Сейчас на сервера Kimi K3 идёт повышенная нагрузка, из-за этого модель может отвечать медленнее обычного. Это проблема на стороне Kimi, а не с нашей стороны.
============================
The Kimi K3 server is currently experiencing heavy traffic, which may cause the model to respond more slowly than usual. This is an issue on Kimi's end, not ours.
============================
The Kimi K3 server is currently experiencing heavy traffic, which may cause the model to respond more slowly than usual. This is an issue on Kimi's end, not ours.
🌭2
============================
❤2👎1
deepseek/deepseek-v4-pro - 30% off until 17:00 Moscow time
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥8❤3
google/gemini-3.5-flash-lite - $0.10/M input tokens | $0.6/M output tokens
google/gemini-3.6-flash - $0.35/M input tokens | $1.4/M output tokens
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥3
Please open Telegram to view this post
VIEW IN TELEGRAM
❤5
Мы запустили эндпоинт для пользователей из РФ
Менять ключ, баланс или формат запросов не нужно. Достаточно заменить базовый адрес API. Все модели и OpenAI-совместимые методы работают как обычно.
Основной endpoint продолжает работать:
Статус обоих подключений можно проверить на https://aigate.shop/status
============================
We have launched an endpoint for users in the Russian Federation
There is no need to change the key, balance, or request format. Simply replace the base API address. All models and OpenAI-compatible methods work as usual.
The main endpoint continues to work:
You can check the status of both connections at https://aigate.shop/status
https://ru-api.aigate.shop/v1Менять ключ, баланс или формат запросов не нужно. Достаточно заменить базовый адрес API. Все модели и OpenAI-совместимые методы работают как обычно.
Основной endpoint продолжает работать:
https://api.aigate.shop/v1Статус обоих подключений можно проверить на https://aigate.shop/status
============================
We have launched an endpoint for users in the Russian Federation
https://ru-api.aigate.shop/v1There is no need to change the key, balance, or request format. Simply replace the base API address. All models and OpenAI-compatible methods work as usual.
The main endpoint continues to work:
https://api.aigate.shop/v1You can check the status of both connections at https://aigate.shop/status
❤7🔥4
poolside/laguna-s-2.1 - FREE
RPM is limited to 15 per user.
Please open Telegram to view this post
VIEW IN TELEGRAM
❤2
anthropic/claude-opus-5 - $1/M input tokens | $4/M output tokens
Please open Telegram to view this post
VIEW IN TELEGRAM
❤7
google/gemini-3.5-flash-lite - 20% off until 18:00 Moscow time
google/gemini-3.6-flash - 20% off until 18:00 Moscow time
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥2🌭1
z-ai/glm-5.2-ultrafast - $0.7/M input tokens | $2/m output tokens
~500 tokens per second output
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥6🌭1
moonshotai/kimi-k3-fast - $1.1/M input tokens | $3.7/M output tokens
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥8👎2
Модели claude недоступны примерно до конца дня из за технических работ.
============================
Claude models are expected to remain unavailable until approximately the end of the day due to internal issues.
============================
Claude models are expected to remain unavailable until approximately the end of the day due to internal issues.
👎9😁1
qwen/qwen3.7-flash - FREE
RPM is limited to 15 per user
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥9🌭2❤1👎1😁1
openai/gpt-5.6-luna - $0.05/M input tokens | $0.28/M output tokens
openai/gpt-5.6-terra - $0.5/M input tokens | $1.75/M output tokens
Please open Telegram to view this post
VIEW IN TELEGRAM
❤5🔥1
thinkingmachines/inkling-small - FREE
RPM is limited to 15 per user
Please open Telegram to view this post
VIEW IN TELEGRAM
deepseek/deepseek-v3.2 - FREE
RPM is limited to 15 per user
Please open Telegram to view this post
VIEW IN TELEGRAM
❤12🔥4👎3😁2🌭2