ECS Features

ECS provides secure, scalable, on-demand compute resources with flexible billing modes and easy O&M, greatly reducing your costs.

Kunpeng ECSs

Kunpeng ECSs are powered by Kunpeng processors. They are cost-effective and suitable for heavy workloads. Kunpeng ECSs come in multiple flavors: Kunpeng general computing-plus kC1, Kunpeng memory-optimized kM1, Kunpeng ultra-high I/O kI1, and Kunpeng AI inference-accelerated kAi1s ECSs.

Kunpeng General Computing-plus kC1

Kunpeng general computing-plus kC1 ECSs use Kunpeng 920 processors and 25GE high-speed intelligent NICs to offer powerful computing and high-performance networks, meeting the requirements of governments and Internet enterprises for high cost-effectiveness, high security, and high reliability.

Kunpeng Memory-optimized kM1

Kunpeng memory-optimized kM1 ECSs use Kunpeng 920 processors and 25GE high-speed intelligent NICs to provide up to 480 GiB of DDR4-based memory and high-performance networks. Such ECSs are well suitable for large in-memory datasets.

Kunpeng Ultra-high I/O kI1

Kunpeng ultra-high I/O kI1 ECSs use high-performance local NVMe SSDs to provide high storage input/output operations per second (IOPS) and low read/write latency. You can create such ECSs with high-performance local NVMe SSDs attached on the management console.

Kunpeng AI Inference-accelerated kAi1s

Kunpeng AI inference-accelerated kAi1s ECSs use Huawei Ascend 310 processors to improve energy efficiency ratio (EER) and promote the widespread adoption of AI inference services.

General Computing ECSs (S Series)

General computing ECSs provide a balance of compute, memory, and networking resources and a baseline level of vCPU performance with the ability to burst above the baseline.

Such ECSs are good for general workloads such as web servers, development environment, and small-scale databases.

General Computing-plus ECSs (C Series)

General computing-plus ECSs provide dedicated vCPUs, so there is no CPU contention between ECSs. Such ECSs use the latest-generation network acceleration engines and Data Plane Development Kit (DPDK) to deliver extra network performance for requirements in diverse scenarios.

Memory-optimized ECSs (M Series)

Memory-optimized ECSs provide ultra-high network bandwidth and high packets per second (PPS). They are designed for memory-intensive applications such as precision marketing, e-commerce, and IoV big data analysis.

GPU-accelerated ECSs

GPU-accelerated ECSs provide outstanding floating-point computing capabilities to meet the demands of real-time, highly concurrent massive computing applications.

GPU-accelerated ECSs are classified as graphics-accelerated (G series) and processing-accelerated (P series) ECSs.

• G series ECSs are good for 3D animation rendering and computer-aided design (CAD).

• P series ECSs are good for deep learning, scientific computing, and computer-aided engineering (CAE).


ECS is compatible with the following types of APIs: • ECS-defined APIs (ECS APIs) • Native OpenStack APIs that comply with OpenStack community specifications (OpenStack APIs) The two types of APIs offer similar functions but apply to different application scenarios. You can use OpenStack APIs to interconnect ECSs with open-source ecosystem tools. ECS APIs have enhanced certain functions based on the OpenStack APIs. You are advised to use ECS APIs. OpenStack APIs have V2 and V2.1 versions. V2.1 supports all functions provided by V2. Additionally, V2.1 supports microversions. If you intend to use OpenStack APIs, the V2.1 version is recommended.

All regions


With the ECS SDK package, you can call ECS APIs to create applications on Huawei Cloud.

Currently, SDKs support Java, Python, and Go languages. You can use APIs or any other well-known SDKs.

All regions