List model quotas - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center

Call the GET /api/v1/quotas endpoint to query the rate limit quotas for each model under the current API key, including request rate limits (QPS/RPM) and usage limits (TPM), to understand and plan your API usage.

Prerequisites

An API key has been created and configured as the environment variable DASHSCOPE_API_KEY. For more information, see Configure an API key in environment variables.

Request

HTTP method: GET

Request URL

Replace {WorkspaceId} with your workspace ID.

Region	Endpoint
Singapore	`https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/quotas`
China (Beijing)	`https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/quotas`
China (Hong Kong)	`https://{WorkspaceId}.cn-hongkong.maas.aliyuncs.com/api/v1/quotas`
Germany (Frankfurt)	`https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1/quotas`
US (Virginia)	`https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/quotas`

Authentication

Set Authorization: Bearer {API_KEY} in the request header.

Request parameters

All parameters are passed through the query string.

Parameter	Type	Required	Description
name	String	No	Fuzzy search by model name. Example: `qwen`
model	String	No	Exact match by model ID. Example: `qwen3-max`
page_no	Integer	No	Page number, starting from 1. Default: `1`.
page_size	Integer	No	Number of models returned per page. Default: `20`.

Response parameters

Parameter	Type	Description
request_id	String	The request ID, used for troubleshooting.
output.total	Number	The total number of models that match the query criteria.
output.page_no	Number	The current page number.
output.page_size	Number	The number of entries per page.
output.quotas[].model	String	The model ID.
output.quotas[].workspace_id	String	The workspace ID.
output.quotas[].model_limit	Object	Account-level rate limits. This represents the overall rate limit cap for the model under the current account. Contains the following fields: `request_limit` (Number): The request rate limit value. `request_limit_period` (Number): The time period for the request rate limit, in seconds. A value of `60` indicates per minute (RPM), and a value of `1` indicates per second (QPS). `usage_limit` (Number): The usage limit value. A value of `null` indicates no usage limit. `usage_limit_field` (String): The usage limit type, such as `total_tokens`. `usage_limit_period` (Number): The time period for the usage limit, in seconds. `async_user_queue_limit` (Number): The maximum number of queued asynchronous tasks. `async_user_concurrency_limit` (Number): The maximum number of concurrent asynchronous tasks.
output.quotas[].workspace_limit	Object	Workspace-level rate limits. You can set individual rate limits for each workspace, but the combined limits across all workspaces cannot exceed the `model_limit`. A value of `null` indicates that no workspace-level limit has been set. Contains the same fields as `model_limit`.

Rate limit details

Model Studio applies rate limits at two levels:

model_limit (account level): The overall rate limit cap for the model under the current account, shared across all workspaces.
workspace_limit (workspace level): You can configure individual rate limits for each workspace. The combined limits across all workspaces cannot exceed the model_limit cap.

Rate limit types

Field	Meaning	Example
request_limit + request_limit_period	Request rate limit	`request_limit=60, request_limit_period=60` means a maximum of 60 requests per minute (RPM). `request_limit=5, request_limit_period=1` means a maximum of 5 requests per second (QPS).
usage_limit + usage_limit_period	Usage limit	`usage_limit=100000, usage_limit_field=total_tokens, usage_limit_period=60` means a maximum of 100,000 tokens per minute (TPM). A value of `null` indicates no usage limit.
async_user_queue_limit	Async queue limit	The maximum number of tasks that can be queued when using asynchronous calls.
async_user_concurrency_limit	Async concurrency limit	The maximum number of tasks that can be executed simultaneously when using asynchronous calls.

Sample requests

Example 1: Query quotas for all models

curl "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/quotas?page_no=1&page_size=100" \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header "Content-Type: application/json"

Example 2: Query quotas for a specific model

curl "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/quotas?model=qwen3-max" \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header "Content-Type: application/json"

Sample response

{
    "code": null,
    "message": null,
    "success": true,
    "output": {
        "total": 453,
        "page_no": 1,
        "page_size": 10,
        "quotas": [
            {
                "model": "qwen3-max",
                "workspace_id": "ws-o72y059armtglf1u",
                "model_limit": {
                    "request_limit": 500,
                    "request_limit_period": 1,
                    "usage_limit": 500000,
                    "usage_limit_field": "total_tokens",
                    "usage_limit_period": 6,
                    "async_user_queue_limit": null,
                    "async_user_concurrency_limit": null
                },
                "workspace_limit": null
            },
            {
                "model": "wan2.6-i2v-flash",
                "workspace_id": "ws-o72y059armtglf1u",
                "model_limit": {
                    "request_limit": 5,
                    "request_limit_period": 1,
                    "usage_limit": null,
                    "usage_limit_field": null,
                    "usage_limit_period": null,
                    "async_user_queue_limit": 500,
                    "async_user_concurrency_limit": 5
                },
                "workspace_limit": null
            },
            {
                "model": "qwen-image-max",
                "workspace_id": "ws-o72y059armtglf1u",
                "model_limit": {
                    "request_limit": 2,
                    "request_limit_period": 60,
                    "usage_limit": 1000000,
                    "usage_limit_field": "total_tokens",
                    "usage_limit_period": 60,
                    "async_user_queue_limit": null,
                    "async_user_concurrency_limit": null
                },
                "workspace_limit": null
            }
        ]
    },
    "request_id": "2043b55f-f0d2-95ee-a449-234e1ee57042"
}

In the preceding example:

qwen3-max: A maximum of 500 requests per second, and a maximum of 500,000 tokens per 6 seconds. No workspace-level limit is set.
wan2.6-i2v-flash: A maximum of 5 requests per second with no usage limit. The async task queue limit is 500 and the async concurrency limit is 5.
qwen-image-max: A maximum of 2 requests per minute and a maximum of 1,000,000 tokens per minute. No workspace-level limit is set.

Error codes

If the call fails, an error message is returned. For more information about error codes and solutions, see Error messages.

List models
Rate limiting