Adding Models in Batches

Create models in batches. (If the provider already exists, new models will be added.)

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

Each account has all the permissions required to call all APIs, but IAM users must be assigned the required permissions.

If you are using role/policy-based authorization, see Permissions Policies and Supported Actions for details on the required permissions.
If you are using identity policy-based authorization, the following identity policy-based permissions are required.

Action

Access Level

Resource Type (*: required)

Condition Key

Alias

Dependencies

workspace:modelProvider:addModel

Write

-

-

-

-

Action	Access Level	Resource Type (*: required)	Condition Key	Alias	Dependencies
workspace:modelProvider:addModel	Write	-	-	-	-

POST /v3/ai-agents/model-providers/{provider_id}/models/batch

**Table 1** Path Parameters
Parameter	Mandatory	Type	Description
provider_id	Yes	String	Provider ID.

**Table 2** Request body parameters
Parameter	Mandatory	Type	Description
models	Yes	Array of CreateModelReq objects	Model list.

**Table 3** CreateModelReq
Parameter	Mandatory	Type	Description
name	Yes	String	Model name.
input	No	Array of strings	Input type array.
provider_model_id	Yes	String	Model ID on the provider side.
description	No	String	Model description.
reasoning	No	Boolean	Whether inference is supported.
cost	No	ModelCost object	Fee information.
context_window	No	Integer	Maximum context window.
max_tokens	No	Integer	Maximum number of output tokens.
compat	No	ModelCompat object	Compatibility configuration.

**Table 4** ModelCost
Parameter	Mandatory	Type	Description
input	No	Double	Fee per million input tokens.
output	No	Double	Fee per million output tokens.
cache_read	No	Double	Cache reading fee per million tokens.
cache_write	No	Double	Cache writing fee per million tokens.

**Table 5** ModelCompat
Parameter	Mandatory	Type	Description
supports_usage_streaming	No	Boolean	Whether usage streaming transmission is supported.
supports_developer_role	No	Boolean	Whether the developer role is supported.

Status code: 200

**Table 6** Response body parameters
Parameter	Type	Description
created_models	Array of ModelItemResp objects	List of created models.
total	Integer	Total number of created models.

**Table 7** ModelItemResp
Parameter	Type	Description
id	String	Model ID.
name	String	Model name.
provider_model_id	String	Model ID on the provider side.
input	Array of strings	Input type array.
description	String	Model description.
is_builtin	Boolean	Whether the model is a built-in model.

Status code: 400

**Table 8** Response body parameters
Parameter	Type	Description
error_code	String	Error code, which is returned upon failure.
error_msg	String	Error message.

Status code: 401

**Table 9** Response body parameters
Parameter	Type	Description
error_code	String	Error code, which is returned upon failure.
error_msg	String	Error message.

Status code: 403

**Table 10** Response body parameters
Parameter	Type	Description
error_code	String	Error code, which is returned upon failure.
error_msg	String	Error message.

Status code: 500

**Table 11** Response body parameters
Parameter	Type	Description
error_code	String	Error code, which is returned upon failure.
error_msg	String	Error message.

None

None

Status Code	Description
200	Operation successful.
400	The request cannot be understood by the server due to malformed syntax.
401	Authorization failed.
403	No permissions.
500	Internal server error.

Parent topic: Model Management

Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.

The system is busy. Please try again later.

For any further questions, feel free to contact us through the chatbot.