Help Center> ModelArts> API Reference> Service Management> Obtaining Supported Service Deployment Specifications

Updated on 2024-03-21 GMT+08:00

View PDF

Obtaining Supported Service Deployment Specifications

Function

This API is used to obtain supported service deployment specifications.

Debugging

You can debug this API through automatic authentication in API Explorer or use the SDK sample code generated by API Explorer.

URI

GET /v1/{project_id}/services/specifications

**Table 1** Path Parameters
Parameter	Mandatory	Type	Description
project_id	Yes	String	Project ID. For details, see Obtaining a Project ID and Name.

**Table 2** Query Parameters
Parameter	Mandatory	Type	Description
is_personal_cluster	No	Boolean	Whether to obtain the service deployment flavors supported by dedicated resource pool. The default value is false.
infer_type	No	String	Inference mode. Options: real-time, which is the default value batch edge
limit	No	String	Maximum number of records returned on each page. The default value is 1000.
offset	No	String	Start offset of the returned data. Default value: 0

Request Parameters

**Table 3** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	User token. It can be obtained by calling the IAM API that is used to obtain a user token. The value of X-Subject-Token in the response header is the user token.

Response Parameters

Status code: 200

**Table 4** Response body parameters
Parameter	Type	Description
total_count	Integer	Total number of deployed service specifications.
count	Integer	Number of specifications in the current list.
specifications	Array of Specification objects	Supported service deployment flavors

**Table 5** Specification
Parameter	Type	Description
is_open	Boolean	Whether to enable the flavor. The default value is true. If this parameter is set to false, submit a service ticket to apply for the flavor.
spec_status	String	Specification status. Options: normal: The specification is normal. sellout: The specification cannot be used to deploy services because it is sold out.
specification	String	Unique flavor ID
billing_spec	String	Unique ID of the billing specifications
category	String	The flavor type.
cpu_info	CpuInfo object	Specifies the CPU information of the flavor.
memory_info	MemoryInfo object	Specifies the memory information of the flavor.
gpu_info	GpuInfo object	Specifies the GPU information of the flavor.
npu_info	NpuInfo object	NPU information of the flavor.
source_type	String	Model type, which can be empty or auto. The default value is empty, indicating that the model is generated by the user. If the value is auto, the model is trained using ExeML. The billing mode varies depending on the model type.
is_free	Boolean	Whether the flavor is free of charge. The value true indicates that the flavor is free of charge.
over_quota	Boolean	Whether the quota exceeds the upper limit. The value true indicates that the quota exceeds the upper limit.
extend_params	Integer	Billing item
display_en	String	Specifications description in English
display_cn	String	Specification description

**Table 6** CpuInfo
Parameter	Type	Description
arch	String	Architecture type.
cpu	Number	Number of CPUs

**Table 7** MemoryInfo
Parameter	Type	Description
unit	String	Unit.
memory	Integer	Memory size.

**Table 8** GpuInfo
Parameter	Type	Description
brand	String	Brand.
version	String	Card type.
unit	String	Unit
memory	Integer	Memory size of the card.
gpu	Number	Number of GPUs

**Table 9** NpuInfo
Parameter	Type	Description
brand	String	Brand.
version	String	Card type.
unit	String	Unit
memory	Integer	Memory size of the card.
npu	Integer	Number of NPUs.

Example Requests

GET https://{endpoint}/v1/{project_id}/services/specifications

Example Responses

Status code: 200

Service deployment flavors

{
  "total_count" : 3,
  "count" : 3,
  "specifications" : [ {
    "specification" : "modelarts.vm.cpu.2u",
    "billing_spec" : "modelarts.vm.cpu.2u",
    "category" : "CPU",
    "cpu_info" : {
      "arch" : "x86",
      "cpu" : 2.0
    },
    "memory_info" : {
      "unit" : "GB",
      "memory" : 8
    },
    "gpu_info" : {
      "unit" : "MB",
      "gpu" : 0.0,
      "memory" : 0
    },
    "npu_info" : {
      "unit" : "MB",
      "npu" : 0,
      "memory" : 0
    },
    "display_en" : "CPU: 2 vCPUs | 8 GiB",
    "display_cn" : "CPU: 2 Core 8 GiB",
    "is_open" : true,
    "spec_status" : "normal",
    "is_free" : false,
    "over_quota" : false,
    "extend_params" : 1
  }, {
    "specification" : "modelarts.vm.gpu.p4",
    "billing_spec" : "modelarts.vm.gpu.p4",
    "category" : "GPU",
    "cpu_info" : {
      "arch" : "x86",
      "cpu" : 8.0
    },
    "memory_info" : {
      "unit" : "GB",
      "memory" : 32
    },
    "gpu_info" : {
      "unit" : "GB",
      "brand" : "NVIDIA",
      "version" : "P4",
      "gpu" : 1.0,
      "memory" : 16
    },
    "npu_info" : {
      "unit" : "MB",
      "npu" : 0,
      "memory" : 0
    },
    "display_en" : "CPU: 8 vCPUs | 32 GiB GPU: P4",
    "display_cn" : "CPU: 8 Core 32 GiB GPU: 1 * P4",
    "is_open" : true,
    "spec_status" : "normal",
    "is_free" : false,
    "over_quota" : false,
    "extend_params" : 1
  }, {
    "specification" : "modelarts.vm.ai1.a310",
    "billing_spec" : "modelarts.vm.ai1.a310",
    "category" : "NPU",
    "cpu_info" : {
      "arch" : "x86",
      "cpu" : 2.0
    },
    "memory_info" : {
      "unit" : "GB",
      "memory" : 8
    },
    "gpu_info" : {
      "unit" : "MB",
      "gpu" : 0.0,
      "memory" : 0
    },
    "npu_info" : {
      "unit" : "GB",
      "brand" : "Ascend",
      "version" : "Snt3",
      "npu" : 1,
      "memory" : 8
    },
    "display_en" : "CPU: 2 vCPUs | 8 GiB Ascend: 1 x Ascend snt3",
    "display_cn" : "CPU: 2 cores 8 GiB Ascend: 1 x Ascend snt3",
    "is_open" : false,
    "spec_status" : "normal",
    "is_free" : false,
    "over_quota" : false,
    "extend_params" : 1
  } ]
}