Speech Synthesis - Deploy Model

Prerequisites

Supported region: The features described in this document are only available in the China (Beijing) region, and you must use the API Key from that region.
Account permissions: If you use an Alibaba Cloud sub-account (RAM user), you need to grant the sub-account model invocation, training, and deployment permissions.
Configure environment variables: You have successfully obtained an API Key and configured it as an environment variable.
Prerequisite: Model fine-tuning training is complete. Please first call the Query Tuning Job API to confirm that the job status status is SUCCEEDED before deploying.

Deploy model

China (Beijing)

POST https://dashscope.aliyuncs.com/api/v1/deployments

For Windows CMD, replace $DASHSCOPE_API_KEY with %DASHSCOPE_API_KEY%. For PowerShell, replace it with $env:DASHSCOPE_API_KEY

Request parameters

Headers

Content-Type string (Required)Fixed value: application/jsonAuthorization string (Required)API Key authentication. Format: Bearer sk-xxxx.

Request Body

model_name string (Required)The model ID to deploy (not the base model name, but the model identifier generated after fine-tuning or export). How to obtain:

Fine-tuned model: Use the value of Create a Tuning Job response field output.finetuned_output.
Exported model: Use the value of Query Exported Model Details response field output[].model_name.

plan string (Required)Deployment method. CosyVoice series tuned models only support mu (Model Unit deployment).deploy_spec string (Required)Deployment template specification. Can be obtained from the Query Deployable Models API response field template_id. CosyVoice currently supports:

MU5: Single-machine deployment, capacity must be a multiple of 1.
MU2: Single-machine deployment - flagship complex inference edition, capacity must be a multiple of 8.

capacity integer (Required)The number of resource units for deployment, must be a multiple of base_capacity. The value constraint depends on deploy_spec, see the description above.billing_method string (Required)Billing method. Currently supports POST_PAY (pay-as-you-go).name string (Optional)The display name of the model in the console. If not provided, the value of model_name is used automatically.

Deploy model

curl --location 'https://dashscope.aliyuncs.com/api/v1/deployments' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "<Replace with model_name>",
    "plan": "mu",
    "deploy_spec": "MU5",
    "capacity": 1,
    "billing_method": "POST_PAY"
}'

Response parameters

request_id stringThe unique identifier of the request.output objectJob details.

Properties

deployed_model stringThe unique identifier of the deployed model. Used to query model deployment status and invoke the model.model_name stringModel identifier name.status stringDeployment status:

PENDING: Deploying.
RUNNING: Running.
FAILED: Deployment failed.

base_model stringThe base model used.gmt_create stringDeployment job creation time.gmt_modified stringDeployment job update time.workspace_id stringThe workspace ID associated with the Alibaba Cloud Model Studio API Key. See Get the Workspace ID.charge_type stringBilling mode. post_paid indicates pay-as-you-go.creator stringThe Alibaba Cloud account ID of the creator.modifier stringThe Alibaba Cloud account ID of the modifier.plan stringDeployment method.

code stringError code. Returned when the call fails.message stringDetailed error description. Returned when the call fails.

Success response example
Error response example

Key fields: output.deployed_model (unique identifier of the deployed model), output.status (deployment status).

{
    "request_id": "96020b2e-9072-4c8a-9981-xxxxxxxxx",
    "output": {
        "deployed_model": "cosyvoice-v3-flash-ft-202507011122-xxxx",
        "gmt_create": "2025-07-01T10:30:00.000",
        "gmt_modified": "2025-07-01T10:30:00.000",
        "status": "PENDING",
        "model_name": "cosyvoice-v3-flash-ft-202507011122-xxxx",
        "base_model": "cosyvoice-v3-flash",
        "workspace_id": "llm-xxxxxxxxx",
        "charge_type": "post_paid",
        "creator": "12xxxxxxx",
        "modifier": "12xxxxxxx",
        "plan": "mu"
    }
}

Next step

Deployment is an asynchronous operation. After calling this API, you can use the Query and Manage Deployments API to check the deployment status.

​Prerequisites

​Deploy model