylık 10$ aboneliğidir**.
OpenCode Go, iki aylık planla popüler açık kodlama modellerine güvenilir erişim sağlar:
Go, OpenCode'daki diğer sağlayıcılar gibi çalışır. OpenCode Go'ya abone olur ve API anahtarınızı alırsınız. Bu **tamamen isteğe bağlıdır** ve OpenCode'u kullanmak için bunu kullanmanıza gerek yoktur.
| Plan | Fiyat | Dahil edilen kullanım |
| ---- | ----- | -------------- |
| **Go** | **aylık $10** | Aşağıdaki modellere daha düşük maliyetli erişim |
| **Go Plus** | **aylık $40** | Aşağıdaki modellerde daha yüksek kullanım limitleri |
Öncelikle uluslararası kullanıcılar için tasarlanmıştır ve dünya genelinde istikrarlı erişim sağlar.
Go, OpenCode içindeki diğer sağlayıcılar gibi çalışır. OpenCode Go'ya abone olur ve
API anahtarınızı alırsınız. Bu **tamamen isteğe bağlıdır**; OpenCode kullanmak için
Go kullanmanız gerekmez.
Hizmet öncelikle uluslararası kullanıcılar için tasarlanmıştır ve dünya genelinde istikrarlı erişim sağlar.
---
## Arka Plan
Açık modeller gerçekten çok iyi hale geldi. Artık kodlama görevleri için özel mülk modellere yakın bir performansa ulaşıyorlar. Ve birçok sağlayıcı onlara rekabetçi bir şekilde hizmet verebildiği için genellikle çok daha ucuzdurlar.
Açık modeller gerçekten çok iyi hale geldi. Artık kodlama görevlerinde
tescilli modellere yakın performans gösteriyorlar. Birçok sağlayıcı bunları
rekabetçi biçimde sunabildiği için genellikle çok daha ucuzlar.
Ancak, bu modellere güvenilir, düşük gecikmeli erişim sağlamak zor olabilir. Sağlayıcılar kalite ve erişilebilirlik açısından farklılık gösterir.
Ancak güvenilir ve düşük gecikmeli erişim sağlamak zor olabilir. Sağlayıcılar
kalite ve erişilebilirlik bakımından farklılık gösterir.
:::tip
OpenCode ile iyi çalışan seçili bir model ve sağlayıcı grubunu test ettik.
@@ -27,24 +38,30 @@ OpenCode ile iyi çalışan seçili bir model ve sağlayıcı grubunu test ettik
Bunu çözmek için birkaç şey yaptık:
1. Seçili bir grup açık modeli test ettik ve bu modelleri en iyi nasıl çalıştırabileceğimizi öğrenmek için ekipleriyle görüştük.
2. Ardından, bunların doğru şekilde sunulduğundan emin olmak için birkaç sağlayıcıyla birlikte çalıştık.
3. Son olarak, model/sağlayıcı kombinasyonunu kıyasladık (benchmark) ve gönül rahatlığıyla önerebileceğimiz bir liste oluşturduk.
1. Seçili açık modelleri test ettik ve en iyi nasıl çalıştırılacaklarını
ekipleriyle görüştük.
2. Ardından doğru şekilde sunulduklarından emin olmak için birkaç sağlayıcıyla
çalıştık.
3. Son olarak model/sağlayıcı kombinasyonlarını karşılaştırdık ve güvenle
önerebileceğimiz bir liste oluşturduk.
OpenCode Go, bu modellere **aylık 10$** karşılığında erişmenizi sağlar.
Hem Go hem de Go Plus bu modellere erişim sağlar; kullanım miktarınıza
uygun planı seçin.
---
## Nasıl çalışır?
OpenCode Go, OpenCode'daki diğer sağlayıcılar gibi çalışır.
OpenCode Go, OpenCode içindeki diğer sağlayıcılar gibi çalışır.
1. **<a href={console}>OpenCode Zen</a>**'e giriş yapın, Go'ya abone olun ve API anahtarınızı kopyalayın.
2. TUI'de `/connect` komutunu çalıştırın, `OpenCode Go`yu seçin ve API anahtarınızı yapıştırın.
3. Go üzerinden kullanabileceğiniz modellerin listesini görmek için TUI'de `/models` komutunu çalıştırın.
1. **<a href={console}>OpenCode Console</a>** oturumu açın, Go veya Go Plus'a abone olun ve
API anahtarınızı kopyalayın.
2. TUI içinde `/connect` komutunu çalıştırın, `OpenCode Go` seçin ve
API anahtarınızı yapıştırın.
3. Go üzerinden kullanılabilen modelleri görmek için TUI içinde `/models` çalıştırın.
:::note
Her çalışma alanından yalnızca bir üye OpenCode Go'ya abone olabilir.
Her çalışma alanında yalnızca bir üye OpenCode Go veya Go Plus abonesi olabilir.
:::
Mevcut model listesi şunları içerir:
@@ -54,13 +71,13 @@ Mevcut model listesi şunları içerir:
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free** (sınırlı bir süre için)
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,9 +88,7 @@ Mevcut model listesi şunları içerir:
- **Muse Spark 1.2 Contributor** ([sınırlı bölgeler](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
@@ -81,222 +96,318 @@ Mevcut model listesi şunları içerir:
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (sınırlı bir süre için)
- **LongCat 2.5 Preview Free** (sınırlı bir süre için)
Test edip yenilerini ekledikçe model listesi değişebilir.
Yeni modeller test edip ekledikçe liste değişebilir.
---
## Nerede kullanabilirim?
OpenCode Go, [OpenCode](https://opencode.ai) ve benzer türde istekler üreten diğer kodlama aracıları için tasarlanmıştır.
Trafik, diğer kullanıcıların deneyimini olumsuz etkileyen kötüye kullanımlara karşı izlenir.
OpenCode Go, [OpenCode](https://opencode.ai) ve benzer istekler üreten diğer kodlama aracıları
için tasarlanmıştır. Trafik, diğer kullanıcıların deneyimini olumsuz etkileyen
kötüye kullanımlara karşı izlenir.
İstemciniz şunları yapmalıdır:
1. Tipik kodlama aracısı trafiği göndermelidir.
2. Genel bir SDK veya HTTP kitaplığı adı yerine `my-coding-agent/1.0` gibi kendine ait bir user agent ile kendini tanıtmalıdır.
3. Yönlendirmeyi ve istem önbelleğe almayı optimize edebilmemiz için her konuşmada `x-opencode-session` içinde değişmeyen bir oturum kimliği göndermelidir.
2. Genel bir SDK veya HTTP kitaplığı adı yerine `my-coding-agent/1.0` gibi kendi
user agent değeriyle kendini tanıtmalıdır.
3. Yönlendirme ve istem önbelleğini optimize edebilmemiz için her konuşmada `x-opencode-session` içinde değişmeyen bir oturum kimliği göndermelidir.
### Doğrulanmış İstemciler
OpenCode'un yanı sıra aşağıdaki istemcilerin OpenCode Go ile düzgün çalıştığı doğrulanmıştır.
Ancak gelecekte de çalışmaya devam edeceklerini garanti etmiyoruz.
OpenCode dışında aşağıdaki istemcilerin düzgün çalıştığı doğrulanmıştır
OpenCode Go ile. Ancak gelecekte çalışmaya devam edeceklerini garanti etmiyoruz.
| İstemci | Oturum desteği |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Hermes** | [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) içeren derlemeler, ana ve yardımcı OpenCode isteklerinde başlığı gönderir. Düzeltme v0.21.0'dan sonra birleştirilmiştir; dolayısıyla v0.21.0 sürümü tek başına bu düzeltmeyi içermez. |
| **Claude Code** | Go, Claude Code'un yerel oturum başlığını tanır. Özel başlık ekleyen bir sarmalayıcı gerekmez. |
| **Codex** | Go, Codex'in yerel oturum başlığını tanır. Bazı sürümler ve proxy yapılandırmaları hâlâ bu başlığı göndermemektedir; istekleri iletirken oturum başlığını koruyun. |
| **ZCode** | Go, ZCode'un yerel oturum başlığını tanır. [`x-opencode-session` talebimiz](https://github.com/zai-org/feedback/issues/492) hâlâ açıktır ancak artık özellikle bu başlığın gönderilmesi gerekli değildir. |
| **Pi** | Güncel derlemeler OpenCode için oturum bilgilerini gönderir. Eski kurulumları güncelleyin. |
| **jcode** | [Oturum başlığı düzeltmesini](https://github.com/1jehuang/jcode/issues/1167) içeren **v0.81.6 veya sonraki bir sürüme** güncelleyin. |
| **Kilo Code CLI** | [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) içeren derlemeler OpenCode oturum başlıklarını geri getirir. Bu düzeltme CLI'ı kapsar, VS Code uzantısını kapsamaz. Bkz. [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
| İstemci | Oturum desteği |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) içeren derlemeler ana ve yardımcı OpenCode isteklerinde başlığı gönderir. Düzeltme v0.21.0 sonrasında birleştirilmiştir; bu sürüm tek başına düzeltmeyi içermez. |
| **Claude Code** | Go, yerel oturum başlığını tanır. Özel başlık sarmalayıcısı gerekmez. |
| **Codex** | Go, yerel oturum başlığını tanır. Bazı sürümler ve proxy yapılandırmaları hâlâ başlığı atlar; istekleri iletirken oturum başlığını koruyun. |
| **ZCode** | Go, yerel oturum başlığını tanır. [`x-opencode-session` talebimiz](https://github.com/zai-org/feedback/issues/492) hâlâ açıktır ancak artık özellikle bu başlığı göndermek gerekmez. |
| **Pi** | Güncel derlemeler OpenCode için oturum bilgisi gönderir. Eski kurulumları güncelleyin. |
| **jcode** | [Oturum başlığı düzeltmesini](https://github.com/1jehuang/jcode/issues/1167) içeren **v0.81.6 veya sonraki bir sürüme** güncelleyin. |
| **Kilo Code CLI** | [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) içeren derlemeler OpenCode oturum başlıklarını geri getirir. Düzeltme CLI'ı kapsar, VS Code uzantısını kapsamaz. Bkz. [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723). |
### Sorunlu Olduğu Bilinen İstemciler
Bu istemcilerin incelediğimiz sürümlerinde oturum desteği eksik veya tamamlanmamıştır.
Bağlantı verilen bildirimlerden düzeltmeleri ve geçici çözümleri takip edebilirsiniz.
Bağlantılı bildirimlerden düzeltmeler ve geçici çözümler izlenebilir.
| İstemci | Durum ve takip |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | Oturum bilgileri bazı model yollarında ulaşırken diğerlerinde eksiktir. Go, DeepSeek Harness'ın yerel başlığını tanır; yapılması gereken, bu başlığın tüm adaptörlerden gönderilmesidir. [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
| **GitHub Copilot Chat** | Otomatik oturum başlığı desteği [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) içinde talep edilmiştir. |
| **Kimi Code** | Otomatik oturum başlığı desteği [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) içinde talep edilmiştir. |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) için [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327) içinde bir düzeltme önerilmiştir ancak henüz birleştirilmemiştir. |
| İstemci | Durum ve takip |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | Oturum bilgisi bazı model yollarında gelirken diğerlerinde eksiktir. Go yerel başlığı tanır; kalan iş, başlığın tüm adaptörlerden gönderilmesidir. [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
| **GitHub Copilot Chat** | Otomatik oturum başlığı desteği [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) içinde talep edilmiştir. |
| **Kimi Code** | Otomatik oturum başlığı desteği [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) içinde talep edilmiştir. |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) için [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327) içinde henüz birleştirilmemiş bir düzeltme önerilmiştir. |
## Kullanım limitleri
Kullanım limitleri aylık dolar tutarları olarak tanımlanır. Aşağıdaki tabloda her modelin aylık limiti ve token maliyetleri gösterilmektedir.
Kullanım limitleri aylık dolar tutarları olarak tanımlanır. Aşağıdaki tablo her planın
aylık limitini ve her modelin token maliyetini gösterir. Token fiyatları
Go ve Go Plus için aynıdır.
Her model için şu kullanım limitleri geçerlidir: 5 saatlik — aylık limitin %20'si; haftalık — %50'si; aylık — %100'ü.
Her modelde şu limitler geçerlidir: 5 saatlik — aylık limitin %20'si;
haftalık — %50'si; aylık — %100'ü.
Örneğin bir modelin aylık limiti $60 ise şu tutarlara kadar kullanım yapabilirsiniz:
Örneğin bir modelin aylık limiti Go için $60, Go Plus için $120 ise
şu tutarlara kadar harcayabilirsiniz:
- **5 saatlik limit** — $12 tutarında kullanım
- **Haftalık limit** — $30 tutarında kullanım
- **Aylık limit** — $60 tutarında kullanım
- **5 saatlik limit** — Go ile $12 veya Go Plus ile $24
- **Haftalık limit** — Go ile $30 veya Go Plus ile $60
- **Aylık limit** — Go ile $60 veya Go Plus ile $120
Modeller genelinde Go için 5 saatlik $12, haftalık $30 ve aylık $60 kullanım hakkı;
Go Plus için 5 saatlik $48, haftalık $120 ve aylık $240 kullanım hakkı vardır. Aşağıdaki
model aylık limitleri, kullanımın bu haklara nasıl
yansıyacağını belirler.
Token fiyatları 1M token başına verilmiştir.
| Model | Input | Output | Cached Read | Cached Write | Aylık limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ------------------------------------------------------ |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **Sınırsız**<br /><small>sınırlı bir süre için</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **Sınırsız**<br /><small>sınırlı bir süre için</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| Model | Girdi | Çıktı | Önbellek okuma | Önbellek yazma | Aylık limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | Ücretsiz | Ücretsiz | Ücretsiz | - | **Sınırsız**<br /><small>sınırlı bir süre için</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Ücretsiz | Ücretsiz | Ücretsiz | - | **Sınırsız**<br /><small>sınırlı bir süre için</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| Model | Girdi | Çıktı | Önbellek okuma | Önbellek yazma | Aylık limit |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | Ücretsiz | Ücretsiz | Ücretsiz | - | **Sınırsız**<br /><small>sınırlı bir süre için</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | Ücretsiz | Ücretsiz | Ücretsiz | - | **Sınırsız**<br /><small>sınırlı bir süre için</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** Sınırlı bir süre için ücretsiz.
**LongCat 2.5 Preview Free:** Sınırlı bir süre için ücretsiz.
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak saatleri pazartesiden cumaya 01:00-04:00 ve 06:00-10:00 UTC'dir; hafta sonları dahil diğer tüm saatler Off-Peak'tir. [Daha fazla bilgi](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak saatleri 01:00-04:00 and 06:00-10:00 UTC, pazartesiden cumaya geçerlidir; hafta sonları dahil diğer tüm saatler Off-Peak'tir. [Daha fazla bilgi](https://api-docs.deepseek.com/quick_start/pricing/).
**DeepSeek V4 Flash Vision Exp:** Görseller boyutlarına göre token'lara dönüştürülür ve metin token'larıyla birlikte girdi token'ları olarak ücretlendirilir. [Daha fazla bilgi](https://api-docs.deepseek.com/quick_start/pricing/).
### Tahmini istek sayısı
### Tahmini istekler
Aşağıdaki tabloda tipik Go kullanım modellerine dayalı tahmini istek sayısı verilmiştir:
Aşağıdaki tablolar tipik Go kullanımına göre tahmini istek sayılarını gösterir. Go
Plus tahminleri her modelin daha yüksek kullanım limitine göre ölçeklenir.
| Model | 5 saatte bir istek | haftalık istek | aylık istek |
| ---------------------------- | ------------------ | -------------- | ----------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Sınırsız | Sınırsız | Sınırsız |
| LongCat 2.5 Preview Free | Sınırsız | Sınırsız | Sınırsız |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
Tahminler istek başına aşağıdaki token sayılarını kullanır; gerçek kullanım değişir.
| Model | 5 saatteki istek | Haftalık istek | Aylık istek |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | Sınırsız | Sınırsız | Sınırsız |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | Sınırsız | Sınırsız | Sınırsız |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
- Grok 4.7/4.6 — İstek başına 390 girdi, 32.500 önbelleğe alınmış, 120 çıktı token'ı
- GLM-5.3-Flash — İstek başına 1.000 girdi, 55.000 önbelleğe alınmış, 200 çıktı token'ı
- GLM-5.3/5.2/5.1 — İstek başına 700 girdi, 52.000 önbelleğe alınmış, 150 çıktı token'ı
- GPT 6 Luna — İstek başına 1.000 girdi, 50.000 önbelleğe alınmış, 220 çıktı token'ı
- GPT 5.6 Luna — İstek başına 1.000 girdi, 50.000 önbelleğe alınmış, 220 çıktı token'ı
- Kimi K3 — İstek başına 1.050 girdi, 76.500 önbelleğe alınmış, 300 çıktı token'ı
- Kimi K2.7/K2.6 — İstek başına 870 girdi, 55.000 önbelleğe alınmış, 200 çıktı token'ı
- LongCat-2.0 — İstek başına 920 girdi, 88.900 önbelleğe alınmış, 200 çıktı token'ı
- DeepSeek V4.1 Flash — İstek başına 410 girdi, 71.300 önbelleğe alınmış, 310 çıktı token'ı
- DeepSeek V4 Pro — İstek başına 750 girdi, 82.000 önbelleğe alınmış, 290 çıktı token'ı
- DeepSeek V4 Flash — İstek başına 410 girdi, 71.300 önbelleğe alınmış, 310 çıktı token'ı
- DeepSeek V4 Flash Vision Exp — İstek başına 410 girdi, 71.300 önbelleğe alınmış, 310 çıktı token'ı
- MiniMax M3 — İstek başına 510 girdi, 56.000 önbelleğe alınmış, 190 çıktı token'ı
- MiniMax M2.7 — İstek başına 300 girdi, 55.000 önbelleğe alınmış, 125 çıktı token'ı
- Muse Spark 1.3 Contributor — İstek başına 620 girdi, 71.400 önbelleğe alınmış, 300 çıktı token'ı
- Muse Spark 1.2 Contributor — İstek başına 620 girdi, 71.400 önbelleğe alınmış, 300 çıktı token'ı
- Qwen3.8 Max — İstek başına 420 girdi, 66.000 önbelleğe alınmış, 200 çıktı token'ı
- Qwen3.8 Flash — İstek başına 600 girdi, 58.000 önbelleğe alınmış, 200 çıktı token'ı
- Qwen3.7 Max — İstek başına 420 girdi, 66.000 önbelleğe alınmış, 200 çıktı token'ı
- Qwen3.7 Plus — İstek başına 500 girdi, 57.000 önbelleğe alınmış, 190 çıktı token'ı
- Qwen3.6 Plus — İstek başına 500 girdi, 57.000 önbelleğe alınmış, 190 çıktı token'ı
- Hy4 preview — İstek başına 830 girdi, 71.500 önbelleğe alınmış, 295 çıktı token'ı
- Hy3 — İstek başına 830 girdi, 71.500 önbelleğe alınmış, 295 çıktı token'ı
- MiMo-V2.6-Flash — İstek başına 830 girdi, 71.500 önbelleğe alınmış, 295 çıktı token'ı
- MiMo-V2.6-Pro — İstek başına 790 girdi, 86.000 önbelleğe alınmış, 305 çıktı token'ı
- MiMo-V2.5 — İstek başına 830 girdi, 71.500 önbelleğe alınmış, 295 çıktı token'ı
- MiMo-V2.5-Pro — İstek başına 790 girdi, 86.000 önbelleğe alınmış, 305 çıktı token'ı
</TabItem>
<TabItem label="Go Plus">
| Model | 5 saatteki istek | Haftalık istek | Aylık istek |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Sınırsız | Sınırsız | Sınırsız |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | Sınırsız | Sınırsız | Sınırsız |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
Tahminlerde istek başına aşağıdaki token sayıları kullanılır; gerçek kullanım değişebilir.
- Grok 4.7/4.6 — 390 girdi, 32,500 önbelleğe alınmış, 120 çıktı token'ı/istek
- GLM-5.3-Flash — 1,000 girdi, 55,000 önbelleğe alınmış, 200 çıktı token'ı/istek
- GLM-5.3/5.2 — 700 girdi, 52,000 önbelleğe alınmış, 150 çıktı token'ı/istek
- GPT 6 Luna — 1,000 girdi, 50,000 önbelleğe alınmış, 220 çıktı token'ı/istek
- GPT 5.6 Luna — 1,000 girdi, 50,000 önbelleğe alınmış, 220 çıktı token'ı/istek
- Kimi K3 — 1,050 girdi, 76,500 önbelleğe alınmış, 300 çıktı token'ı/istek
- Kimi K2.7/K2.6 — 870 girdi, 55,000 önbelleğe alınmış, 200 çıktı token'ı/istek
- LongCat-2.0 — 920 girdi, 88,900 önbelleğe alınmış, 200 çıktı token'ı/istek
- DeepSeek V4.1 Flash — 410 girdi, 71,300 önbelleğe alınmış, 310 çıktı token'ı/istek
- DeepSeek V4 Pro — 750 girdi, 82,000 önbelleğe alınmış, 290 çıktı token'ı/istek
- DeepSeek V4 Flash — 410 girdi, 71,300 önbelleğe alınmış, 310 çıktı token'ı/istek
- DeepSeek V4 Flash Vision Exp — 410 girdi, 71,300 önbelleğe alınmış, 310 çıktı token'ı/istek
- MiniMax M3 — 510 girdi, 56,000 önbelleğe alınmış, 190 çıktı token'ı/istek
- MiniMax M2.7 — 300 girdi, 55,000 önbelleğe alınmış, 125 çıktı token'ı/istek
- Muse Spark 1.3 Contributor — 620 girdi, 71,400 önbelleğe alınmış, 300 çıktı token'ı/istek
- Muse Spark 1.2 Contributor — 620 girdi, 71,400 önbelleğe alınmış, 300 çıktı token'ı/istek
- MiMo-V2.6-Flash — 830 girdi, 71,500 önbelleğe alınmış, 295 çıktı token'ı/istek
- MiMo-V2.6-Pro — 790 girdi, 86,000 önbelleğe alınmış, 305 çıktı token'ı/istek
- MiMo-V2.5 — 830 girdi, 71,500 önbelleğe alınmış, 295 çıktı token'ı/istek
- MiMo-V2.5-Pro — 790 girdi, 86,000 önbelleğe alınmış, 305 çıktı token'ı/istek
- Qwen3.8 Max — 420 girdi, 66,000 önbelleğe alınmış, 200 çıktı token'ı/istek
- Qwen3.8 Flash — 600 girdi, 58,000 önbelleğe alınmış, 200 çıktı token'ı/istek
- Qwen3.7 Plus — 500 girdi, 57,000 önbelleğe alınmış, 190 çıktı token'ı/istek
- Hy4 preview — 830 girdi, 71,500 önbelleğe alınmış, 295 çıktı token'ı/istek
- Hy3 — 830 girdi, 71,500 önbelleğe alınmış, 295 çıktı token'ı/istek
Mevcut kullanımınızı **<a href={console}>konsoldan</a>** takip edebilirsiniz.
:::tip
Kullanım sınırına ulaşırsanız, ücretsiz modelleri kullanmaya devam edebilirsiniz.
Kullanım limitine ulaşırsanız ücretsiz modelleri kullanmaya devam edebilirsiniz.
:::
Erken kullanımlardan ve geri bildirimlerden edindiğimiz deneyimlere bağlı olarak kullanım limitleri değişebilir.
İlk kullanımlardan ve geri bildirimlerden öğrendiklerimize göre kullanım limitleri değişebilir.
---
### Limit dışı kullanım
Eğer Zen bakiyenizde kredileriniz varsa, konsoldan **Bakiye kullan (Use balance)** seçeneğini etkinleştirebilirsiniz. Bu özellik etkinleştirildiğinde, kullanım limitlerinize ulaştıktan sonra Go, istekleri engellemek yerine Zen bakiyenizi kullanmaya devam edecektir.
Zen bakiyenizde krediniz varsa konsolda **Use balance** seçeneğini
etkinleştirebilirsiniz. Etkinleştirildiğinde Go, kullanım limitlerine ulaştıktan sonra istekleri
engellemek yerine Zen bakiyenizi kullanır.
---
### Bazı modellerin kullanımı neden daha düşük?
Go ile aylık 10$ ödersiniz ve sunulan aylık kullanım modele göre değişir.
Go ile sunulan aylık kullanım modele göre değişir.
Çoğu modelde bunu toplu indirimler ve ayrılmış GPU kapasitesi sayesinde mümkün kılıyoruz. Ardından bu tasarrufları daha fazla aylık kullanım olarak size aktarıyoruz.
Çoğu modelde bunu toplu indirimler ve ayrılmış GPU kapasitesiyle sağlıyor, tasarrufu daha yüksek aylık kullanım olarak size aktarıyoruz.
Bazı modellerde ise model yeni olduğu veya herkese açık fiyatlandırması zaten indirimli olduğu için henüz indirim pazarlığı yapma ya da modeli daha düşük maliyetle barındırma fırsatımız olmadı.
Bazı modeller yeni olduğu veya herkese açık fiyatı zaten indirimli olduğu için henüz indirim pazarlığı yapma ya da daha düşük maliyetle barındırma fırsatımız olmadı.
Bu modellerde bile model sağlayıcılarına doğrudan ödeme yaptığınız duruma kıyasla biraz daha fazla kullanım elde edersiniz; bu nedenle sunulan aylık kullanım daha azdır.
Bu modellerde yine de sağlayıcılara doğrudan ödeme yapmaya göre biraz daha fazla kullanım elde edersiniz; dahil edilen aylık kullanım bu nedenle daha düşüktür.
---
## Uç Noktalar
Go modellerine aşağıdaki API uç noktaları aracılığıyla da erişebilirsiniz.
Go modellerine aşağıdaki API uç noktalarından da erişebilirsiniz.
| Model | Model ID | Uç Nokta | AI SDK Paketi |
| Model | Model ID | Uç Nokta | AI SDK Paketi |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -305,11 +416,11 @@ Go modellerine aşağıdaki API uç noktaları aracılığıyla da erişebilirsi
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -320,26 +431,24 @@ Go modellerine aşağıdaki API uç noktaları aracılığıyla da erişebilirsi
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
OpenCode yapılandırmanızdaki [model id](/docs/config/#models) formatı `opencode-go/<model-id>` şeklindedir. Örneğin, Kimi K3 için yapılandırmanızda `opencode-go/kimi-k3` kullanmalısınız.
OpenCode yapılandırmanızdaki [model id](/docs/config/#models)
`opencode-go/<model-id>` biçimini kullanır. Örneğin Kimi K3 için
yapılandırmanızda `opencode-go/kimi-k3` kullanırsınız.
---
### Modeller
Mevcut modellerin tam listesini ve metadata'larını şuradan alabilirsiniz:
Mevcut modellerin tam listesini ve metadata bilgilerini şuradan alabilirsiniz:
```
https://opencode.ai/zen/go/v1/models
@@ -350,46 +459,43 @@ https://opencode.ai/zen/go/v1/models
## Gizlilik
| Model | Model eğitimi | Veri saklama |
| ---------------------------- | ------------- | ------------ |
| Grok 4.7 | Kullanılmaz | 30 gün |
| Grok 4.6 | Kullanılmaz | 30 gün |
| GPT 6 Luna | Kullanılmaz | 30 gün |
| GPT 5.6 Luna | Kullanılmaz | 30 gün |
| GLM-5.3-Flash | Kullanılmaz | 0 gün |
| GLM-5.3 | Kullanılmaz | 0 gün |
| GLM-5.2 | Kullanılmaz | 0 gün |
| GLM-5.1 | Kullanılmaz | 0 gün |
| Kimi K3 | Kullanılmaz | 0 gün |
| Kimi K2.7 Code | Kullanılmaz | 0 gün |
| Kimi K2.6 | Kullanılmaz | 0 gün |
| LongCat-2.0 | Kullanılmaz | 0 gün |
| MiMo-V2.6-Pro | Kullanılmaz | 0 gün |
| MiMo-V2.6-Flash | Kullanılmaz | 0 gün |
| MiMo-V2.5-Pro | Kullanılmaz | 0 gün |
| MiMo-V2.5 | Kullanılmaz | 0 gün |
| Qwen3.8 Max | Kullanılmaz | 0 gün |
| Qwen3.8 Flash | Kullanılmaz | 0 gün |
| Qwen3.7 Max | Kullanılmaz | 0 gün |
| Qwen3.7 Plus | Kullanılmaz | 0 gün |
| Qwen3.6 Plus | Kullanılmaz | 0 gün |
| MiniMax M3 | Kullanılmaz | 0 gün |
| MiniMax M2.7 | Kullanılmaz | 0 gün |
| Muse Spark 1.3 Contributor | Evet | ZDR değil |
| Muse Spark 1.2 Contributor | Evet | ZDR değil |
| DeepSeek V4.1 Flash | Kullanılmaz | 0 gün |
| DeepSeek V4 Pro | Kullanılmaz | 0 gün |
| DeepSeek V4 Flash | Kullanılmaz | 0 gün |
| DeepSeek V4 Flash Vision Exp | Kullanılmaz | 0 gün |
| Hy4 preview | Kullanılmaz | 0 gün |
| Hy3 | Kullanılmaz | 0 gün |
| Space Bunny Free | Kullanılmaz | 0 gün |
| LongCat 2.5 Preview Free | Kullanılmaz | 0 gün |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | Kullanılmaz | 30 gün |
| Grok 4.6 | Kullanılmaz | 30 gün |
| GPT 6 Luna | Kullanılmaz | 30 gün |
| GPT 5.6 Luna | Kullanılmaz | 30 gün |
| GLM-5.3-Flash | Kullanılmaz | 0 gün |
| GLM-5.3 | Kullanılmaz | 0 gün |
| GLM-5.2 | Kullanılmaz | 0 gün |
| Kimi K3 | Kullanılmaz | 0 gün |
| Kimi K2.7 Code | Kullanılmaz | 0 gün |
| Kimi K2.6 | Kullanılmaz | 0 gün |
| LongCat-2.0 | Kullanılmaz | 0 gün |
| MiMo-V2.6-Pro | Kullanılmaz | 0 gün |
| MiMo-V2.6-Flash | Kullanılmaz | 0 gün |
| MiMo-V2.5-Pro | Kullanılmaz | 0 gün |
| MiMo-V2.5 | Kullanılmaz | 0 gün |
| Qwen3.8 Max | Kullanılmaz | 0 gün |
| Qwen3.8 Flash | Kullanılmaz | 0 gün |
| Qwen3.7 Plus | Kullanılmaz | 0 gün |
| MiniMax M3 | Kullanılmaz | 0 gün |
| MiniMax M2.7 | Kullanılmaz | 0 gün |
| Muse Spark 1.3 Contributor | Evet | ZDR değil |
| Muse Spark 1.2 Contributor | Evet | ZDR değil |
| DeepSeek V4.1 Flash | Kullanılmaz | 0 gün\* |
| DeepSeek V4 Pro | Kullanılmaz | 0 gün\* |
| DeepSeek V4 Flash | Kullanılmaz | 0 gün\* |
| DeepSeek V4 Flash Vision Exp | Kullanılmaz | 0 gün\* |
| Hy4 preview | Kullanılmaz | 0 gün |
| Hy3 | Kullanılmaz | 0 gün |
| Space Bunny Free | Kullanılmaz | 0 gün |
| LongCat 2.5 Preview Free | Kullanılmaz | 0 gün |
- **Grok 4.7/4.6:** 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).
- **Grok 4.7/4.6:** ZDR, durum bilgisi tutan Responses API, Files and Collections ve Batch API dahil 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 6 Luna / 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).
- **Muse Spark 1.3 Contributor:** İstemlerinizi ve tamamlamalarınızı gelecekteki Meta modellerini eğitmek için kullanma izni karşılığında büyük ölçüde indirimli token fiyatları. Kullanılabilirlik, Meta'nın [Coğrafi Kullanım Politikası](https://ai.developer.meta.com/legal/geographic-use-policy) kapsamında izin verilen bölgelerle sınırlıdır. [Daha fazla bilgi](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** İstemlerinizi ve tamamlamalarınızı gelecekteki Meta modellerini eğitmek için kullanma izni karşılığında büyük ölçüde indirimli token fiyatları. Kullanılabilirlik, Meta'nın [Coğrafi Kullanım Politikası](https://ai.developer.meta.com/legal/geographic-use-policy) kapsamında izin verilen bölgelerle sınırlıdır. [Daha fazla bilgi](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR anlaşması aylık olarak yenilenir. Mevcut anlaşma 30 Eylül 2026 tarihine kadar geçerlidir.
- **Muse Spark 1.3 Contributor:** İstem ve tamamlamalarınızı gelecekteki Meta modellerini eğitmekte kullanma izni karşılığında token fiyatları büyük ölçüde indirilir. Kullanılabilirlik Meta'nın [Coğrafi Kullanım Politikası](https://ai.developer.meta.com/legal/geographic-use-policy) kapsamındaki bölgelerle sınırlıdır. [Daha fazla bilgi](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **Muse Spark 1.2 Contributor:** İstem ve tamamlamalarınızı gelecekteki Meta modellerini eğitmekte kullanma izni karşılığında token fiyatları büyük ölçüde indirilir. Kullanılabilirlik Meta'nın [Coğrafi Kullanım Politikası](https://ai.developer.meta.com/legal/geographic-use-policy) kapsamındaki bölgelerle sınırlıdır. [Daha fazla bilgi](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
- **DeepSeek:** ZDR anlaşması aylık yenilenir. Mevcut anlaşma 31 Ekim 2026 tarihine kadar geçerlidir.
---
@@ -397,7 +503,7 @@ https://opencode.ai/zen/go/v1/models
OpenCode Go'yu şu amaçlarla oluşturduk:
1. Düşük maliyetli bir abonelik ile yapay zeka destekli kodlamayı daha fazla kişi için **erişilebilir** kılmak.
1. Düşük maliyetli abonelikle yapay zekâ destekli kodlamayı daha fazla kişi için **erişilebilir** kılmak.
2. En iyi açık kodlama modellerine **güvenilir** erişim sağlamak.
3. Kodlama aracısı (agent) kullanımı için **test edilmiş ve kıyaslanmış** modelleri bir araya getirmek.
4. OpenCode ile diğer sağlayıcıları da kullanmanıza olanak tanıyarak **kilitlenme (vendor lock-in) olmamasını** sağlamak.
3. Kodlama aracısı kullanımı için **test edilmiş ve kıyaslanmış** modelleri seçmek.
4. OpenCode ile diğer sağlayıcıları da kullanmanıza izin vererek **bağımlılık oluşturmamak**.
packages/web/src/content/docs/zh-cn/go.mdx
+287 -208
View File
@@ -1,25 +1,31 @@
---
title: Go
description: 低成本的开源编程模型订阅服务。
description: 通过两种用量方案，稳定访问开源编程模型。
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go 是一项**每月 10 美元的低成本订阅服务**，让你能够稳定地访问流行的开源编程模型。
OpenCode Go 让你能够稳定访问流行的开源编程模型，并提供两种月度方案：
Go 的工作方式与 OpenCode 中的任何其他提供商（provider）一样。订阅 OpenCode Go 后你将获得 API 密钥。它是 **完全可选** 的，并非使用 OpenCode 所必需的条件。
| 方案 | 价格 | 包含的用量 |
| ---- | ----- | -------------- |
| **Go** | **$10/月** | 以较低成本访问下列模型 |
| **Go Plus** | **$40/月** | 下列模型均享有更高的用量限制 |
它主要面向国际用户，并提供稳定的全球访问。
Go 的工作方式与 OpenCode 中的其他提供商一样。订阅 OpenCode Go 后，你将获得 API 密钥。它是**完全可选**的，并非使用 OpenCode 所必需。
该服务主要面向国际用户，并提供稳定的全球访问。
---
## 背景
开源模型现在变得非常强大。在编程任务中，它们的性能已接近专有模型。由于许多提供商都可以提供具有竞争力的服务，它们通常要便宜得多。
开源模型已经变得非常强大。在编程任务中，它们的性能已接近专有模型。由于许多提供商都能以有竞争力的价格提供服务，它们通常便宜得多。
然而，获得可靠、低延迟的访问可能很困难。各提供商在质量和可用性方面参差不齐。
然而，要获得可靠、低延迟的访问可能很困难。各提供商在质量和可用性方面参差不齐。
:::tip
我们测试了一组经过精选且与 OpenCode 配合良好的模型和提供商。
@@ -27,11 +33,11 @@ Go 的工作方式与 OpenCode 中的任何其他提供商（provider）一样
为了解决这个问题，我们做了以下几件事：
1. 我们测试了一组精选的开源模型，并与他们的团队探讨了如何以最佳方式运行它们。
2. 随后我们与一些提供商合作，以确保正确提供这些服务。
3. 最后，我们对模型和提供商的组合进行了基准测试（benchmark），得出了一份我们乐于推荐的列表。
1. 我们测试了一组精选的开源模型，并与其团队探讨了如何以最佳方式运行它们。
2. 随后，我们与一些提供商合作，确保这些模型得到正确的服务。
3. 最后，我们对模型与提供商的组合进行了基准测试，整理出一份值得推荐的列表。
OpenCode Go 让你能够以**每月 10 美元**的价格访问这些模型。
Go 和 Go Plus 均可访问这些模型；请根据你的使用量选择合适的方案。
---
@@ -39,28 +45,28 @@ OpenCode Go 让你能够以**每月 10 美元**的价格访问这些模型。
OpenCode Go 的工作方式与 OpenCode 中的其他提供商一样。
1. 登录 **<a href={console}>OpenCode Zen</a>**，订阅 Go，然后复制你的 API 密钥。
1. 登录 **<a href={console}>OpenCode Console</a>**，订阅 Go 或 Go Plus，然后复制你的 API 密钥。
2. 在 TUI 中运行 `/connect` 命令，选择 `OpenCode Go`，然后粘贴你的 API 密钥。
3. 在 TUI 中运行 `/models` 以查看通过 Go 可用的模型列表。
3. 在 TUI 中运行 `/models`，查看可通过 Go 使用的模型列表。
:::note
每个工作空间只能有一名成员订阅 OpenCode Go。
每个工作空间只能有一名成员订阅 OpenCode Go 或 Go Plus。
:::
当前支持的模型列表包括：
当前的模型列表包括：
- **Grok 4.7**
- **Grok 4.6**
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free**（限时）
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,119 +77,162 @@ OpenCode Go 的工作方式与 OpenCode 中的其他提供商一样。
- **Muse Spark 1.2 Contributor** ([仅限部分地区](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
- **DeepSeek V4 Flash Vision Exp**
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (限时)
- **LongCat 2.5 Preview Free** (限时)
- **Space Bunny Free**（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。
随着我们测试并添加新模型，该列表可能会发生变化。
---
## 可以在哪里使用？
OpenCode Go 适用于 [OpenCode](https://opencode.ai) 以及其他会产生类似请求的编程 Agent。
我们会监控流量，以识别影响其他用户体验的滥用行为。
OpenCode Go 适用于 [OpenCode](https://opencode.ai) 以及其他会产生类似请求的编程 Agent。我们会监控流量，识别影响其他用户体验的滥用行为。
你的客户端应当：
1. 发送典型的编程 Agent 流量。
1. 发送典型的编程 Agent 流量
2. 使用自身专属的 user agent 标识（例如 `my-coding-agent/1.0`），而不是通用的 SDK 或 HTTP 库名称。
3. 为每段对话在 `x-opencode-session` 请求头中发送稳定的会话 ID，以便我们优化路由和提示词缓存。
3. 为每段对话在 `x-opencode-session` 中发送稳定的会话 ID，以便我们优化路由和提示词缓存。
### 已验证的客户端
除 OpenCode 外，以下客户端已通过验证，能够正常使用 OpenCode Go。但我们无法保证它们未来仍能正常使用。
| 客户端 | 会话支持 |
| ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | 包含 [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) 的构建版本会在主要和辅助 OpenCode 请求中发送该请求头。此修复在 v0.21.0 发布后才合并，因此 v0.21.0 本身并不包含该修复。 |
| **Claude Code** | Go 能识别其原生会话请求头，无需额外封装来添加自定义请求头。 |
| **Codex** | Go 能识别其原生会话请求头。某些版本和代理配置仍会遗漏该请求头；转发请求时请保留会话请求头。 |
| **ZCode** | Go 能识别其原生会话请求头。我们[请求支持 `x-opencode-session` 的 issue](https://github.com/zai-org/feedback/issues/492) 仍处于开放状态，但已不再需要发送这一特定请求头。 |
| **Pi** | 当前构建版本会为 OpenCode 发送会话信息。请更新旧版安装。 |
| **jcode** | 请更新至 **v0.81.6 或更高版本**，其中包含[会话请求头修复](https://github.com/1jehuang/jcode/issues/1167)。 |
| 客户端 | 会话支持 |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | 包含 [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) 的构建版本会在主要和辅助 OpenCode 请求中发送该请求头。此修复在 v0.21.0 发布后才合并，因此该版本本身并不包含此修复。 |
| **Claude Code** | Go 能识别其原生会话请求头，无需自定义请求头封装。 |
| **Codex** | Go 能识别其原生会话请求头。某些版本和代理配置仍会遗漏该请求头；转发请求时请保留会话请求头。 |
| **ZCode** | Go 能识别其原生会话请求头。我们[请求支持 `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) 仍处于开放状态，但已不再需要发送这一特定请求头。 |
| **Pi** | 当前构建版本会为 OpenCode 发送会话信息。请更新旧版安装。 |
| **jcode** | 请更新至 **v0.81.6 或更高版本**，其中包含[会话请求头修复](https://github.com/1jehuang/jcode/issues/1167)。 |
| **Kilo Code CLI** | 包含 [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) 的构建版本恢复了 OpenCode 会话请求头。此修复仅适用于 CLI，不适用于 VS Code 扩展。参见 [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723)。 |
### 已知存在问题的客户端
在我们调查的版本中，以下客户端缺少会话支持，或支持不完整。相关报告链接可用于跟踪修复进展和临时解决方案。
| 客户端 | 状态与跟踪 |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 客户端 | 状态与跟踪 |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | 某些模型调用路径会传递会话信息，但其他路径中缺失。我们能识别其原生请求头；剩余工作是在所有适配器中发送该请求头。参见[讨论 #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495)。 |
| **GitHub Copilot Chat** | [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) 已提出自动发送会话请求头的支持请求。 |
| **Kimi Code** | [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) 已提出自动发送会话请求头的支持请求。 |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) 已有拟议修复 [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327)，但尚未合并。 |
| **GitHub Copilot Chat** | [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) 已提出自动发送会话请求头的支持请求。 |
| **Kimi Code** | [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) 已提出自动发送会话请求头的支持请求。 |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) 已有拟议修复 [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327)，但尚未合并。 |
## 使用限制
使用限制以每月美元金额定义。下表列出了每个模型的每月限制和 token 成本。
使用限制以每月美元金额定义。下表列出了每种方案的每月限制和各模型的 token 成本。Go 与 Go Plus 的 token 价格相同。
每个模型都有以下使用限制：5 小时 — 每月限制的 20%；每周 — 50%；每月 — 100%。
例如，如果某个模型的每月限制为 $60，你最多可以使用：
例如，如果某个模型在 Go 的每月限制为 $60，在 Go Plus 的每月限制为 $120，你最多可以使用：
- **5 小时限制** — $12 的使用额度
- **每周限制** — $30 的使用额度
- **每月限制** — $60 的使用额度
- **5 小时限制** — Go 为 $12，Go Plus 为 $24
- **每周限制** — Go 为 $30，Go Plus 为 $60
- **每月限制** — Go 为 $60，Go Plus 为 $120
Token 价格按每 1M tokens 列示。
跨模型计算时，Go 的 5 小时、每周和每月额度分别为 $12、$30 和 $60；Go Plus 则分别为 $48、$120 和 $240。下方每个模型的每月限制决定其用量如何计入这些额度。
| 模型 | 输入 | 输出 | 缓存读取 | 缓存写入 | 每月限制 |
| --------------------------------------- | ------ | ------ | --------- | -------- | ----------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **无限制**<br /><small>限时</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **无限制**<br /><small>限时</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
Token 价格按每 1M tokens 计算。
<Tabs syncKey="go-plan">
<TabItem label="Go">
| 模型 | 输入 | 输出 | 缓存读取 | 缓存写入 | 每月限制 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | 免费 | 免费 | 免费 | - | **无限制**<br /><small>限时</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | 免费 | 免费 | 免费 | - | **无限制**<br /><small>限时</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| 模型 | 输入 | 输出 | 缓存读取 | 缓存写入 | 每月限制 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | 免费 | 免费 | 免费 | - | **无限制**<br /><small>限时</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | 免费 | 免费 | 免费 | - | **无限制**<br /><small>限时</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** 限时免费。
@@ -191,103 +240,140 @@ Token 价格按每 1M tokens 列示。
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak 时段为周一至周五的 01:00-04:00 和 06:00-10:00 UTC；其他所有时段（包括周末）均为 Off-Peak。[了解更多](https://api-docs.deepseek.com/quick_start/pricing/)。
**DeepSeek V4 Flash Vision Exp:** 图片会根据尺寸转换为 token，并与文本 token 一起按输入 token 计费。 [了解更多](https://api-docs.deepseek.com/quick_start/pricing/)。
**DeepSeek V4 Flash Vision Exp:** 图片会根据尺寸转换为 token，并与文本 token 一起按输入 token 计费。[了解更多](https://api-docs.deepseek.com/quick_start/pricing/)。
### 预估请求数
下表根据典型的 Go 使用模式提供了预估请求数：
下表根据典型的 Go 使用模式估算请求数。Go Plus 的估算值会根据各模型更高的用量限制相应增加。
| Model | 每 5 小时请求数 | 每周请求数 | 每月请求数 |
| ---------------------------- | --------------- | ---------- | ---------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 无限制 | 无限制 | 无限制 |
| LongCat 2.5 Preview Free | 无限制 | 无限制 | 无限制 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| 模型 | 每 5 小时请求数 | 每周请求数 | 每月请求数 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | 无限制 | 无限制 | 无限制 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 无限制 | 无限制 | 无限制 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| 模型 | 每 5 小时请求数 | 每周请求数 | 每月请求数 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | 无限制 | 无限制 | 无限制 |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | 无限制 | 无限制 | 无限制 |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
预估值采用以下每次请求的 token 数量；实际使用情况会有所不同。
- Grok 4.7/4.6 — 每次请求 390 个输入 token，32,500 个缓存 token，120 个输出 token
- GLM-5.3-Flash — 每次请求 1,000 个输入 token，55,000 个缓存 token，200 个输出 token
- GLM-5.3/5.2/5.1 — 每次请求 700 个输入 token，52,000 个缓存 token，150 个输出 token
- GPT 6 Luna — 每次请求 1,000 个输入 token，50,000 个缓存 token，220 个输出 token
- GPT 5.6 Luna — 每次请求 1,000 个输入 token，50,000 个缓存 token，220 个输出 token
- Kimi K3 — 每次请求 1,050 个输入 token，76,500 个缓存 token，300 个输出 token
- Kimi K2.7/K2.6 — 每次请求 870 个输入 token，55,000 个缓存 token，200 个输出 token
- LongCat-2.0 — 每次请求 920 个输入 token，88,900 个缓存 token，200 个输出 token
- DeepSeek V4.1 Flash — 每次请求 410 个输入 token，71,300 个缓存 token，310 个输出 token
- DeepSeek V4 Pro — 每次请求 750 个输入 token，82,000 个缓存 token，290 个输出 token
- DeepSeek V4 Flash — 每次请求 410 个输入 token，71,300 个缓存 token，310 个输出 token
- DeepSeek V4 Flash Vision Exp — 每次请求 410 个输入 token，71,300 个缓存 token，310 个输出 token
- MiMo-V2.6-Flash — 每次请求 830 个输入 token，71,500 个缓存 token，295 个输出 token
- MiMo-V2.6-Pro — 每次请求 790 个输入 token，86,000 个缓存 token，305 个输出 token
- MiMo-V2.5 — 每次请求 830 个输入 token，71,500 个缓存 token，295 个输出 token
- MiMo-V2.5-Pro — 每次请求 790 个输入 token，86,000 个缓存 token，305 个输出 token
- MiniMax M3 — 每次请求 510 个输入 token，56,000 个缓存 token，190 个输出 token
- MiniMax M2.7 — 每次请求 300 个输入 token，55,000 个缓存 token，125 个输出 token
- Muse Spark 1.3 Contributor — 每次请求 620 个输入 token，71,400 个缓存 token，300 个输出 token
- Muse Spark 1.2 Contributor — 每次请求 620 个输入 token，71,400 个缓存 token，300 个输出 token
- Qwen3.8 Max — 每次请求 420 个输入 token，66,000 个缓存 token，200 个输出 token
- Qwen3.8 Flash — 每次请求 600 个输入 token，58,000 个缓存 token，200 个输出 token
- Qwen3.7 Max — 每次请求 420 个输入 token，66,000 个缓存 token，200 个输出 token
- Qwen3.7 Plus — 每次请求 500 个输入 token，57,000 个缓存 token，190 个输出 token
- Qwen3.6 Plus — 每次请求 500 个输入 token，57,000 个缓存 token，190 个输出 token
- Hy4 preview — 每次请求 830 个输入 token，71,500 个缓存 token，295 个输出 token
- Hy3 — 每次请求 830 个输入 token，71,500 个缓存 token，295 个输出 token
- Grok 4.7/4.6 — 390 个输入 token，32,500 个缓存 token，120 个输出 token
- GLM-5.3-Flash — 1,000 个输入 token，55,000 个缓存 token，200 个输出 token
- GLM-5.3/5.2 — 700 个输入 token，52,000 个缓存 token，150 个输出 token
- GPT 6 Luna — 1,000 个输入 token，50,000 个缓存 token，220 个输出 token
- GPT 5.6 Luna — 1,000 个输入 token，50,000 个缓存 token，220 个输出 token
- Kimi K3 — 1,050 个输入 token，76,500 个缓存 token，300 个输出 token
- Kimi K2.7/K2.6 — 870 个输入 token，55,000 个缓存 token，200 个输出 token
- LongCat-2.0 — 920 个输入 token，88,900 个缓存 token，200 个输出 token
- DeepSeek V4.1 Flash — 410 个输入 token，71,300 个缓存 token，310 个输出 token
- DeepSeek V4 Pro — 750 个输入 token，82,000 个缓存 token，290 个输出 token
- DeepSeek V4 Flash — 410 个输入 token，71,300 个缓存 token，310 个输出 token
- DeepSeek V4 Flash Vision Exp — 410 个输入 token，71,300 个缓存 token，310 个输出 token
- MiniMax M3 — 510 个输入 token，56,000 个缓存 token，190 个输出 token
- MiniMax M2.7 — 300 个输入 token，55,000 个缓存 token，125 个输出 token
- Muse Spark 1.3 Contributor — 620 个输入 token，71,400 个缓存 token，300 个输出 token
- Muse Spark 1.2 Contributor — 620 个输入 token，71,400 个缓存 token，300 个输出 token
- MiMo-V2.6-Flash — 830 个输入 token，71,500 个缓存 token，295 个输出 token
- MiMo-V2.6-Pro — 790 个输入 token，86,000 个缓存 token，305 个输出 token
- MiMo-V2.5 — 830 个输入 token，71,500 个缓存 token，295 个输出 token
- MiMo-V2.5-Pro — 790 个输入 token，86,000 个缓存 token，305 个输出 token
- Qwen3.8 Max — 420 个输入 token，66,000 个缓存 token，200 个输出 token
- Qwen3.8 Flash — 600 个输入 token，58,000 个缓存 token，200 个输出 token
- Qwen3.7 Plus — 500 个输入 token，57,000 个缓存 token，190 个输出 token
- Hy4 preview — 830 个输入 token，71,500 个缓存 token，295 个输出 token
- Hy3 — 830 个输入 token，71,500 个缓存 token，295 个输出 token
你可以在 **<a href={console}>控制台</a>** 中跟踪你当前的使用情况。
你可以在 **<a href={console}>控制台</a>** 中跟踪当前用量。
:::tip
如果你达到了使用限制，你可以继续使用免费模型。
如果达到使用限制，你仍可继续使用免费模型。
:::
使用限制可能会随着我们从早期使用和反馈中学习而发生变化。
随着我们从早期使用情况和反馈中学习，使用限制可能会发生变化。
---
### 超出限制的使用
如果你的 Zen 余额中还有积分，可以在控制台中启用 **使用余额（Use balance）** 选项。启用后，当你达到使用限制时，Go 会回退使用你的 Zen 余额，而不是拦截请求。
如果你的 Zen 余额中还有积分，可以在控制台中启用 **使用余额（Use balance）** 选项。启用后，当你达到使用限制时，Go 会改用 Zen 余额，而不是拦截请求。
---
### 为什么某些模型的使用额度较低
使用 Go 时，你每月支付 $10，包含的每月使用额度因模型而异。
使用 Go 时，包含的每月使用额度因模型而异。
对于大多数模型，我们通过批量折扣和预留 GPU 容量来实现这一目标。然后，我们通过提高每月使用额度，将节省的成本回馈给你。
对于大多数模型，我们通过批量折扣和预留 GPU 容量来实现这一点，再以更高的每月使用额度将节省的成本回馈给你。
对于某些模型，我们还没有机会协商折扣或以更低的成本托管它们，这可能是因为模型较新，或者其公开价格已经是折扣价。
对于某些模型，我们还没有机会协商折扣或以更低的成本托管，原因可能是模型较新，或其公开价格已经是折扣价。
对于这些模型，你获得的使用额度仍会略高于直接向模型提供商付费；这就是它们包含的每月使用额度较低的原因。
对于这些模型，你获得的用量仍会略高于直接向模型提供商付费；这就是它们包含的每月使用额度较低的原因。
---
@@ -295,7 +381,7 @@ Token 价格按每 1M tokens 列示。
你也可以通过以下 API 端点访问 Go 模型。
| 模型 | 模型 ID | 端点 | AI SDK 包 |
| 模型 | 模型 ID | 端点 | AI SDK 包 |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -304,11 +390,11 @@ Token 价格按每 1M tokens 列示。
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -319,20 +405,16 @@ Token 价格按每 1M tokens 列示。
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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`。
OpenCode 配置中的[模型 ID](/docs/config/#models)使用 `opencode-go/<model-id>` 格式。例如，Kimi K3 在配置中应使用 `opencode-go/kimi-k3`。
---
@@ -349,46 +431,43 @@ https://opencode.ai/zen/go/v1/models
## 隐私保护
| 模型 | 模型训练 | 数据留存 |
| ---------------------------- | -------- | -------- |
| Grok 4.7 | 不使用 | 30 天 |
| Grok 4.6 | 不使用 | 30 天 |
| GPT 6 Luna | 不使用 | 30 天 |
| GPT 5.6 Luna | 不使用 | 30 天 |
| GLM-5.3-Flash | 不使用 | 0 天 |
| GLM-5.3 | 不使用 | 0 天 |
| GLM-5.2 | 不使用 | 0 天 |
| GLM-5.1 | 不使用 | 0 天 |
| Kimi K3 | 不使用 | 0 天 |
| Kimi K2.7 Code | 不使用 | 0 天 |
| Kimi K2.6 | 不使用 | 0 天 |
| LongCat-2.0 | 不使用 | 0 天 |
| MiMo-V2.6-Pro | 不使用 | 0 天 |
| MiMo-V2.6-Flash | 不使用 | 0 天 |
| MiMo-V2.5-Pro | 不使用 | 0 天 |
| MiMo-V2.5 | 不使用 | 0 天 |
| Qwen3.8 Max | 不使用 | 0 天 |
| Qwen3.8 Flash | 不使用 | 0 天 |
| Qwen3.7 Max | 不使用 | 0 天 |
| Qwen3.7 Plus | 不使用 | 0 天 |
| Qwen3.6 Plus | 不使用 | 0 天 |
| MiniMax M3 | 不使用 | 0 天 |
| MiniMax M2.7 | 不使用 | 0 天 |
| Muse Spark 1.3 Contributor | 是 | 非 ZDR |
| Muse Spark 1.2 Contributor | 是 | 非 ZDR |
| DeepSeek V4.1 Flash | 不使用 | 0 天 |
| DeepSeek V4 Pro | 不使用 | 0 天 |
| DeepSeek V4 Flash | 不使用 | 0 天 |
| DeepSeek V4 Flash Vision Exp | 不使用 | 0 天 |
| Hy4 preview | 不使用 | 0 天 |
| Hy3 | 不使用 | 0 天 |
| Space Bunny Free | 不使用 | 0 天 |
| LongCat 2.5 Preview Free | 不使用 | 0 天 |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | 不使用 | 30 天 |
| Grok 4.6 | 不使用 | 30 天 |
| GPT 6 Luna | 不使用 | 30 天 |
| GPT 5.6 Luna | 不使用 | 30 天 |
| GLM-5.3-Flash | 不使用 | 0 天 |
| GLM-5.3 | 不使用 | 0 天 |
| GLM-5.2 | 不使用 | 0 天 |
| Kimi K3 | 不使用 | 0 天 |
| Kimi K2.7 Code | 不使用 | 0 天 |
| Kimi K2.6 | 不使用 | 0 天 |
| LongCat-2.0 | 不使用 | 0 天 |
| MiMo-V2.6-Pro | 不使用 | 0 天 |
| MiMo-V2.6-Flash | 不使用 | 0 天 |
| MiMo-V2.5-Pro | 不使用 | 0 天 |
| MiMo-V2.5 | 不使用 | 0 天 |
| Qwen3.8 Max | 不使用 | 0 天 |
| Qwen3.8 Flash | 不使用 | 0 天 |
| Qwen3.7 Plus | 不使用 | 0 天 |
| MiniMax M3 | 不使用 | 0 天 |
| MiniMax M2.7 | 不使用 | 0 天 |
| Muse Spark 1.3 Contributor | 是 | 非 ZDR |
| Muse Spark 1.2 Contributor | 是 | 非 ZDR |
| DeepSeek V4.1 Flash | 不使用 | 0 天\* |
| DeepSeek V4 Pro | 不使用 | 0 天\* |
| DeepSeek V4 Flash | 不使用 | 0 天\* |
| DeepSeek V4 Flash Vision Exp | 不使用 | 0 天\* |
| Hy4 preview | 不使用 | 0 天 |
| Hy3 | 不使用 | 0 天 |
| Space Bunny Free | 不使用 | 0 天 |
| LongCat 2.5 Preview Free | 不使用 | 0 天 |
- **Grok 4.7/4.6:** 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 6 Luna / 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)。
- **Muse Spark 1.3 Contributor:** 以允许使用你的提示词和补全结果训练未来的 Meta 模型为交换，token 价格可获得大幅折扣。仅在 Meta 的[地理使用政策](https://ai.developer.meta.com/legal/geographic-use-policy)允许的地区提供。[了解更多](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)。
- **Muse Spark 1.2 Contributor:** 以允许使用你的提示词和补全结果训练未来的 Meta 模型为交换，token 价格可获得大幅折扣。仅在 Meta 的[地理使用政策](https://ai.developer.meta.com/legal/geographic-use-policy)允许的地区提供。[了解更多](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)。
- **DeepSeek:** ZDR 协议每月续签。当前协议有效期至 2026 年 9 月 30 日。
- **DeepSeek:** ZDR 协议每月续签。当前协议有效期至 2026 年 10 月 31 日。
---
@@ -396,7 +475,7 @@ https://opencode.ai/zen/go/v1/models
我们创建 OpenCode Go 的目的是：
1. 通过低成本订阅让更多人能够 **无门槛地** 使用 AI 编程。
2. 为最佳开源编程模型提供 **可靠的** 访问。
3. 精选经过 **测试和基准评估**，适合编程 Agent 使用的模型。
4. **无锁定（no lock-in）**，允许你与 OpenCode 一起使用任何其他提供商。
1. 通过低成本订阅，让更多人能够**轻松使用** AI 编程。
2. 为最佳开源编程模型提供**可靠**的访问。
3. 精选经过**测试和基准评估**、适合编程 Agent 使用的模型。
4. 允许你在 OpenCode 中同时使用任何其他提供商，确保**不被单一提供商锁定**。
packages/web/src/content/docs/zh-tw/go.mdx
+286 -207
View File
@@ -1,23 +1,29 @@
---
title: Go
description: 專為開源寫程式模型提供的低成本訂閱服務。
description: 透過兩種用量方案，穩定存取開源寫程式模型。
---
import config from "../../../../config.mjs"
import { Tabs, TabItem } from "@astrojs/starlight/components"
export const console = config.console
export const email = `mailto:${config.email}`
OpenCode Go 是一項**每月 $10 美元的低成本訂閱服務**，讓您能穩定使用受歡迎的開源寫程式模型。
OpenCode Go 讓您能穩定存取受歡迎的開源寫程式模型，並提供兩種月繳方案：
Go 的運作方式與 OpenCode 中的任何其他供應商相同。您訂閱 OpenCode Go 並取得您的 API key。這是**完全可選的**，您不需要使用它也能使用 OpenCode。
| 方案 | 價格 | 包含的用量 |
| ---- | ----- | -------------- |
| **Go** | **$10/月** | 以較低成本存取下列模型 |
| **Go Plus** | **$40/月** | 下列模型均享有更高的用量限制 |
它主要為國際使用者設計，提供穩定的全球存取體驗。
Go 的運作方式與 OpenCode 中的其他供應商相同。訂閱 OpenCode Go 後，您會取得 API key。這是**完全可選的**，您不需要使用它也能使用 OpenCode。
這項服務主要為國際使用者設計，提供穩定的全球存取體驗。
---
## 背景
開源模型已經變得非常強大。它們在寫程式任務上的表現，現在已經接近專有模型。而且因為有許多供應商競爭提供服務，它們通常便宜得多。
開源模型已經變得非常強大。它們在寫程式任務上的表現已接近專有模型。由於許多供應商都能以具競爭力的價格提供服務，它們通常便宜得多。
然而，要獲得穩定、低延遲的存取可能很困難。各家供應商的品質和可用性不一。
@@ -27,24 +33,24 @@ Go 的運作方式與 OpenCode 中的任何其他供應商相同。您訂閱 Ope
為了解決這個問題，我們做了幾件事：
1. 我們測試了一組精選的開源模型，並與它們的團隊討論如何最佳化運行。
2. 接著我們與幾家供應商合作，確保這些模型被正確地提供服務。
3. 最後，我們對模型與供應商的組合進行了基準測試，並整理出一份我們樂於推薦的清單。
1. 我們測試了一組精選的開源模型，並與其團隊討論如何以最佳方式運行。
2. 接著，我們與幾家供應商合作，確保這些模型獲得正確的服務。
3. 最後，我們對模型與供應商的組合進行基準測試，整理出一份值得推薦的清單。
OpenCode Go 讓您可以用**每月 $10 美元**存取這些模型。
Go 和 Go Plus 均可存取這些模型；請依您的使用量選擇合適的方案。
---
## 運作方式
OpenCode Go 的運作方式與 OpenCode 中的任何其他供應商相同。
OpenCode Go 的運作方式與 OpenCode 中的其他供應商相同。
1. 您登入 **<a href={console}>OpenCode Zen</a>**，訂閱 Go，然後複製您的 API key。
2. 您在 TUI 中執行 `/connect` 命令，選擇 `OpenCode Go`，然後貼上您的 API key。
3. 在 TUI 中執行 `/models` 即可查看透過 Go 可用的模型清單。
1. 登入 **<a href={console}>OpenCode Console</a>**，訂閱 Go 或 Go Plus，然後複製您的 API key。
2. 在 TUI 中執行 `/connect` 命令，選擇 `OpenCode Go`，然後貼上您的 API key。
3. 在 TUI 中執行 `/models`，查看可透過 Go 使用的模型清單。
:::note
每個工作區只能有一位成員訂閱 OpenCode Go。
每個工作區只能有一位成員訂閱 OpenCode Go 或 Go Plus。
:::
目前的模型清單包括：
@@ -54,13 +60,13 @@ OpenCode Go 的運作方式與 OpenCode 中的任何其他供應商相同。
- **GLM-5.3-Flash**
- **GLM-5.3**
- **GLM-5.2**
- **GLM-5.1**
- **GPT 6 Luna**
- **GPT 5.6 Luna**
- **Kimi K3**
- **Kimi K2.7 Code**
- **Kimi K2.6**
- **LongCat-2.0**
- **LongCat 2.5 Preview Free**（限時）
- **MiMo-V2.6-Flash**
- **MiMo-V2.6-Pro**
- **MiMo-V2.5**
@@ -71,17 +77,14 @@ OpenCode Go 的運作方式與 OpenCode 中的任何其他供應商相同。
- **Muse Spark 1.2 Contributor** ([僅限部分地區](https://ai.developer.meta.com/legal/geographic-use-policy))
- **Qwen3.8 Max**
- **Qwen3.8 Flash**
- **Qwen3.7 Max**
- **Qwen3.7 Plus**
- **Qwen3.6 Plus**
- **DeepSeek V4.1 Flash**
- **DeepSeek V4 Pro**
- **DeepSeek V4 Flash**
- **DeepSeek V4 Flash Vision Exp**
- **Hy4 preview**
- **Hy3**
- **Space Bunny Free** (限時)
- **LongCat 2.5 Preview Free** (限時)
- **Space Bunny Free**（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。
@@ -89,101 +92,147 @@ OpenCode Go 的運作方式與 OpenCode 中的任何其他供應商相同。
## 可以在哪裡使用？
OpenCode Go 適用於 [OpenCode](https://opencode.ai) 以及其他會產生類似請求的程式設計 Agent。
我們會監控流量，以識別影響其他使用者體驗的濫用行為。
OpenCode Go 適用於 [OpenCode](https://opencode.ai) 以及其他會產生類似請求的寫程式 Agent。我們會監控流量，以識別影響其他使用者體驗的濫用行為。
您的用戶端應：
1. 傳送典型的程式設計 Agent 流量。
1. 傳送典型的寫程式 Agent 流量
2. 使用自身專屬的 user agent 識別資訊（例如 `my-coding-agent/1.0`），而非通用的 SDK 或 HTTP 函式庫名稱。
3. 為每段對話在 `x-opencode-session` 請求標頭中傳送穩定的工作階段 ID，以便我們最佳化路由和提示詞快取。
3. 為每段對話在 `x-opencode-session` 中傳送穩定的工作階段 ID，以便我們最佳化路由和提示詞快取。
### 已驗證的用戶端
除了 OpenCode，以下用戶端已通過驗證，可正常使用 OpenCode Go。但我們無法保證它們未來仍能正常使用。
| 用戶端 | 工作階段支援 |
| ----------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | 包含 [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) 的建置版本會在主要和輔助 OpenCode 請求中傳送該標頭。此修正是在 v0.21.0 發布後才合併，因此 v0.21.0 本身並未包含此修正。 |
| **Claude Code** | Go 可辨識其原生工作階段標頭，無須額外封裝來新增自訂標頭。 |
| **Codex** | Go 可辨識其原生工作階段標頭。部分版本和代理伺服器設定仍會遺漏該標頭；轉送請求時請保留工作階段標頭。 |
| **ZCode** | Go 可辨識其原生工作階段標頭。我們[請求支援 `x-opencode-session` 的 issue](https://github.com/zai-org/feedback/issues/492) 仍未關閉，但已不再需要傳送這個特定標頭。 |
| **Pi** | 目前的建置版本會為 OpenCode 傳送工作階段資訊。請更新舊版安裝。 |
| **jcode** | 請更新至 **v0.81.6 或更新版本**，其中包含[工作階段標頭修正](https://github.com/1jehuang/jcode/issues/1167)。 |
| 用戶端 | 工作階段支援 |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Hermes** | 包含 [PR #101864](https://github.com/NousResearch/hermes-agent/pull/101864) 的建置版本會在主要和輔助 OpenCode 請求中傳送該標頭。此修正是在 v0.21.0 發布後才合併，因此該版本本身並未包含此修正。 |
| **Claude Code** | Go 可辨識其原生工作階段標頭，無須自訂標頭封裝。 |
| **Codex** | Go 可辨識其原生工作階段標頭。部分版本和代理伺服器設定仍會遺漏該標頭；轉送請求時請保留工作階段標頭。 |
| **ZCode** | Go 可辨識其原生工作階段標頭。我們[請求支援 `x-opencode-session`](https://github.com/zai-org/feedback/issues/492) 仍未關閉，但已不再需要傳送這個特定標頭。 |
| **Pi** | 目前的建置版本會為 OpenCode 傳送工作階段資訊。請更新舊版安裝。 |
| **jcode** | 請更新至 **v0.81.6 或更新版本**，其中包含[工作階段標頭修正](https://github.com/1jehuang/jcode/issues/1167)。 |
| **Kilo Code CLI** | 包含 [PR #13752](https://github.com/Kilo-Org/kilocode/pull/13752) 的建置版本恢復了 OpenCode 工作階段標頭。此修正僅適用於 CLI，不適用於 VS Code 擴充套件。請參閱 [issue #13723](https://github.com/Kilo-Org/kilocode/issues/13723)。 |
### 已知有問題的用戶端
在我們調查的版本中，以下用戶端缺少工作階段支援，或支援不完整。相關回報連結可用來追蹤修正進度與暫時解決方式。
| 用戶端 | 狀態與追蹤 |
| ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 用戶端 | 狀態與追蹤 |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **DeepSeek Harness** | 部分模型呼叫路徑會傳遞工作階段資訊，但其他路徑中缺少這些資訊。我們可辨識其原生標頭；剩餘工作是在所有配接器中傳送該標頭。請參閱[討論 #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495)。 |
| **GitHub Copilot Chat** | [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) 已提出自動傳送工作階段標頭的支援請求。 |
| **Kimi Code** | [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) 已提出自動傳送工作階段標頭的支援請求。 |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) 已有修正提案 [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327)，但尚未合併。 |
| **GitHub Copilot Chat** | [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186) 已提出自動傳送工作階段標頭的支援請求。 |
| **Kimi Code** | [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) 已提出自動傳送工作階段標頭的支援請求。 |
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) 已有修正提案 [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327)，但尚未合併。 |
## 使用限制
使用限制以每月美元金額定義。下表列出每個模型的每月限制和 token 成本。
使用限制以每月美元金額定義。下表列出每種方案的每月限制和各模型的 token 成本。Go 與 Go Plus 的 token 價格相同。
每個模型都有以下使用限制：5 小時 — 每月限制的 20%；每週 — 50%；每月 — 100%。
例如，如果某個模型的每月限制為 $60，您最多可以使用：
例如，如果某個模型在 Go 的每月限制為 $60，在 Go Plus 的每月限制為 $120，您最多可以使用：
- **5 小時限制** — $12 的使用額度
- **每週限制** — $30 的使用額度
- **每月限制** — $60 的使用額度
- **5 小時限制** — Go 為 $12，Go Plus 為 $24
- **每週限制** — Go 為 $30，Go Plus 為 $60
- **每月限制** — Go 為 $60，Go Plus 為 $120
Token 價格按每 1M tokens 列示。
跨模型計算時，Go 的 5 小時、每週和每月額度分別為 $12、$30 和 $60；Go Plus 則分別為 $48、$120 和 $240。下方每個模型的每月限制決定其用量如何計入這些額度。
| 模型 | 輸入 | 輸出 | 快取讀取 | 快取寫入 | 每月限制 |
| --------------------------------------- | ------ | ------ | --------- | -------- | ----------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| GLM-5.1 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| MiniMax M2.5 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| Qwen3.6 Plus (≤ 256K tokens) | $0.50 | $3.00 | $0.05 | $0.625 | **$60** |
| Qwen3.6 Plus (> 256K tokens) | $2.00 | $6.00 | $0.20 | $2.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | Free | Free | Free | - | **無限制**<br /><small>限時</small> |
| LongCat 2.5 Preview Free | Free | Free | Free | - | **無限制**<br /><small>限時</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
Token 價格按每 1M tokens 計算。
<Tabs syncKey="go-plan">
<TabItem label="Go">
| 模型 | 輸入 | 輸出 | 快取讀取 | 快取寫入 | 每月限制 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$60** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$15** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$60** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$15** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$60** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$60** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$60** |
| LongCat 2.5 Preview Free | 免費 | 免費 | 免費 | - | **無限制**<br /><small>限時</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$60** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$15** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$60** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$60** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$60** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$15** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$30** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$60** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$60** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$15** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$15** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$30** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$30** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$15** |
| 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** |
| Space Bunny Free | 免費 | 免費 | 免費 | - | **無限制**<br /><small>限時</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$15** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$15** |
| 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 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$15** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$15** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$15** |
</TabItem>
<TabItem label="Go Plus">
| 模型 | 輸入 | 輸出 | 快取讀取 | 快取寫入 | 每月限制 |
| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | **$180** |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | **$120** |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | **$180** |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | **$60** |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | **$180** |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | **$240** |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | **$240** |
| LongCat 2.5 Preview Free | 免費 | 免費 | 免費 | - | **無限制**<br /><small>限時</small> |
| MiMo-V2.6-Flash | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.6-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiMo-V2.5 | $0.14 | $0.28 | $0.0028 | - | **$120** |
| MiMo-V2.5-Pro | $0.435 | $0.87 | $0.003625 | - | **$60** |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | - | **$180** |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 | $0.375 | **$240** |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.002 | - | **$120** |
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | **$60** |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 | **$90** |
| Qwen3.7 Plus (≤ 256K tokens) | $0.40 | $1.60 | $0.04 | $0.50 | **$180** |
| Qwen3.7 Plus (> 256K tokens) | $1.20 | $4.80 | $0.12 | $1.50 | **$180** |
| DeepSeek V4.1 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4.1 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Pro (Off-Peak) | $0.66 | $1.98 | $0.022 | - | **$60** |
| DeepSeek V4 Pro (Peak) | $1.32 | $3.96 | $0.044 | - | **$60** |
| DeepSeek V4 Flash (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$120** |
| DeepSeek V4 Flash (Peak) | $0.30 | $1.20 | $0.006 | - | **$120** |
| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15 | $0.60 | $0.003 | - | **$60** |
| DeepSeek V4 Flash Vision Exp (Peak) | $0.30 | $1.20 | $0.006 | - | **$60** |
| Hy4 preview | $0.834 | $2.501 | $0.042 | - | **$120** |
| Hy3 | $0.14 | $0.58 | $0.035 | - | **$240** |
| Space Bunny Free | 免費 | 免費 | 免費 | - | **無限制**<br /><small>限時</small> |
| Grok 4.7 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.7 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| Grok 4.6 (≤ 200K tokens) | $2.00 | $6.00 | $0.50 | - | **$60** |
| Grok 4.6 (> 200K tokens) | $4.00 | $12.00 | $1.00 | - | **$60** |
| GPT 6 Luna (≤ 272K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | **$60** |
| GPT 6 Luna (> 272K tokens) | $0.20 | $0.75 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (≤ 272K tokens) | $0.20 | $1.20 | $0.02 | $0.25 | **$60** |
| GPT 5.6 Luna (> 272K tokens) | $0.40 | $1.80 | $0.04 | $0.50 | **$60** |
</TabItem>
</Tabs>
**Space Bunny Free:** 限時免費。
@@ -191,103 +240,140 @@ Token 價格按每 1M tokens 列示。
**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak 時段為週一至週五的 01:00-04:00 和 06:00-10:00 UTC；其他所有時段（包括週末）均為 Off-Peak。[了解更多](https://api-docs.deepseek.com/quick_start/pricing/)。
**DeepSeek V4 Flash Vision Exp:** 圖片會根據尺寸轉換為 token，並與文字 token 一起按輸入 token 計費。 [了解更多](https://api-docs.deepseek.com/quick_start/pricing/)。
**DeepSeek V4 Flash Vision Exp:** 圖片會根據尺寸轉換為 token，並與文字 token 一起按輸入 token 計費。[了解更多](https://api-docs.deepseek.com/quick_start/pricing/)。
### 預估請求次數
下表根據典型的 Go 使用模式提供預估請求次數：
下表根據典型的 Go 使用模式估算請求次數。Go Plus 的估算值會依各模型更高的用量限制相應增加。
| Model | 每 5 小時請求數 | 每週請求數 | 每月請求數 |
| ---------------------------- | --------------- | ---------- | ---------- |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| GLM-5.1 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Max | 170 | 420 | 840 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 無限制 | 無限制 | 無限制 |
| LongCat 2.5 Preview Free | 無限制 | 無限制 | 無限制 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
<Tabs syncKey="go-plan">
<TabItem label="Go">
| 模型 | 每 5 小時請求數 | 每週請求數 | 每月請求數 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 6,320 | 15,790 | 31,580 |
| GLM-5.3 | 220 | 540 | 1,080 |
| GLM-5.2 | 880 | 2,150 | 4,300 |
| Kimi K3 | 110 | 250 | 490 |
| Kimi K2.7 Code | 1,350 | 3,380 | 6,750 |
| Kimi K2.6 | 1,150 | 2,880 | 5,750 |
| LongCat-2.0 | 11,400 | 28,600 | 57,200 |
| LongCat 2.5 Preview Free | 無限制 | 無限制 | 無限制 |
| MiMo-V2.6-Flash | 30,100 | 75,200 | 150,400 |
| MiMo-V2.6-Pro | 3,250 | 8,150 | 16,300 |
| MiMo-V2.5 | 30,100 | 75,200 | 150,400 |
| MiMo-V2.5-Pro | 3,250 | 8,150 | 16,300 |
| MiniMax M3 | 3,200 | 8,000 | 16,000 |
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
| Muse Spark 1.3 Contributor | 45,300 | 113,300 | 226,600 |
| Muse Spark 1.2 Contributor | 45,300 | 113,300 | 226,600 |
| Qwen3.8 Max | 160 | 400 | 810 |
| Qwen3.8 Flash | 5,400 | 13,500 | 27,000 |
| Qwen3.7 Plus | 4,300 | 10,800 | 21,600 |
| DeepSeek V4.1 Flash | 26,000 | 65,000 | 130,000 |
| DeepSeek V4 Pro | 1,050 | 2,600 | 5,200 |
| DeepSeek V4 Flash | 13,000 | 32,500 | 65,000 |
| 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 |
| Space Bunny Free | 無限制 | 無限制 | 無限制 |
| Grok 4.7 | 169 | 423 | 845 |
| Grok 4.6 | 169 | 423 | 845 |
| GPT 6 Luna | 4,230 | 10,560 | 21,130 |
| GPT 5.6 Luna | 2,050 | 5,100 | 10,250 |
</TabItem>
<TabItem label="Go Plus">
| 模型 | 每 5 小時請求數 | 每週請求數 | 每月請求數 |
| ---------------------------- | -------------------- | ----------------- | ------------------ |
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | 無限制 | 無限制 | 無限制 |
| MiMo-V2.6-Flash | 60,200 | 150,400 | 300,800 |
| MiMo-V2.6-Pro | 13,000 | 32,600 | 65,200 |
| MiMo-V2.5 | 60,200 | 150,400 | 300,800 |
| MiMo-V2.5-Pro | 13,000 | 32,600 | 65,200 |
| MiniMax M3 | 9,600 | 24,000 | 48,000 |
| MiniMax M2.7 | 13,600 | 34,000 | 68,000 |
| Muse Spark 1.3 Contributor | 90,600 | 226,600 | 453,200 |
| Muse Spark 1.2 Contributor | 90,600 | 226,600 | 453,200 |
| Qwen3.8 Max | 640 | 1,600 | 3,240 |
| Qwen3.8 Flash | 16,200 | 40,500 | 81,000 |
| Qwen3.7 Plus | 12,900 | 32,400 | 64,800 |
| DeepSeek V4.1 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Pro | 4,200 | 10,400 | 20,800 |
| DeepSeek V4 Flash | 52,000 | 130,000 | 260,000 |
| DeepSeek V4 Flash Vision Exp | 26,000 | 65,000 | 130,000 |
| Hy4 preview | 5,400 | 13,520 | 27,080 |
| Hy3 | 17,200 | 43,000 | 86,000 |
| Space Bunny Free | 無限制 | 無限制 | 無限制 |
| Grok 4.7 | 676 | 1,692 | 3,380 |
| Grok 4.6 | 676 | 1,692 | 3,380 |
| GPT 6 Luna | 16,920 | 42,240 | 84,520 |
| GPT 5.6 Luna | 8,200 | 20,400 | 41,000 |
</TabItem>
</Tabs>
這些預估值採用以下每次請求的 token 數量；實際使用情況會有所不同。
- Grok 4.7/4.6 — 每次請求 390 個輸入 token、32,500 個快取 token、120 個輸出 token
- GLM-5.3-Flash — 每次請求 1,000 個輸入 token、55,000 個快取 token、200 個輸出 token
- GLM-5.3/5.2/5.1 — 每次請求 700 個輸入 token、52,000 個快取 token、150 個輸出 token
- GPT 6 Luna — 每次請求 1,000 個輸入 token、50,000 個快取 token、220 個輸出 token
- GPT 5.6 Luna — 每次請求 1,000 個輸入 token、50,000 個快取 token、220 個輸出 token
- Kimi K3 — 每次請求 1,050 個輸入 token、76,500 個快取 token、300 個輸出 token
- Kimi K2.7/K2.6 — 每次請求 870 個輸入 token、55,000 個快取 token、200 個輸出 token
- LongCat-2.0 — 每次請求 920 個輸入 token、88,900 個快取 token、200 個輸出 token
- DeepSeek V4.1 Flash — 每次請求 410 個輸入 token、71,300 個快取 token、310 個輸出 token
- DeepSeek V4 Pro — 每次請求 750 個輸入 token、82,000 個快取 token、290 個輸出 token
- DeepSeek V4 Flash — 每次請求 410 個輸入 token、71,300 個快取 token、310 個輸出 token
- DeepSeek V4 Flash Vision Exp — 每次請求 410 個輸入 token、71,300 個快取 token、310 個輸出 token
- MiniMax M3 — 每次請求 510 個輸入 token、56,000 個快取 token、190 個輸出 token
- MiniMax M2.7 — 每次請求 300 個輸入 token、55,000 個快取 token、125 個輸出 token
- Muse Spark 1.3 Contributor — 每次請求 620 個輸入 token、71,400 個快取 token、300 個輸出 token
- Muse Spark 1.2 Contributor — 每次請求 620 個輸入 token、71,400 個快取 token、300 個輸出 token
- Qwen3.8 Max — 每次請求 420 個輸入 token、66,000 個快取 token、200 個輸出 token
- Qwen3.8 Flash — 每次請求 600 個輸入 token、58,000 個快取 token、200 個輸出 token
- Qwen3.7 Max — 每次請求 420 個輸入 token、66,000 個快取 token、200 個輸出 token
- Qwen3.7 Plus — 每次請求 500 個輸入 token、57,000 個快取 token、190 個輸出 token
- Qwen3.6 Plus — 每次請求 500 個輸入 token、57,000 個快取 token、190 個輸出 token
- Hy4 preview — 每次請求 830 個輸入 token、71,500 個快取 token、295 個輸出 token
- Hy3 — 每次請求 830 個輸入 token、71,500 個快取 token、295 個輸出 token
- MiMo-V2.6-Flash — 每次請求 830 個輸入 token、71,500 個快取 token、295 個輸出 token
- MiMo-V2.6-Pro — 每次請求 790 個輸入 token、86,000 個快取 token、305 個輸出 token
- MiMo-V2.5 — 每次請求 830 個輸入 token、71,500 個快取 token、295 個輸出 token
- MiMo-V2.5-Pro — 每次請求 790 個輸入 token、86,000 個快取 token、305 個輸出 token
- Grok 4.7/4.6 — 390 個輸入 token、32,500 個快取 token、120 個輸出 token
- GLM-5.3-Flash — 1,000 個輸入 token、55,000 個快取 token、200 個輸出 token
- GLM-5.3/5.2 — 700 個輸入 token、52,000 個快取 token、150 個輸出 token
- GPT 6 Luna — 1,000 個輸入 token、50,000 個快取 token、220 個輸出 token
- GPT 5.6 Luna — 1,000 個輸入 token、50,000 個快取 token、220 個輸出 token
- Kimi K3 — 1,050 個輸入 token、76,500 個快取 token、300 個輸出 token
- Kimi K2.7/K2.6 — 870 個輸入 token、55,000 個快取 token、200 個輸出 token
- LongCat-2.0 — 920 個輸入 token、88,900 個快取 token、200 個輸出 token
- DeepSeek V4.1 Flash — 410 個輸入 token、71,300 個快取 token、310 個輸出 token
- DeepSeek V4 Pro — 750 個輸入 token、82,000 個快取 token、290 個輸出 token
- DeepSeek V4 Flash — 410 個輸入 token、71,300 個快取 token、310 個輸出 token
- DeepSeek V4 Flash Vision Exp — 410 個輸入 token、71,300 個快取 token、310 個輸出 token
- MiniMax M3 — 510 個輸入 token、56,000 個快取 token、190 個輸出 token
- MiniMax M2.7 — 300 個輸入 token、55,000 個快取 token、125 個輸出 token
- Muse Spark 1.3 Contributor — 620 個輸入 token、71,400 個快取 token、300 個輸出 token
- Muse Spark 1.2 Contributor — 620 個輸入 token、71,400 個快取 token、300 個輸出 token
- MiMo-V2.6-Flash — 830 個輸入 token、71,500 個快取 token、295 個輸出 token
- MiMo-V2.6-Pro — 790 個輸入 token、86,000 個快取 token、305 個輸出 token
- MiMo-V2.5 — 830 個輸入 token、71,500 個快取 token、295 個輸出 token
- MiMo-V2.5-Pro — 790 個輸入 token、86,000 個快取 token、305 個輸出 token
- Qwen3.8 Max — 420 個輸入 token、66,000 個快取 token、200 個輸出 token
- Qwen3.8 Flash — 600 個輸入 token、58,000 個快取 token、200 個輸出 token
- Qwen3.7 Plus — 500 個輸入 token、57,000 個快取 token、190 個輸出 token
- Hy4 preview — 830 個輸入 token、71,500 個快取 token、295 個輸出 token
- Hy3 — 830 個輸入 token、71,500 個快取 token、295 個輸出 token
您可以在 **<a href={console}>console</a>** 中追蹤您目前的使用量。
您可以在 **<a href={console}>控制台</a>** 中追蹤目前的用量。
:::tip
如果您達到了使用限制，您可以繼續使用免費模型。
如果達到使用限制，您仍可繼續使用免費模型。
:::
使用限制可能會隨著我們從早期使用情況和回饋中學習而有所調整。
隨著我們從早期使用情況和回饋中學習，使用限制可能會有所調整。
---
### 超出限制的使用量
如果您在您的 Zen 餘額中也有額度，您可以在 console 中啟用 **Use balance** 選項。啟用後，當您達到使用限制時，Go 將會改用您的 Zen 餘額，而不是阻擋請求。
如果您的 Zen 餘額中還有額度，可以在控制台中啟用 **使用餘額（Use balance）** 選項。啟用後，當您達到使用限制時，Go 會改用 Zen 餘額，而不是阻擋請求。
---
### 為什麼部分模型的使用額度較低
使用 Go 時，您每月支付 $10，包含的每月使用額度因模型而異。
使用 Go 時，包含的每月使用額度因模型而異。
對大多數模型而言，我們透過大量採購折扣和預留 GPU 容量來達成此目標，再透過提高每月使用額度，將節省的成本回饋給您。
對大多數模型而言，我們透過大量採購折扣和預留 GPU 容量來達成此目標，再以更高的每月使用額度將節省的成本回饋給您。
對於部分模型，我們尚未有機會議定折扣或以較低成本託管，原因可能是模型剛推出，或其公開價格已經過折扣。
對於這些模型，您獲得的使用額度仍會比直接向模型供應商付費多一些；這就是它們包含的每月使用額度較低的原因。
對於這些模型，您獲得的用量仍會比直接向模型供應商付費多一些；這就是它們包含的每月使用額度較低的原因。
---
@@ -295,7 +381,7 @@ Token 價格按每 1M tokens 列示。
您也可以透過以下 API 端點存取 Go 模型。
| 模型 | 模型 ID | 端點 | AI SDK 套件 |
| 模型 | 模型 ID | 端點 | AI SDK 套件 |
| ---------------------------- | ---------------------------- | ------------------------------------------------ | --------------------------- |
| Grok 4.7 | grok-4.7 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Grok 4.6 | grok-4.6 | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
@@ -304,11 +390,11 @@ Token 價格按每 1M tokens 列示。
| GLM-5.3-Flash | glm-5.3-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.3 | glm-5.3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.2 | glm-5.2 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| GLM-5.1 | glm-5.1 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K3 | kimi-k3 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.7 Code | kimi-k2.7-code | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| Kimi K2.6 | kimi-k2.6 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat-2.0 | longcat-2.0 | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Pro | deepseek-v4-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| DeepSeek V4 Flash | deepseek-v4-flash | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -319,26 +405,22 @@ Token 價格按每 1M tokens 列示。
| MiMo-V2.5-Pro | mimo-v2.5-pro | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| MiniMax M3 | minimax-m3 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.7 | minimax-m2.7 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| MiniMax M2.5 | minimax-m2.5 | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Muse Spark 1.3 Contributor | muse-spark-1.3-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Muse Spark 1.2 Contributor | muse-spark-1.2-contributor | `https://opencode.ai/zen/go/v1/responses` | `@ai-sdk/openai` |
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/zen/go/v1/messages` | `@ai-sdk/anthropic` |
| 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` |
| Space Bunny Free | space-bunny-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
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`。
OpenCode 設定中的[模型 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`。
---
### 模型
你可以從以下位置取得所有可用模型及其中繼資料的完整清單：
您可以從以下位置取得所有可用模型及其中繼資料的完整清單：
```
https://opencode.ai/zen/go/v1/models
@@ -349,46 +431,43 @@ https://opencode.ai/zen/go/v1/models
## 隱私權
| 模型 | 模型訓練 | 資料保留 |
| ---------------------------- | -------- | -------- |
| Grok 4.7 | 不使用 | 30 天 |
| Grok 4.6 | 不使用 | 30 天 |
| GPT 6 Luna | 不使用 | 30 天 |
| GPT 5.6 Luna | 不使用 | 30 天 |
| GLM-5.3-Flash | 不使用 | 0 天 |
| GLM-5.3 | 不使用 | 0 天 |
| GLM-5.2 | 不使用 | 0 天 |
| GLM-5.1 | 不使用 | 0 天 |
| Kimi K3 | 不使用 | 0 天 |
| Kimi K2.7 Code | 不使用 | 0 天 |
| Kimi K2.6 | 不使用 | 0 天 |
| LongCat-2.0 | 不使用 | 0 天 |
| MiMo-V2.6-Pro | 不使用 | 0 天 |
| MiMo-V2.6-Flash | 不使用 | 0 天 |
| MiMo-V2.5-Pro | 不使用 | 0 天 |
| MiMo-V2.5 | 不使用 | 0 天 |
| Qwen3.8 Max | 不使用 | 0 天 |
| Qwen3.8 Flash | 不使用 | 0 天 |
| Qwen3.7 Max | 不使用 | 0 天 |
| Qwen3.7 Plus | 不使用 | 0 天 |
| Qwen3.6 Plus | 不使用 | 0 天 |
| MiniMax M3 | 不使用 | 0 天 |
| MiniMax M2.7 | 不使用 | 0 天 |
| Muse Spark 1.3 Contributor | 是 | 非 ZDR |
| Muse Spark 1.2 Contributor | 是 | 非 ZDR |
| DeepSeek V4.1 Flash | 不使用 | 0 天 |
| DeepSeek V4 Pro | 不使用 | 0 天 |
| DeepSeek V4 Flash | 不使用 | 0 天 |
| DeepSeek V4 Flash Vision Exp | 不使用 | 0 天 |
| Hy4 preview | 不使用 | 0 天 |
| Hy3 | 不使用 | 0 天 |
| Space Bunny Free | 不使用 | 0 天 |
| LongCat 2.5 Preview Free | 不使用 | 0 天 |
| ---------------------------- | -------------- | -------------- |
| Grok 4.7 | 不使用 | 30 天 |
| Grok 4.6 | 不使用 | 30 天 |
| GPT 6 Luna | 不使用 | 30 天 |
| GPT 5.6 Luna | 不使用 | 30 天 |
| GLM-5.3-Flash | 不使用 | 0 天 |
| GLM-5.3 | 不使用 | 0 天 |
| GLM-5.2 | 不使用 | 0 天 |
| Kimi K3 | 不使用 | 0 天 |
| Kimi K2.7 Code | 不使用 | 0 天 |
| Kimi K2.6 | 不使用 | 0 天 |
| LongCat-2.0 | 不使用 | 0 天 |
| MiMo-V2.6-Pro | 不使用 | 0 天 |
| MiMo-V2.6-Flash | 不使用 | 0 天 |
| MiMo-V2.5-Pro | 不使用 | 0 天 |
| MiMo-V2.5 | 不使用 | 0 天 |
| Qwen3.8 Max | 不使用 | 0 天 |
| Qwen3.8 Flash | 不使用 | 0 天 |
| Qwen3.7 Plus | 不使用 | 0 天 |
| MiniMax M3 | 不使用 | 0 天 |
| MiniMax M2.7 | 不使用 | 0 天 |
| Muse Spark 1.3 Contributor | 是 | 非 ZDR |
| Muse Spark 1.2 Contributor | 是 | 非 ZDR |
| DeepSeek V4.1 Flash | 不使用 | 0 天\* |
| DeepSeek V4 Pro | 不使用 | 0 天\* |
| DeepSeek V4 Flash | 不使用 | 0 天\* |
| DeepSeek V4 Flash Vision Exp | 不使用 | 0 天\* |
| Hy4 preview | 不使用 | 0 天 |
| Hy3 | 不使用 | 0 天 |
| Space Bunny Free | 不使用 | 0 天 |
| LongCat 2.5 Preview Free | 不使用 | 0 天 |
- **Grok 4.7/4.6:** 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 6 Luna / 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)。
- **Muse Spark 1.3 Contributor:** 以允許使用您的提示詞和生成結果來訓練未來的 Meta 模型為交換，token 價格可享大幅折扣。僅在 Meta 的[地理使用政策](https://ai.developer.meta.com/legal/geographic-use-policy)允許的地區提供。[了解更多](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)。
- **Muse Spark 1.2 Contributor:** 以允許使用您的提示詞和生成結果來訓練未來的 Meta 模型為交換，token 價格可享大幅折扣。僅在 Meta 的[地理使用政策](https://ai.developer.meta.com/legal/geographic-use-policy)允許的地區提供。[了解更多](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier)。
- **DeepSeek:** ZDR 協議每月續簽。目前的協議有效至 2026 年 9 月 30 日。
- **DeepSeek:** ZDR 協議每月續簽。目前的協議有效至 2026 年 10 月 31 日。
---
@@ -396,7 +475,7 @@ https://opencode.ai/zen/go/v1/models
我們建立 OpenCode Go 的目的是：
1. 透過低成本的訂閱服務，讓更多人能**輕鬆獲得** AI 寫程式的協助。
2. 提供**穩定可靠**的途徑來存取最好的開源寫程式模型。
3. 精選經過**測試與效能評估**、適合寫程式代理使用的模型。
4. 允許您在 OpenCode 中同時使用任何其他供應商，確保**不被單一廠商綁定**。
1. 透過低成本訂閱，讓更多人能**輕鬆使用** AI 寫程式。
2. 提供**穩定可靠**的方式來存取最佳開源寫程式模型。
3. 精選經過**測試與效能評估**、適合寫程式 Agent 使用的模型。
4. 允許您在 OpenCode 中同時使用任何其他供應商，確保**不被單一供應商綁定**。
packages/web/src/styles/custom.css
+1 -1
View File
@@ -304,7 +304,7 @@ ol {
padding-inline-start: 1.5rem !important;
}
.sl-markdown-content ul {
.sl-markdown-content ul:not([role="tablist"]) {
list-style: disc !important;
padding-inline-start: 1.5rem !important;
}