On November 15, Huawei Cloud announced that its Model-as-a-Service platform had officially listed the open-source Pangu model openPangu-2.1-Pro, with enhancements across agent development, AI coding and inference optimization. The model is strengthened for deep research, HarmonyOS system control and app development, Ascend operator generation and inference-chain tuning.
Its agent capabilities were optimized on more than 100,000 pieces of specialized data covering skill triggering, tool selection and tool invocation, improving performance on complex, multi-step tasks. Coding support is tailored for the HarmonyOS ArkTS language and app development, with dedicated adaptation for the Ascend operator development workflow.
Key operator and inference-chain optimizations have significantly improved throughput in typical deployment scenarios, the company said. The model will also be integrated into Huawei Cloud products including AgentArts, CodeArts and OfficeAce.
Pricing is set at 0.8 yuan per million input tokens, 3.2 yuan per million output tokens and 0.016 yuan for cache hits, positioning the model as a lower-cost option for enterprise AI deployments.





