ListPredefinedModels

Updated at:
Copy as MD

Queries the models and their capabilities in the built-in model catalog of AgentCore for a specified provider.

Operation description

Queries the models and their capabilities in the built-in model catalog of AgentCore for a specified provider.

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

agentcore:ListPredefinedModels

get

*All Resource

*

None None

Request syntax

GET /model-catalog/providers/{providerType}/models HTTP/1.1

Path Parameters

Parameter

Type

Required

Description

Example

providerType

string

Yes

The model provider type.

qwen

Request parameters

Parameter

Type

Required

Description

Example

No parameters required.

Response elements

Element

Type

Description

Example

object

The text response returned by the model when model testing is successful. This field is empty if the test fails.

requestId

string

The request ID.

request-1

message

string

The request processing result message.

success

httpStatusCode

integer

The HTTP status code. The value is 200 if the request succeeds.

200

code

string

The business status code. The value is SUCCESS if the request succeeds.

SUCCESS

success

boolean

Indicates whether the request is successful.

data

array<object>

The list of predefined models.

array<object>

The business value of the field.

modelName

string

The upstream model name.

qwen-max

releaseDate

string

The release date of the model, in the YYYY-MM-DD format.

2025-02-01

contextSize

integer

The context window size of the model, in tokens. The value must be a positive integer.

128000

maxTokens

integer

The maximum number of output tokens supported by the model per generation.

131072

capabilities

object

The model capability configuration.

toolCall

boolean

Indicates whether the model supports tool calling.

multiToolCall

boolean

Specifies whether the model is able to invoke multiple tools in a single response through tool calling.

streamToolCall

boolean

Specifies whether the model is able to invoke tools through streaming tool calling.

vision

boolean

Indicates whether the model supports image input.

audio

boolean

Indicates whether the model supports audio input or output.

video

boolean

Indicates whether the model supports video input.

document

boolean

Indicates whether the model supports document input.

reasoning

boolean

Indicates whether the model supports reasoning capabilities.

Examples

Success response

JSON format

{
  "requestId": "request-1",
  "message": "success",
  "httpStatusCode": 200,
  "code": "SUCCESS",
  "success": false,
  "data": [
    {
      "modelName": "qwen-max",
      "releaseDate": "2025-02-01",
      "contextSize": 128000,
      "maxTokens": 131072,
      "capabilities": {
        "toolCall": false,
        "multiToolCall": false,
        "streamToolCall": false,
        "vision": false,
        "audio": false,
        "video": false,
        "document": false,
        "reasoning": false
      }
    }
  ]
}

Error codes

HTTP status code

Error code

Error message

Description

400 InvalidParameter The specified model provider is not supported.

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.