このページは現在英語のみで、表示されている言語を準備しています。
关闭
Tencent Cloud のお知らせ > お知らせの詳細
[LLM Service TokenHub] Notice on Decommissioning and Upgrade of Tencent Cloud GLM-5、GLM-5-Turbo、GLM-5.1 Model
2026-09-08 15:04:48
As Tencent Cloud continues to upgrade and iterate its large language models, we will progressively decommission and upgrade older model versions.
In accordance with our upgrade plan, the following models will be officially decommissioned starting at 00:00 (Beijing Time) on October 9, 2026, after which API access to these models will no longer be available:
GLM-5、GLM-5-Turbo、GLM-5.1(model parameter: glm-5、glm-5-0；glm-5-turbo；glm-5.1、glm-5-1)
To ensure the smooth operation of your business, please pay attention to the following guidelines:
1. Recommended Migration
● We recommend migrating to the more capable GLM-5.3 model. For integration documentation, please refer to [LLM Service TokenHub API Protocol Documentation - Tencent Cloud].
2. Business Adjustment Recommendations
Different models vary in pricing and effectiveness. Please check and update the model name (model parameter value) in your code before October 9, 2026 to complete the model switch and avoid any impact on your business calls.
Special Note:
● Pay-as-you-go API users: the system will automatically switch to GLM-5.3;
● Regarding the batch inference service: After GLM-5.1 is decommissioned, its batch inference service will be decommissioned directly without automatic migration. Please make sure to retrieve the results of your batch inference tasks before 00:00 (Beijing Time) on October 9, 2026, to avoid any impact on your business. We will be launching the batch inference service for the Hy3 model in the near future. Please stay tuned.
● If you do not wish the system to automatically switch, please complete model replacement, disable the relevant calls, or submit a ticket before the offline date. If the original model parameters continue to be used after the offline date, the platform will perform automatic switching in accordance with the rules in this announcement to ensure service continuity as much as possible. After automatic switching, related calls will be billed according to the pricing rules of the switched-to model. Please confirm the new model's pricing and applicable scope via the console or billing documentation before the switch takes effect. For billing documentation, please refer to [LLM Service TokenHub Billing Documentation - Tencent Cloud]
● The automatic switch will take effect at 00:00 Beijing time (UTC+8) on October 9, 2026. During the switch, existing API calls may experience a few seconds of request timeout — we recommend implementing a retry mechanism. After the switch is complete, if you are not satisfied with the new model's performance, you may manually switch to another available model at any time.
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 have any questions during use, please submit a ticket for feedback. We will verify and resolve your issue as soon as possible.
