Atualmente o conteúdo está disponível apenas em inglês. A versão em português será complementada o mais breve possível. Agradecemos pela compreensão.
关闭
Tencent Cloud Notices > Notice Details
[LLM Service TokenHub] Notice on the Release of Tencent Cloud DeepSeek-V4-Flash GA and Its Vendor Direct Version
2026-08-07 12:20:48
To continuously improve model inference performance and optimize underlying compute scheduling, DeepSeek-V4-Flash GA went live on August 5, 2026, 18:00:00 (Beijing Time); DeepSeek-V4-Flash GA [Vendor Direct] was released in sync with the original manufacturer on July 31, 2026, 18:00:00 (Beijing Time). Following this update, Agent capabilities have been significantly enhanced, with benchmark results far surpassing V4-Pro-Preview.
Note:
Both DeepSeek-V4-Flash GA and its Vendor Direct version correspond to DeepSeek's official DeepSeek-V4-Flash-0731 release. The API calling method remains unchanged:
● DeepSeek-V4-Flash (official release): set the Model ID parameter to deepseek-v4-flash
● DeepSeek-V4-Flash GA[Vendor Direct]: set the Model ID parameter to deepseek-v4-flash-202605
Users currently using the above Model ID parameters will be automatically and seamlessly upgraded by the platform — no action is required to enjoy the capabilities of the new version.
Thank you for your understanding and support. Tencent Cloud will continue to iterate and enhance our large language model product portfolio to provide you with more powerful model capabilities and services.
If you encounter any issues during use, please feel free to submit a ticket for feedback. We will assist you as soon as possible!
