CreateService - Create an EAS model service - Platform For AI

Operation description

**Before you call this operation, read the EAS billing information.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.
API: The API that you can call to perform the action.
Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.
Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.
- For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.
- For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.
Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.
Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

eas:CreateService

create

*All Resource

*

None

Request syntax

POST /api/v2/services HTTP/1.1

Request parameters

Parameter	Type	Required	Description	Example
body	string	No	The request body. Key parameters are listed in Table 1. Request body parameters and Table 2. Metadata parameters. For the full parameter list, see Parameters of model services.	Image deployment service: { "name": "foo", "metadata": { "instance": 2, "memory": 7000, "cpu": 4 }, "containers": [ { "image": "**", "script": " --listen=0.0.0.0 --server_port=8000 --headless", "port": 8000 } ], "storage": [ { "oss": { "path": "oss://examplebuket/data111/", "readOnly": false }, "properties": { "resource_type": "model" }, "mount_path": "/data" } ] } Image deployment AI-Web application: { "name": "foo", "metadata": { "instance": 1, "memory": 7000, "cpu": 4, "enable_webservice": true }, "containers": [ { "image": "", "script": " --listen=0.0.0.0 --server_port=8000 --headless", "port": 8000 } ], "storage": [ { "oss": { "path": "oss://examplebucket/data111/", "readOnly": false }, "properties": { "resource_type": "model" }, "mount_path": "/data" } ] } Model + processor deployment service: { "metadata": { "instance": 1, "memory": 7000, "cpu": 4 }, "name": "foo", "model_config": {}, "processor_type": "python", "processor_path": "oss://", "processor_entry": "a.py", "model_path": "oss://**" }
Develop	string	No	Specifies whether to enter development mode. Valid values: true false Valid values: true : true false :	true
Labels	object	No	The custom label.
	string	No	The label.	{"key":"value"}
WorkspaceId	string	No	The workspace ID.	123456

Table 1. Request body parameters

Parameter	Type	Required	Description
name	String	Yes	The service name. Must be unique within a region.
token	String	No	The authentication token. Auto-generated if omitted and generate_token is set to true.
model_path	String	No	The model file path. Supports HTTP URLs (must be publicly accessible) or OSS paths (directory or file). `.tar.gz`, `.tar.bz2`, and `.zip` files are automatically decompressed.
role_arn	string	No	The RAM role ARN for accessing OSS. Required when model_path or processor_path uses an OSS address.
oss_endpoint	String	No	The OSS bucket endpoint. Required when model_path or processor_path uses an OSS path.
model_entry	String	No	The model entry file. Defaults to model_path if not specified. The path is passed to the processor's `Load()` function.
processor_path	String	Yes	The processor file path. Supports local files or HTTP URLs. `.tar.gz`, `.tar.bz2`, and `.zip` files are automatically decompressed.
processor_entry	String	No	Required if processor_type is C, C++, or Python. The processor entry file containing the `Load()` and `Process()` function implementations.
processor_mainclass	String	No	Required if processor_type is Java. The main class in the processor JAR package.
processor_type	String	Yes	The language that is used to implement the processor. Valid values: C, C++, Java, and Python.
metadata	Dict	No	The service metadata. See Table 2.
cloud	Dict	No	The cloud computing configuration. Required when deploying with a specified instance type. Format: `"cloud":{"computing":{"instance_type": "ecs.gxxxxxx.large"}}`.
containers	List	No	The custom image container configuration. Use this when the built-in processor does not meet your requirements. Deploy a model service by using a custom image.

Description The model_path and processor_path parameters accept HTTP URLs or OSS paths. For local debugging, you can specify local files and directories.

HTTP URLs: compress files into .tar.gz, .tar.bz2, or .zip format and upload to OSS to generate the URL.
OSS paths: specify a directory or file name.

Table 2. Metadata parameters

Parameter	Type	Required	Description	Example
instance	Int	No	The number of workers to start.	1
cpu	Int	No	The number of CPUs per worker.	1
gpu	Int	No	The number of GPUs per worker.	0
memory	Int	No	The memory per worker, in MB.	1000
resource	String	No	The resource group for the service.	eas-r-aaabbbccc
rpc.worker_threads	Int	No	The number of concurrent request-processing threads per instance.	5
rpc.max_queue_size	Int	No	The maximum request queue size. Excess requests return HTTP 450.	64
rpc.keepalive	Int	No	The request timeout, in milliseconds.	5000
rpc.rate_limit	Int	No	The per-instance QPS throttling limit. Excess requests return HTTP 429.	0
release	Bool	No	Specifies whether to enable canary release for the service. Valid values: true and false.	false

Response elements

Element	Type	Description	Example
	object	The response parameters.
RequestId	string	The request ID.	40325405-579C-4D82****
ServiceId	string	The ID of the created service.	eas-m-aaxxxddf
ServiceName	string	The name of the created service.	yourname
Status	string	The service state.	Creating
Region	string	The region ID of the created service.	cn-shanghai
InternetEndpoint	string	The public endpoint of the created service.	http://pai-eas.vpc.cn-shanghai.****
IntranetEndpoint	string	The internal endpoint of the created service.	http://pai-eas.cn-shanghai.****

Examples

Success response

JSON format

{
  "RequestId": "40325405-579C-4D82****",
  "ServiceId": "eas-m-aaxxxddf",
  "ServiceName": "yourname",
  "Status": "Creating",
  "Region": "cn-shanghai",
  "InternetEndpoint": "http://pai-eas.vpc.cn-shanghai.****",
  "IntranetEndpoint": "http://pai-eas.cn-shanghai.****"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.