Model Deployment API Reference-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心

This document uses the Qwen model deployment as an example to demonstrate how to use the model deployment feature of Alibaba Cloud Model Studio through HTTP API calls.

ImportantThe regions where the model deployment APIs are available vary by deployment mode: model unit (MU) and Dedicated Throughput (DTU)s are available in China (Beijing); provisioned throughput (PTU) and other deployment modes are available in Beijing and Singapore.

Prerequisites

You have read Dedicated Deployment Overview and Deploy Models Using APIs to understand how to use model deployment APIs and the basic steps for deploying models on Alibaba Cloud Model Studio.
You have configured your Model Studio API key. For more information, see Obtain an API Key.
DTU (dedicated compute) deployments use the same set of deployment APIs. Set plan="dtu" in requests to distinguish the deployment type. DTU requests must use the workspace-scoped maas.aliyuncs.com domain of the region and workspace where the deployment resides (for example, ws-vxxx.cn-beijing.maas.aliyuncs.com) together with the API key of that workspace, instead of dashscope.aliyuncs.com.
The request domain varies by region: use dashscope.aliyuncs.com for the China (Beijing) region and dashscope-intl.aliyuncs.com for the Singapore region. The workspace-specific domain ({WorkspaceId}.{region}.maas.aliyuncs.com) is available in all regions. For the complete regional domain information, see Regional access information.
DTU deployments support pre-paid billing only (charge_type="pre_paid"); post-paid creation is not supported. Renewal and auto-renewal changes are currently supported only in the console. The DTU APIs do not support the AssumedRoleUser role. Before using DTU, enable the DTU feature in the console and apply for a resource quota. For more information, see Dedicated Throughput (DTU).

Get a List of Deployable Models

GET https://dashscope.aliyuncs.com/api/v1/deployments/models

Request Example

Run the following command to list deployable models. Use version=v1.0 to retrieve a full response that includes deployment plans and templates.

curl "https://dashscope.aliyuncs.com/api/v1/deployments/models?page_no=1&page_size=100&version=v1.0&model_source=base" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Query fine-tuned models:

curl "https://dashscope.aliyuncs.com/api/v1/deployments/models?page_no=1&page_size=100&version=v1.0&model_source=custom" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Query DTU deployment plans (when plan=dtu is passed, only DTU pre-paid templates are returned and the version parameter is not required; DTU uses the workspace-scoped domain):

curl "https://ws-vxxx.cn-beijing.maas.aliyuncs.com/api/v1/deployments/models?plan=dtu&model_source=base&page_no=1&page_size=100" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Request Parameters

Parameter	Type	Passing Parameters	Required	Description
page_no	Number	query	No	Page number. Default is 1.
page_size	Number	query	No	Page size. Default is 50. Maximum is 100. Minimum is 1.
model_source	String	query	No	Model source. `base` means system models (default). `custom` means fine-tuned models.
version	String	query	No	API version. Use `v1.0`. When you use `v1.0`, the response includes full deployment plan and template information.
plan	String	query	No	Pass `dtu` to query DTU deployment plans. Only DTU pre-paid templates are returned (see the DTU template fields below). If omitted, the original model catalog is returned and DTU plans are not included.

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

{
    "request_id": "f7da015c-ea90-4d96-af89-2f8d7604026a",
    "output": {
        "page_no": 1,
        "page_size": 100,
        "total": 5,
        "models": [
            {
                "model_name": "qwen3-8b",
                "plans": [
                    {
                        "plan": "mu",
                        "templates": [
                            {
                                "template_id": "MU1",
                                "template_name": "Single-Node Deployment – Standard Inference",
                                "template_type": "COUPLED",
                                "template_version": "v1",
                                "template_desc": "For standard inference scenarios",
                                "roles": {
                                    "unified": {
                                        "model_unit_spec": "MU1",
                                        "capacity_unit_per_instance": 4
                                    }
                                }
                            },
                            {
                                "template_id": "MU1-PD",
                                "template_name": "PD-Separated Deployment – Standard Inference",
                                "template_type": "SEPERATED",
                                "template_version": "v1",
                                "template_desc": "For PD-separated inference scenarios",
                                "roles": {
                                    "prefill": {
                                        "model_unit_spec": "MU1",
                                        "capacity_unit_per_instance": 4
                                    },
                                    "decode": {
                                        "model_unit_spec": "MU1",
                                        "capacity_unit_per_instance": 4
                                    }
                                }
                            }
                        ]
                    },
                    {
                        "plan": "lora"
                    }
                ]
            }
        ]
    }
}

Response Parameters

Parameter	Type	Description
models	Array	List of deployable models.
models[].model_name	String	Model name.
models[].plans	Array	List of supported deployment plans for this model. Returned when using `version=v1.0`.
models[].plans[].plan	String	Deployment plan type: `dtu` (DTU dedicated compute, pre-paid only), `mu` (model unit), `cu` (compute unit), `ptu_v2` (pre-provisioned throughput v2), or `lora` (LoRA shared deployment).
models[].plans[].templates	Array	List of deployment templates. Returned when `plan=mu`.
page_no	Number	Page number of the query.
page_size	Number	Page size of the query.
total	Long	Total number of models that match the query criteria.

Template field description (templates)

Parameter	Type	Description
template_id	String	Template ID. Pass it as the `template_id` parameter in Create a Model Deployment Task.
template_name	String	Template display name.
template_type	String	Template type: `COUPLED` (non-PD-separated, uses the `capacity` parameter) or `SEPERATED` (PD-separated, uses `prefill_capacity` and `decode_capacity` parameters).
template_version	String	Template version.
template_desc	String	Template description.
roles	Object	Node role configuration. COUPLED mode has a `unified` node. SEPERATED mode has `prefill` and `decode` nodes.

Roles Node Fields

Parameter	Type	Description
model_unit_spec	String	Model unit specification.
capacity_unit_per_instance	Number	Capacity units per instance, also called base_capacity. When you create a deployment, `capacity` must be a multiple of this value.

DTU Template Fields (returned when plan=dtu)

Parameter	Type	Description
charge_type	String	Always `pre_paid` (subscription).
sku_code	String	SKU used when you create the deployment.
template_code	String	Deployment template used when you create the deployment. It must belong to the same template item as `sku_code`.
input_tpm_quota	Object	Purchasable range and step for input TPM. See the table below.
output_tpm_quota	Object	Purchasable range and step for output TPM. See the table below.
display_meta	Object	Display information such as plan name, description, and tags. Returned when available.
standard_workload	Object	Standard workload provided by the template (TPM units and workload tiers). Returned when available.

input_tpm_quota and output_tpm_quota specify the purchase rules for input and output TPM respectively. Capacity is measured in tokens/min. They include the following fields:

Field	Type	Description
init	Integer	Minimum purchasable TPM for this dimension. The purchased capacity must not be less than this value.
max	Integer	Maximum purchasable TPM. If max=0 for either dimension, no quota is currently available. Contact sales to apply for resources; 0 does not mean unlimited.
step	Integer	Purchase step for this dimension. The purchased TPM must be an integer multiple of this step (not an offset added on top of init).

When you create or scale a DTU deployment, the dtu_capacity.input_tpm and dtu_capacity.output_tpm you pass must meet all of the following requirements:

Input and output TPM are each within their own [init, max] range.
Input TPM is an integer multiple of input_tpm_quota.step, and output TPM is an integer multiple of output_tpm_quota.step.
Input and output must use the same step multiple: input_tpm / input_tpm_quota.step = output_tpm / output_tpm_quota.step = n (n is a positive integer). You cannot choose different multiples independently.

For example, if the input range is init=10000, max=100000, step=10000 and the output range is init=1000, max=10000, step=1000: buying input 30000 and output 3000 (both 3 times the step, valid); buying input 30000 and output 2000 (multiples 3 and 2, invalid); buying input 15000 and output 1500 (not integer multiples of the steps, invalid).

Create a Model Deployment Task

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

Request Example

DTU Dedicated Compute Deployment

Subscription billing. Capacity is purchased as input/output TPM (uses the workspace-scoped domain; query sku_code, template_code, and the capacity range with plan=dtu in Get a List of Deployable Models). DTU is the successor to model unit (MU) deployment and is recommended for new dedicated deployments:

curl "https://ws-vxxx.cn-beijing.maas.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "your-supported-model",
    "display_name": "Business model service",
    "suffix": "production",
    "plan": "dtu",
    "sku_code": "your-prepaid-sku",
    "template_code": "your-template",
    "charge_type": "pre_paid",
    "pre_paid_info": {
        "pricing_cycle": "Month",
        "duration": 1,
        "auto_renewal": false
    },
    "dtu_capacity": {"input_tpm": 10000, "output_tpm": 10000}
}'

Model Unit Deployment (COUPLED Mode)

Use template_id to specify MU1 and set capacity to the number of capacity units:

curl "https://dashscope.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "qwen3-8b",
    "plan": "mu",
    "template_id": "MU1",
    "capacity": 4
}'

Model Unit Deployment (PD-Separated Mode)

Use the MU1-PD template. Set prefill_capacity and decode_capacity:

curl "https://dashscope.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "qwen3-8b",
    "plan": "mu",
    "template_id": "MU1-PD",
    "prefill_capacity": 4,
    "decode_capacity": 8
}'

PTU v2 Deployment

Billed by token usage:

curl "https://dashscope.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "qwen3-8b",
    "plan": "ptu_v2"
}'

LoRA Shared Deployment

Billed by token usage:

curl "https://dashscope.aliyuncs.com/api/v1/deployments" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model_name": "qwen3-8b-ft-202511132025-0260",
    "plan": "lora"
}'

Request Parameters

Parameter	Type	Parameter passing	Required	Description
model_name	String	body	Yes	Name of the model to deploy.
plan	String	body	Yes	Deployment plan: `dtu` (DTU dedicated compute, pre-paid only), `mu` (model unit), `cu` (compute unit), `ptu_v2` (pre-provisioned throughput v2), or `lora` (LoRA shared deployment).
template_id	String	body	This parameter is required.	Template ID. Must match the `template_id` returned by the Get Deployable Models API. Required when `plan` is `mu`. We recommend using this parameter to specify the model unit spec.
deploy_spec (deprecated)	String	body	No	Model unit spec. Deprecated.
capacity	Number	body	This parameter is required.	Target number of capacity units. Required for COUPLED mode (non-PD-separated). Must be a multiple of `capacity_unit_per_instance`. Ignored but required when billing by token usage (`plan` is `lora`).
prefill_capacity	Number	body	This parameter is required.	Prefill capacity. Required for PD-separated mode (`template_type` is `SEPERATED`).
decode_capacity	Number	body	This parameter is required.	Decode capacity. Required for PD-separated mode (`template_type` is `SEPERATED`).
name	String	body	No	Service display name.
suffix	String	body	No	When you deploy a model, a new model name is generated. The suffix sets the suffix for the new model name. Max length is 8 characters. Must be globally unique. You can omit the suffix for the first deployment of a model. You must set it for later deployments of the same model.
charge_type	String	body	No	Billing method: `post_paid` (pay-as-you-go, default) or `pre_paid` (subscription).
pre_paid_info	Object	body	This parameter is required.	Subscription info. Required when `charge_type` is `pre_paid`. Includes: `auto_renewal` (Boolean, enable auto-renewal), `duration` (Number, subscription duration in months), and `auto_renewal_duration` (Number, auto-renewal duration in months).
pre_paid_info.auto_renewal	Boolean	body	Yes	Enable auto-renewal.
pre_paid_info.duration	Integer	body	Yes	Subscription duration in months.
pre_paid_info.auto_renewal_duration	Integer	body	Conditionally required	Auto-renewal duration in months. Required when autoRenewal=true.
enable_thinking	Boolean	body	No	Enable thinking mode. Supported by some models.
max_context_length	Number	body	No	Maximum context length. Supported by some models.
quantization_precision	String	body	No	Quantization precision.
qpm_limit	Number	body	No	QPM rate limit. Requests per minute. Supported only by some models with `plan` = `mu`.
tpm_limit	Number	body	No	TPM rate limit. Tokens per minute. Supported only by some models with `plan` = `mu`.
display_name	String	body	Conditionally required	Service display name. Max length is 50 characters. Used when `plan` is `dtu` (other plans use `name`).
sku_code	String	body	Conditionally required	Pre-paid SKU available for the current model. Required when `plan` is `dtu`.
template_code	String	body	Conditionally required	Deployment template that matches the model and SKU. Required when `plan` is `dtu`.
dtu_capacity	Object	body	Conditionally required	DTU capacity to purchase. Required when `plan` is `dtu`. You must provide both `input_tpm` and `output_tpm`. For the rules, see the TPM purchase range and steps in Get a List of Deployable Models.
dtu_capacity.input_tpm	Integer	body	Yes	Purchased input TPM (tokens/min). Non-negative integer. Maximum is 2147483647.
dtu_capacity.output_tpm	Integer	body	Yes	Purchased output TPM (tokens/min). Non-negative integer. Maximum is 2147483647.
pre_paid_info.pricing_cycle	String	body	Yes	Billing cycle. For DTU, set it to `Month` (omitting it or passing another value returns InvalidParameter).
pre_paid_info.auto_renewal_cycle	String	body	Conditionally required	Auto-renewal cycle. Required when auto-renewal is enabled. Must conform to the product rules.

NoteAdditional notes for plan = dtu: suffix can be up to 24 characters, and the generated full deployment identifier must not exceed 100 characters; name, random_suffix, deploy_spec, MU/PTU capacity fields, model routing, rate limit, and publishing parameters are not supported — configure rate limits through the rate limit API after the deployment is ready; a successful create response only indicates that the request is accepted (the pre-paid order is processing) — poll the deployment details until the status is RUNNING; renewal and auto-renewal changes must be performed in the console.

Supported Models

Model Unit deployment supports features such as rate limiting and inference acceleration. This table shows which features are supported.

Text generation

Qwen

Model name	Model code	Model unit specification	Hourly unit price (CNY) Minimum billing: minute	Monthly unit price (CNY) Minimum billing: day
Qwen3.6-35B-A3B	qwen3.6-35b-a3b	MU1 x 8	¥432	¥208,944
		MU2 x 8	¥504	¥240,288
		MU3 x 8	¥1,096	¥527,752
		MU9 x 1	¥51	¥24,600
Qwen3.6-27B	qwen3.6-27b	MU9 x 1	¥51	¥24,600
Qwen3.6-Flash-2026-04-16	qwen3.6-flash-2026-04-16	MU1 x 2	¥108	¥52,236
Qwen3.6-Flash-2026-04-16	qwen3.6-flash-2026-04-16	MU3 x 8	¥1,096	¥527,752
Qwen3.6-Plus-2026-04-02	qwen3.6-plus-2026-04-02	MU1 x 8 MU1 x 16 (PD separation mode)	¥432 PD separation mode: ¥864	¥208,944 PD separation mode: ¥417,888

Qwen3.5-397B-A17B	qwen3.5-397b-a17b	MU3 x 8 MU3 x 16 (PD separation mode)	¥1,096 PD separation mode: ¥2,192	¥527,752 PD separation mode: ¥1,055,504
Qwen3.5-397B-A17B	qwen3.5-397b-a17b	MU6 x 16	¥400	¥193,424
Qwen3.5-122B-A10B	qwen3.5-122b-a10b	MU1 x 4	¥216	¥104,472
Qwen3.5-122B-A10B	qwen3.5-122b-a10b	MU6 x 16	¥400	¥193,424
Qwen3.5-35B-A3B	qwen3.5-35b-a3b	MU1 x 2	¥108	¥52,236
		MU2 x 8	¥504	¥240,288
		MU3 x 8	¥1,096	¥527,752
		MU9 x 1	¥51	¥24,600
Qwen3.5-27B	qwen3.5-27b	MU2 x 8	¥504	¥240,288
		MU3 x 8	¥1,096	¥527,752
		MU8 x 1	¥47	¥22,400
		MU9 x 1	¥51	¥24,600
Qwen3.5-9B	qwen3.5-9b	MU2 x 2	¥126	¥60,072
Qwen3.5-Flash-2026-02-23	qwen3.5-flash-2026-02-23	MU1 x 2	¥108	¥52,236
Qwen3.5-Plus-2026-02-15	qwen3.5-plus-2026-02-15	MU1 x 8 MU1 x 16 (PD separation mode)	¥432 PD separation mode: ¥864	¥208,944 PD separation mode: ¥417,888
		MU2 x 8	¥504	¥240,288
		MU3 x 8 MU3 x 16 (PD separation mode)	¥1,096 PD separation mode: ¥2,192	¥527,752 PD separation mode: ¥1,055,504

Qwen3-235B-A22B-Instruct-2507	qwen3-235b-a22b-instruct-2507	MU1 x 4	¥216	¥104,472
		MU2 x 8	¥504	¥240,288
		MU3 x 8	¥1,096	¥527,752
Qwen3-32B	qwen3-32b	MU6 x 16	¥400	¥193,424
Qwen3-30B-A3B-Thinking-2507	qwen3-30b-a3b-thinking-2507	MU1 x 2	¥108	¥52,236
Qwen3-8B	qwen3-8b	MU1 x 2	¥108	¥52,236
Qwen3-8B	qwen3-8b	MU2 x 2	¥126	¥60,072
Qwen3-4B	qwen3-4b	MU1 x 2	¥108	¥52,236
Qwen3-4B	qwen3-4b	MU5 x 1	¥21	¥10,139
Qwen3-Embedding-0.6B	qwen3-embedding-0.6b	MU5 x 1	¥21	¥10,139
Qwen3-Embedding-0.6B	qwen3-embedding-0.6b	MU6 x 1	¥25	¥12,089
Qwen3-MoE-Rerank-0.6B	qwen3-moe-rerank-0.6b	MU5 x 1	¥21	¥10,139
Qwen3-Rerank-0.6B	qwen3-rerank-0.6b	MU5 x 1	¥21	¥10,139
Qwen3-Rerank-0.6B	qwen3-rerank-0.6b	MU6 x 1	¥25	¥12,089
Qwen3-Max-2025-09-23	qwen3-max-2025-09-23	MU2 x 8	¥504	¥240,288
Qwen3-Max-2025-09-23	qwen3-max-2025-09-23	MU3 x 8	¥1,096	¥527,752
Qwen3-Rerank	qwen3-rerank	MU5 x 1	¥21	¥10,139

Qwen2.5-72B (Open Source)	qwen2.5-72b-instruct	MU1 x 8	¥432	¥208,944
Qwen2.5-14B (Open Source)	qwen2.5-14b-instruct	MU1 x 2	¥108	¥52,236
Qwen2.5-7B (Open Source)	qwen2.5-7b-instruct	MU1 x 2	¥108	¥52,236
Qwen2.5-7B (Open Source)	qwen2.5-7b-instruct	MU5 x 1	¥21	¥10,139

Qwen-Plus-2025-07-28	qwen-plus-2025-07-28	MU1 x 4 MU1 x 16 (PD separation mode)	¥216 PD separation mode: ¥864	¥104,472 PD separation mode: ¥417,888
Qwen-Plus-2025-12-01	qwen-plus-2025-12-01	MU1 x 4	¥216	¥104,472
Qwen-Plus-Character-2025-11-06	qwen-plus-character-2025-11-06	MU1 x 4	¥216	¥104,472

GLM

Model name	Model code	Model unit specification	Hourly unit price (CNY) Minimum billing: minute	Monthly unit price (CNY) Minimum billing: day
GLM-5.1	glm-5.1	MU2 x 8	¥504	¥240,288
		MU3 x 16 (PD separation mode)	PD separation mode: ¥2,192	PD separation mode: ¥1,055,504
		MU6 x 16	¥400	¥193,424
GLM-5	glm-5	MU3 x 16 (PD separation mode)	PD separation mode: ¥2,192	PD separation mode: ¥1,055,504
GLM-4.7	glm-4.7	MU6 x 32 (PD separation mode)	PD separation mode: ¥800	PD separation mode: ¥386,848

DeepSeek

Model name	Model code	Model unit specification	Hourly unit price (CNY) Minimum billing: minute	Monthly unit price (CNY) Minimum billing: day
DeepSeek-v4-Flash	deepseek-v4-flash	MU1 x 8	¥432	¥208,944
MU3 x 8	¥1,096	¥527,752
DeepSeek-v3.2	deepseek-v3.2	MU2 x 16 (PD separation mode)	PD separation mode: ¥1,008	PD separation mode: ¥480,576

Model name

Model code

Model unit specification

Hourly unit price (CNY)

Minimum billing: minute

Monthly unit price (CNY)

Minimum billing: day

DeepSeek-v4-Flash

deepseek-v4-flash

MU1 x 8

¥432

¥208,944

MU3 x 8

¥1,096

¥527,752

DeepSeek-v3.2

deepseek-v3.2

MU2 x 16 (PD separation mode)

PD separation mode: ¥1,008

PD separation mode: ¥480,576

More models

Model name	Model code	Model unit specification	Hourly unit price (CNY) Minimum billing: minute	Monthly unit price (CNY) Minimum billing: day
Kimi-K2.5	kimi-k2.5	MU2 x 8	¥504	¥240,288

Model name

Model code

Model unit specification

Hourly unit price (CNY)

Minimum billing: minute

Monthly unit price (CNY)

Minimum billing: day

Kimi-K2.5

kimi-k2.5

MU2 x 8

¥504

¥240,288

Model type:

Instruct - After deployment, the model performs inference in non-thinking mode.
Thinking - After deployment, the model performs inference in thinking mode.

Model deployment type:

PD separation mode - Reduces first-token latency and increases throughput. For models deployed in this mode, during inference the first-token computation (Prefill) and subsequent-token computation (Decode) — two computation phases — are split onto different compute nodes.

Multimodal

Qwen-VL

Model name	Model code	Model unit specification	Hourly unit price (CNY) Minimum billing: minute	Monthly unit price (CNY) Minimum billing: day
Qwen3-VL-235B-A22B-Thinking	qwen3-vl-235b-a22b-thinking	MU1 x 8	¥432	¥208,944
		MU2 x 8	¥504	¥240,288
		MU3 x 8	¥1,096	¥527,752
Qwen3-VL-32B-Instruct	qwen3-vl-32b-instruct	MU2 x 8	¥504	¥240,288
Qwen3-VL-32B-Instruct	qwen3-vl-32b-instruct	MU3 x 8	¥1,096	¥527,752
Qwen3-VL-8B-Instruct	qwen3-vl-8b-instruct	MU1 x 2	¥108	¥52,236
Qwen3-VL-8B-Instruct	qwen3-vl-8b-instruct	MU5 x 1	¥21	¥10,139
Qwen3-VL-4B-Instruct	qwen3-vl-4b-instruct	MU1 x 2	¥108	¥52,236
Qwen3-VL-2B-Instruct	qwen3-vl-2b-instruct	MU5 x 1	¥21	¥10,139
Qwen3-VL-Embedding-2B	qwen3-vl-embedding-2b	MU5 x 1	¥21	¥10,139
Qwen3-VL-Flash-2025-10-15	qwen3-vl-flash-2025-10-15	MU1 x 4	¥216	¥104,472
Qwen3-VL-Plus-2025-09-23	qwen3-vl-plus-2025-09-23	MU1 x 4	¥216	¥104,472

Qwen-VL-Max-2025-08-13	qwen-vl-max-2025-08-13	MU6 x 4	¥100	¥48,356

Qwen Omni

Model name	Model code	Model unit specification	Hourly unit price (CNY) Minimum billing: minute	Monthly unit price (CNY) Minimum billing: day
Qwen3.5-Omni-Flash	qwen3.5-omni-flash	MU9 x 1	¥51	¥24,600

Model name

Model code

Model unit specification

Hourly unit price (CNY)

Minimum billing: minute

Monthly unit price (CNY)

Minimum billing: day

Qwen3.5-Omni-Flash

qwen3.5-omni-flash

MU9 x 1

¥51

¥24,600

Model type:

Instruct - After model deployment, inference is performed in non-thinking mode.
Thinking - After model deployment, inference is performed in thinking mode.
Instruct/Thinking - You can choose whether to enable thinking mode during model deployment.

Speech synthesis

CosyVoice

Model name	Model code	Model unit specification	Hourly unit price (CNY)	Monthly unit price (CNY)
cosyvoice-v3-flash	cosyvoice-v3-flash	MU5	¥21	¥10,139

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

{
    "request_id": "f2ae64f7-83cc-410c-bc0b-840443f7eb86",
    "output": {
        "deployed_model": "qwen3-8b-20260115-abcd",
        "name": "My Model Service",
        "model_name": "qwen3-8b",
        "base_model": "qwen3-8b",
        "status": "PENDING",
        "capacity": 4,
        "ready_capacity": 0,
        "base_capacity": 4,
        "workspace_id": "llm-8v53e*******",
        "charge_type": "post_paid",
        "plan": "mu",
        "model_unit_spec": "MU1",
        "creator": "16542902******",
        "modifier": "16542902******",
        "qpm_limit": 100000000,
        "tpm_limit": 3600000,
        "mu_capacity": {
            "unified": {
                "base_capacity": 4,
                "model_unit_spec": "MU1",
                "ready_capacity": 0,
                "capacity": 4
            }
        },
        "gmt_create": "2026-01-15T10:00:00",
        "gmt_modified": "2026-01-15T10:00:00"
    }
}

Parameter	Type	Description
request_id	String	ID of this request.
output	Object	Detailed information about this deployment task.
deployed_model	String	Unique identifier for the new model. Pass it in SDK parameters when you call the model.
name	String	Service display name.
model_name	String	Model name used for this deployment task.
base_model	String	Base model ID for the model used in this deployment task.
status	String	Status of the deployment task. PENDING — Creating the deployment task. DEPLOYING — Deploying. WAIT_PRE_PAID_BILLING_TO_DEPLOYING — Creation is waiting for the pre-paid order to be processed (DTU). WAIT_PRE_PAID_BILLING_TO_SCALING — Scaling is waiting for the pre-paid order to be processed (DTU). RUNNING — Running and ready to process requests. SCALING — Scaling. UPDATING — Updating the deployment task. UPDATING_PAUSED — Update paused. SUSPENDING — Suspending (due to overdue payment). SUSPENDED — Suspended (due to overdue payment). STOPPING — Stopping. STOPPED — Stopped. No longer billed. STARTING — Starting (from STOPPED or FAILED state). FAILED — Failed to create or update the deployment task. DELETING — Deleting the deployment task.
capacity	Number	Target number of capacity units for this deployment task.
ready_capacity	Number	Number of capacity units that are ready and can immediately process requests.
base_capacity	Number	Base capacity per instance.
workspace_id	String	ID of the workspace where this deployment task belongs.
charge_type	String	`post_paid`: pay-as-you-go. `pre_paid`: subscription.
plan	String	Billing mode for this deployment task.
model_unit_spec	String	Model unit specification.
gmt_create	String	Time when the deployment task was created.
gmt_modified	String	You can modify the deployment task time.
creator	String	UID of the user who created this deployment task.
modifier	String	UID of the account that last performed an operation on this deployment task.
fail_reason	String	Failure reason. Returned only when status is FAILED.
enable_thinking	Boolean	Enable thinking mode. Supported by some models.
max_context_length	Number	Maximum context length limit.
qpm_limit	Number	QPM rate limit. Requests per minute.
tpm_limit	Number	TPM rate limit. Tokens per minute.
quantization_precision	String	Quantization precision.
Returned only for DTU (dtu) deployments.
dtu_capacity	Object	Purchased capacity recorded for the deployment. During scaling, this may still be the original capacity. Do not assume the target has taken effect based on this value.
dtu_capacity.input_tpm	Integer	Purchased input token capacity (tokens/min).
dtu_capacity.output_tpm	Integer	Purchased output token capacity (tokens/min).
pre_paid_info.pricing_cycle	String	Returned billing cycle (for example, `Month`). It can be `null`, which means this value is not provided in the response. It does not indicate a failed order or a zero-month subscription.
pre_paid_info.auto_renewal_cycle	String	Returned auto-renewal cycle. Returned when available.
pre_paid_instance_id	String	Subscription instance ID. Returned when available. It is not the deployment identifier and cannot replace `deployed_model`.
Returned only for model unit (mu) deployments.
mu_capacity	Object	MU capacity details. COUPLED mode has a `unified` node. SEPERATED mode has `prefill` and `decode` nodes. Each node includes: base_capacity, model_unit_spec, ready_capacity, and capacity.
pre_paid_info	Object	Subscription information.
pre_paid_info.auto_renewal	Boolean	Enable auto-renewal.
pre_paid_info.duration	Integer	Subscription duration in months.
pre_paid_info.auto_renewal_duration	Integer	Auto-renewal duration in months.
pre_paid_instance_id	String	Subscription instance ID.
pre_paid_gmt_expired	String	Subscription expiration time.
Returned only for pre-provisioned throughput v2 (ptu_v2) deployments.
ptu_capacity	Object	PTU v2 capacity info. Includes: `input_tpm_quota` (Number, input TPM quota) `output_tpm_quota` (Number, output TPM quota)
pre_paid_info	Object	Subscription information.
pre_paid_info.auto_renewal	Boolean	Enable auto-renewal.
pre_paid_info.duration	Integer	Subscription duration in months.
pre_paid_info.auto_renewal_duration	Integer	Auto-renewal duration in months.
pre_paid_instance_id	String	Subscription instance ID.
pre_paid_gmt_expired	String	Subscription expiration time.

For DTU deployments, qpm_limit and tpm_limit are gateway rate limit settings (64-bit integers that may exceed the request limit of the rate limit API). Defaults are qpm_limit=600000 and tpm_limit=output_tpm × 100. They are not the purchased input/output TPM and do not represent a guaranteed inference throughput. The gmt_create and gmt_modified strings do not include a timezone offset. Do not treat them as UTC time.

Query a Model Deployment Task

GET https://dashscope.aliyuncs.com/api/v1/deployments/{deployed_model}

Request Example

curl "https://dashscope.aliyuncs.com/api/v1/deployments/qwen3-8b-20260115-abcd" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Request Parameters

Parameter	Type	Passing Parameters	Required	Description
deployed_model	String	path	Yes	Unique identifier for the deployed model. Get it from Create a Model Deployment Task or List Model Deployment Tasks.

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

{
    "request_id": "d8b8c47b-ae32-4c41-b9f4-9a1e2b3c4d5e",
    "output": {
        "deployed_model": "qwen3-8b-20260115-abcd",
        "name": "My Model Service",
        "model_name": "qwen3-8b",
        "base_model": "qwen3-8b",
        "status": "RUNNING",
        "capacity": 4,
        "ready_capacity": 4,
        "base_capacity": 4,
        "workspace_id": "llm-8v53e*******",
        "charge_type": "post_paid",
        "plan": "mu",
        "model_unit_spec": "MU1",
        "creator": "16542902******",
        "modifier": "16542902******",
        "qpm_limit": 100000000,
        "tpm_limit": 3600000,
        "mu_capacity": {
            "unified": {
                "base_capacity": 4,
                "model_unit_spec": "MU1",
                "ready_capacity": 4,
                "capacity": 4
            }
        },
        "gmt_create": "2026-01-15T10:00:00",
        "gmt_modified": "2026-01-15T10:30:00"
    }
}

Response Parameters

The response parameters are the same as those for creating a model deployment task. For more information, see Response Parameters for Create a Model Deployment Task.

List Model Deployment Tasks

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

Request Example

curl "https://dashscope.aliyuncs.com/api/v1/deployments?page_no=1&page_size=10" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Request Parameters

Parameter	Type	Parameter passing	Required	Description
page_no	Number	query	No	Page number. Default is 1.
page_size	Number	query	No	Page size. Default is 10. Maximum is 100.
plan	String	query	No	Pass `dtu` to list DTU deployments. Status filtering is not supported for DTU deployments.

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

{
    "request_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "output": {
        "page_no": 1,
        "page_size": 10,
        "total": 2,
        "deployments": [
            {
                "deployed_model": "qwen3-8b-20260115-abcd",
                "name": "My Model Service",
                "model_name": "qwen3-8b",
                "base_model": "qwen3-8b",
                "status": "RUNNING",
                "capacity": 4,
                "ready_capacity": 4,
                "base_capacity": 4,
                "workspace_id": "llm-8v53e*******",
                "charge_type": "post_paid",
                "plan": "mu",
                "model_unit_spec": "MU1",
                "creator": "16542902******",
                "modifier": "16542902******",
                "qpm_limit": 100000000,
                "tpm_limit": 3600000,
                "mu_capacity": {
                    "unified": {
                        "base_capacity": 4,
                        "model_unit_spec": "MU1",
                        "ready_capacity": 4,
                        "capacity": 4
                    }
                },
                "gmt_create": "2026-01-15T10:00:00",
                "gmt_modified": "2026-01-15T10:30:00"
            }
        ]
    }
}

Response Parameters

Parameter	Type	Description
page_no	Number	Page number of the query.
page_size	Number	Page size of the query.
total	Long	Total number of deployment tasks that match the query criteria.
deployments	Array	List of deployment tasks. The fields for each element match the response parameters for Create a Model Deployment Task. For details, see the response parameters for Create a Model Deployment Task.

Update a Model Deployment Task

Scaling

NoteUpdating a model deployment task is equivalent to scaling the deployment service. You can call this API only when the service status is RUNNING or SCALING. If you call this API when the service is in another state, an OperationDenied error is returned. DTU deployments are scaled through this API by passing dtu_capacity: input and output TPM must be scaled together (the range and combination constraints are the same as for creation). A successful response only indicates that the request is accepted (the status first changes to WAIT_PRE_PAID_BILLING_TO_SCALING). Poll the deployment details until the status is RUNNING and both input and output capacities reach the target values.

PUT https://dashscope.aliyuncs.com/api/v1/deployments/{deployed_model}/scale

Request Example

Scale in COUPLED mode:

curl -X PUT "https://dashscope.aliyuncs.com/api/v1/deployments/qwen3-8b-20260115-abcd/scale" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json' \
    --data '{
    "capacity": 8
}'

Scale in PD-separated mode:

curl -X PUT "https://dashscope.aliyuncs.com/api/v1/deployments/qwen3-8b-20260115-abcd/scale" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json' \
    --data '{
    "prefill_capacity": 4,
    "decode_capacity": 8
}'

Scale a DTU deployment (uses the workspace-scoped domain; plan can be omitted in the request body):

curl -X PUT "https://ws-vxxx.cn-beijing.maas.aliyuncs.com/api/v1/deployments/your-deployment-id/scale" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json' \
    --data '{
    "dtu_capacity": {"input_tpm": 20000, "output_tpm": 20000}
}'

Request Parameters

Parameter	Type	Passing parameters	Required	Description
deployed_model	String	path	Yes	Unique identifier for the deployed model.
capacity	Number	body	Conditionally required	Target number of capacity units for scaling. Required for COUPLED mode (non-PD-separated). Must be a multiple of `base_capacity`.
prefill_capacity	Number	body	Conditionally required	Target prefill capacity. Required for PD-separated mode.
decode_capacity	Number	body	A condition is required.	Target decode capacity. Required for PD-separated mode.
ptu_capacity	Object	body	Conditionally required	PTU v2 capacity info. Includes: `input_tpm_quota` (Number, input TPM quota) `output_tpm_quota` (Number, output TPM quota)
dtu_capacity	Object	body	Conditionally required	DTU target capacity. Required when `plan` is `dtu`. You must provide both `input_tpm` and `output_tpm`. The range and combination constraints are the same as for creation, and input and output must be scaled together. This API only changes capacity. It does not support changing the model, SKU, template, subscription period, auto-renewal, or rate limits at the same time.

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

{
    "request_id": "e5f6a7b8-c9d0-1234-5678-abcdef012345",
    "output": {
        "deployed_model": "qwen3-8b-20260115-abcd",
        "name": "My Model Service",
        "model_name": "qwen3-8b",
        "base_model": "qwen3-8b",
        "status": "SCALING",
        "capacity": 8,
        "ready_capacity": 4,
        "base_capacity": 4,
        "workspace_id": "llm-8v53e*******",
        "charge_type": "post_paid",
        "plan": "mu",
        "model_unit_spec": "MU1",
        "creator": "16542902******",
        "modifier": "16542902******",
        "qpm_limit": 100000000,
        "tpm_limit": 3600000,
        "mu_capacity": {
            "unified": {
                "base_capacity": 4,
                "model_unit_spec": "MU1",
                "ready_capacity": 4,
                "capacity": 8
            }
        },
        "gmt_create": "2026-01-15T10:00:00",
        "gmt_modified": "2026-01-15T11:00:00"
    }
}

Response Parameters

The response parameters are the same as those for creating a model deployment task. For more information, see the response parameters for Create a Model Deployment Task.

Modify DTU Rate Limits

NoteOnly DTU (dtu) deployments support this API. The deployment must be in the idle RUNNING state. The request must provide both qpm_limit and tpm_limit as positive integers in the range 1-2147483647. rpm_limit can be used as an alias for qpm_limit; use only one of them. Rate limit values are not subject to the purchase step and same-multiple rules of the purchased capacity.

PUT https://ws-vxxx.cn-beijing.maas.aliyuncs.com/api/v1/deployments/{deployed_model}/config

Request Example

curl -X PUT "https://ws-vxxx.cn-beijing.maas.aliyuncs.com/api/v1/deployments/your-deployment-id/config" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json' \
    --data '{
    "qpm_limit": 600,
    "tpm_limit": 100000
}'

On success, the current deployment details are returned (the response parameters are the same as those for Create a Model Deployment Task), and the top-level message is DTU rate limit configuration updated.. This API only changes the rate limit thresholds. It does not change the purchased input or output TPM and does not support updating the model or scaling at the same time.

Update DTU Model

NoteOnly DTU (dtu) deployments support this API, and only a fine-tuned model can be updated to another fine-tuned model: the base model name and version of the target model and the current model must be the same. The deployment must be in the idle RUNNING state, and the template must support model updates. Requests for the same model, concurrent changes, or other conditions that are not met return errors.

PUT https://ws-vxxx.cn-beijing.maas.aliyuncs.com/api/v1/deployments/{deployed_model}/update

Request Example

curl -X PUT "https://ws-vxxx.cn-beijing.maas.aliyuncs.com/api/v1/deployments/your-deployment-id/update" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json' \
    --data '{
    "new_model_name": "your-new-finetuned-model"
}'

Request Parameters

Parameter	Type	Passing parameters	Required	Description
deployed_model	String	path	Yes	Unique identifier for the deployed model.
new_model_name	String	body	Yes	Target fine-tuned model name. It must be visible in the current workspace and you must have permission to use it.

WarningThe update is published continuously in the minimum batch strategy allowed by the template, without pausing for first-batch validation. During the update, the serviceable capacity may decrease, the old and new models may serve requests at the same time, and latency increases, rate limiting, or request failures may occur. Minimum-batch publishing does not guarantee zero loss or zero downtime. Confirm that the target model is available before you start, and choose a time window in which these impacts are acceptable.

This API only updates the model. It does not support modifying rate limits, capacity, SKU, template, subscription information, publishing ratio, or pause parameters. A successful response only indicates that the request is accepted (the top-level message is DTU model update request accepted. The model is published continuously without pausing. Poll deployment details to confirm completion.). Poll the deployment details until the status is RUNNING and model_name has changed to the target model. A return to RUNNING alone does not prove the update succeeded — the old model may still be in use if the update failed and rolled back.

Stop a Deployed Model

NoteOnly model unit (mu) deployments support stopping the service. You can call this API only when the service status is RUNNING or SCALING. If you call this API for cu, ptu_v2, lora, or dtu deployments, an UnsupportedOperation error is returned. After the service is stopped, it is no longer billed. You can restart the service using the API Details API. DTU deployments do not support starting or stopping through the API.

POST https://dashscope.aliyuncs.com/api/v1/deployments/{deployed_model}/stop

Request Example

curl -X POST "https://dashscope.aliyuncs.com/api/v1/deployments/qwen3-8b-20260115-abcd/stop" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Request Parameters

Parameter	Type	Passing parameters	Required	Description
deployed_model	String	path	Yes	Unique identifier for the deployed model.

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

{
    "request_id": "f1a2b3c4-d5e6-7890-abcd-ef1234567890",
    "output": {
        "deployed_model": "qwen3-8b-20260115-abcd",
        "name": "My Model Service",
        "model_name": "qwen3-8b",
        "base_model": "qwen3-8b",
        "status": "STOPPING",
        "capacity": 4,
        "ready_capacity": 4,
        "base_capacity": 4,
        "workspace_id": "llm-8v53e*******",
        "charge_type": "post_paid",
        "plan": "mu",
        "model_unit_spec": "MU1",
        "creator": "16542902******",
        "modifier": "16542902******",
        "qpm_limit": 100000000,
        "tpm_limit": 3600000,
        "mu_capacity": {
            "unified": {
                "base_capacity": 4,
                "model_unit_spec": "MU1",
                "ready_capacity": 4,
                "capacity": 4
            }
        },
        "gmt_create": "2026-01-15T10:00:00",
        "gmt_modified": "2026-01-15T12:00:00"
    }
}

Response Parameters

The response parameters are the same as those for creating a model deployment task. For more information, see the response parameters for Create a Model Deployment Task.

Restart a Deployed Model

NoteDTU (dtu) deployments do not currently support starting the service through this API.

POST https://dashscope.aliyuncs.com/api/v1/deployments/{deployed_model}/start

Request Example

curl -X POST "https://dashscope.aliyuncs.com/api/v1/deployments/qwen3-8b-20260115-abcd/start" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Request Parameters

Parameter	Type	Passing parameters	Required	Description
deployed_model	String	path	Yes	Unique identifier for the deployed model. Get it from Create a Model Deployment Task or List Model Deployment Tasks.

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

After the service starts, the status is STARTING and then changes to RUNNING

{
  "request_id": "xxx-xxx-xxx",
  "output": {
    "deployed_model": "qwen-7b-chat-ft-20240101-abcd",
    "model_name": "qwen-7b-chat-ft",
    "base_model": "qwen-7b-chat",
    "status": "STARTING",
    "capacity": 1,
    "ready_capacity": 0,
    "base_capacity": 1,
    "plan": "mu",
    "model_unit_spec": "MU5",
    "workspace_id": "workspace-xxx",
    "charge_type": "post_paid",
    "creator": "user123",
    "modifier": "user123",
    "qpm_limit": 100000000,
    "tpm_limit": 3600000,
    "mu_capacity": {
      "unified": {
        "base_capacity": 1,
        "model_unit_spec": "",
        "ready_capacity": 0,
        "capacity": 1
      }
    },
    "gmt_create": "2024-01-01T10:00:00",
    "gmt_modified": "2024-01-01T13:00:00"
  }
}

Response Parameters

The response parameters are the same as those for creating a model deployment task. For more information, see the response parameters for Create a Model Deployment Task.

Delete a Model Deployment Task

NoteYou can delete a service only when its status is STOPPED or FAILED. For services in the RUNNING state, you must first call the API Details API to stop them. DTU (dtu) deployments do not currently support deletion through this API. Unsubscribe in the console. For more information, see Dedicated Throughput (DTU).

DELETE https://dashscope.aliyuncs.com/api/v1/deployments/{deployed_model}

Request Example

curl -X DELETE "https://dashscope.aliyuncs.com/api/v1/deployments/qwen3-8b-20260115-abcd" \
    --header "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
    --header 'Content-Type: application/json'

Request Parameters

Parameter	Type	Parameter passing	Required	Description
deployed_model	String	path	Yes	Unique identifier for the deployed model.

Response Example and Parameters

Click to view the details.

After you run the command, the following result is returned:

{
    "request_id": "g1h2i3j4-k5l6-7890-mnop-qr1234567890",
    "output": {
        "deployed_model": "qwen3-8b-20260115-abcd",
        "name": "My Model Service",
        "model_name": "qwen3-8b",
        "base_model": "qwen3-8b",
        "status": "DELETING",
        "capacity": 4,
        "ready_capacity": 0,
        "base_capacity": 4,
        "workspace_id": "llm-8v53e*******",
        "charge_type": "post_paid",
        "plan": "mu",
        "model_unit_spec": "MU1",
        "creator": "16542902******",
        "modifier": "16542902******",
        "gmt_create": "2026-01-15T10:00:00",
        "gmt_modified": "2026-01-15T14:00:00"
    }
}

Response Parameters

The response parameters are the same as those for creating a model deployment task. For more information, see the response parameters for Create a Model Deployment Task.

Abnormal Response

{
    "request_id": "6fec0a3f-a1df-4f89-8c8f-33cb0db9f5b0",
    "code": "InvalidParameter",
    "message": "capacity is required when template_type is COUPLED"
}

Response Parameters

Parameter	Type	Description
request_id	String	System-generated ID for this request.
code	String	Error code that identifies the error type.
message	String	Error details for troubleshooting.

Common Errors

Error Reason	Description
`InvalidParameter`	Parameter error. For example, a required parameter is missing, a parameter value is invalid, or template_id and deploy_spec are passed at the same time.
`AccessDenied`	Insufficient permissions or resource does not exist.
`OperationDenied`	The operation is not allowed in the current state. For example, scaling a service that is not in the RUNNING state, or deleting a service that is not in the STOPPED or FAILED state.
`UnsupportedOperation`	The current deployment plan does not support this operation. For example, cu deployments do not support stopping the service.
`StockLimit`	Insufficient resource stock. Cannot complete scaling or deployment.
`InternalError`	Internal error.
`NotFound`	The specified deployment task does not exist.
`Conflict`	Operation conflict. For example, the service is performing another operation.
`QuotaExceeded`	Insufficient quota (common for DTU pre-paid purchases). Check the available quota or contact support.
`InsufficientResource`	Insufficient resources. Deployment or scaling cannot be completed. Adjust the capacity or contact support.
`ServiceUnavailable`	The service is temporarily unavailable. Retry after a backoff.