At 10:00 (Beijing Time) on October 17, 2026, the Tencent Cloud DeepSeek-V4.1-Flash Vendor Direct model was silently upgraded to the DeepSeek-V4.1-Flash-1017 Vendor Direct model.
Upgrade Details:
Historical models DeepSeek-V4-Flash 0731 GA Vendor Direct and DeepSeek-V4-Flash-Vision-Exp Vendor Direct have also been silently upgraded.
Model ID unchanged: all the following model IDs remain available after the upgrade; no changes to your existing code or configuration are required.
deepseek/deepseek-flash
Historical model IDs: deepseek-v4-flash-202605, deepseek/deepseek-v4-flash-0731, deepseek/deepseek-v4-flash, deepseek/deepseek-v4-flash-vision-exp
Existing inference billing unchanged: billing standards for model calls remain as-is and are not affected.
Thank you for your continued attention to and support for Tencent Cloud LLM services. Tencent Cloud will keep iterating its LLM product matrix to bring you more powerful model capabilities and services. If you encounter any issues during use, please feel free to submit a ticket, and we will look into and address them as soon as possible.