Huawei Cloud discontinues support for openPangu-2.0 models on MaaS platform and recommends alternatives
Read more
Pandaily
pandaily.com

Huawei Cloud discontinues support for openPangu-2.0 models on MaaS platform and recommends alternatives

Huawei Cloud has announced plans to decommission the openPangu-2.0-Flash and openPangu-2.0-Pro model services on its MaaS (Model as a Service) platform. According to the model deprecation notice, these services will stop being sold on November 6th Beijing time and will be completely disabled on November 30th.

IT Home reported this notice, which was published on the Huawei Cloud support website on November 3rd. As part of the schedule, new users will be unable to purchase or activate the specified services after November 6th, but existing customers will retain the ability to use them until the end of the month. After November 30th, access to both models will be closed for both new and existing users. The notice lists these services in the CN Southwest-Guiyang1 Huawei Cloud region.

The company offers recommended replacements for each model. Users of openPangu-2.0-Flash version 20260630 are advised to switch to DeepSeek-V4.1-Flash-1017, while users of openPangu-2.0-Pro version 20260730 are directed to Zhipu's GLM-5.3. Huawei Cloud emphasizes that the models differ in capabilities, API parameters, pricing, and real-world performance, and advises customers to review the documentation and conduct their own assessment before switching.

The migration guide indicates that customers using the standard MaaS V1 API will need to switch to an OpenAI-compatible endpoint, whereas those already using API V2 or an OpenAI-compatible interface only need to change the model parameter.

According to IT Home, Huawei Cloud plans to release a new generation of openPangu models incrementally but has not yet disclosed their names or timelines. These two models were among Huawei's largest open releases this year: openPangu-2.0-Flash with 92 billion parameters was released at the end of June, and the sparse openPangu-2.0-Pro model with 505 billion parameters, trained on Ascend NPUs, was released at the end of July. In September, Huawei also released code for pre-training, controlled fine-tuning, and reinforcement learning for this series. However, the deprecation notice applies only to hosted MaaS services and does not affect open releases.

Model changes on the platform happen frequently. In the same bulletin, Huawei Cloud scheduled the decommissioning of GLM-5.1 on November 16th, replacing it with GLM-5.3, and is also migrating users from DeepSeek-V4-Flash to DeepSeek-V4.1-Flash and decommissioning Kimi-K2.6 on November 8th, while also listing several Qwen and Wan models for retirement.

Previously, DeepSeek-V4-Pro was decommissioned in September, and several versions of DeepSeek, Qwen, and GLM were retired in the summer. For MaaS customers, this means that workloads built on openPangu-2.0 must be migrated to other hosted platform models, at least until the next generation of openPangu is available.

Similar stories

Xiaomi discontinues support for MiMo-V2.5 models and transitions API to multimodal equivalents
Read more
technode.com

Xiaomi discontinues support for MiMo-V2.5 models and transitions API to multimodal equivalents

Xiaomi has discontinued the use of MiMo-V2.5-Pro and MiMo-V2.5 models. This decision was made on October 21st at 10 AM Beijing time as part of the transition of their service APIs to newer models in the MiMo-V2.6 family.

Starting October 14th, requests addressed to the old model names are automatically redirected to MiMo-V2.6-Pro and MiMo-V2.6-Flash, respectively. This transition provides users of MiMo-V2.5-Pro, who previously used only text format, with the ability to access multimodal content understanding through substitution.

Furthermore, for users migrating from MiMo-V2.5 to MiMo-V2.6-Flash, the standard maximum completion length has increased from 32,768 to 131,072 tokens. Xiaomi stated that the new models demonstrate superiority over their predecessors in terms of both capabilities and performance, while the V2.6 series maintains the pricing policy of the previous generation's API.

Xiaomi MiMo-V2.6-Pro Model Available in Tencent WorkBuddy and TokenHub with 1 Million Token Context Window
Read more
pandaily.com

Xiaomi MiMo-V2.6-Pro Model Available in Tencent WorkBuddy and TokenHub with 1 Million Token Context Window

The Xiaomi MiMo-V2.6-Pro model is now integrated into the Tencent WorkBuddy agent and hosted on Tencent Cloud TokenHub under the identifier mimo-v2.6-pro. This model features a 1 million token context window and supports compatibility with APIs from OpenAI and Anthropic.

Xiaomi's technical account announced on October 20th that MiMo-V2.6-Pro has been launched within the Tencent WorkBuddy desktop AI agent. A similar model is also available in the Tencent Cloud TokenHub model catalog under the API ID mimo-v2.6-pro.

This development relates to the model's distribution, not the release of a new open version, as Xiaomi already released and opened the source code for the MiMo-V2.6 Pro and Flash models in September. The new step involves integrating Pro into the main Chinese office agent and into the model gateway for multiple vendors in Tencent Cloud, allowing third-party applications to call it using familiar SDKs.

According to Xiaomi, MiMo-V2.6-Pro provides a one-million-token context window, multi-agent task splitting functionality, and joint understanding of images, video, audio, and text. Xiaomi positions the integration with WorkBuddy for long professional workflows such as deep research, document handling, design drafting, and small tool development. The company also cited a score of 46 in the artificial intelligence index as the best result among open models, noting that this rating is a characteristic of a third-party ranking and may change as other models are updated.

On the Tencent Cloud TokenHub platform, mimo-v2.6-pro is documented with a 1 million token context, a maximum input of 1 million tokens, and a maximum output of 128 thousand tokens, along with multimodal understanding, deep reasoning, structured output, function calling, and caching. The endpoint supports OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages formats, enabling teams to direct existing clients to TokenHub without rewriting protocol code. The MiMo-V2.6-Flash model is presented similarly under the identifier mimo-v2.6-flash.

WorkBuddy users can select this model as the backend within the Tencent agent. Developers requiring API access should use TokenHub, rather than Xiaomi's open-source path from September. TokenHub usage rates align with the Tencent Cloud model catalog and differ from Xiaomi's previously available self-service API rates for the MiMo-V2.6 series.

Despite the lack of details on the model's new architecture, this launch marks the appearance of another Chinese foundational model as a first-class option within a major third-party agent and cloud inference hub.

Access to pandaily.com website is restricted using Cloudflare
Read more
pandaily.com

Access to pandaily.com website is restricted using Cloudflare

The owner of the pandaily.com website has temporarily blocked user access to the resource. This restriction is implemented using the Cloudflare service.

For more detailed information about this situation, users can refer to the official Cloudflare documentation on HTTP status codes, specifically at the link https://developers.cloudflare.com/support/troubleshooting/http-status-codes/cloudflare-1xxx-errors/error-1015/.

Popular