The DeepSeek online model has been upgraded, the current version number is DeepSeek-V3.1-Terminus.

DeepSeek announced this evening that the online model has been upgraded, with the current version number DeepSeek-V3.1-Terminus, which includes two versions: the thinking model and the non-thinking model, both with a context length of 128k, and it is now available for users to experience online. Among them, the output length of the non-thinking model is set to 4K by default, with a maximum of 8K, while the output length of the thinking model is set to 32K by default, with a maximum of 64K. In terms of pricing, the model charges 0.5 yuan for one million tokens input (cache hit), 4 yuan for cache misses, and 12 yuan for one million tokens output.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
0/400
No comments
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate App
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)