List models - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center

Call the GET /api/v1/models endpoint to retrieve the list of available models on Model Studio. You can filter by model provider, modality type, model capability, and deployment mode, and get information such as pricing and context length.

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://dashscope-intl.aliyuncs.com/api/v1/models`
China (Beijing)	`https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/models`
China (Hong Kong)	`https://cn-hongkong.dashscope.aliyuncs.com/api/v1/models`
Germany (Frankfurt)	`https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1/models`
Japan (Tokyo)	`https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/api/v1/models`
US (Virginia)	`https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/models`

Authentication

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

Request parameters

All parameters are passed via query string.

name · String · Optional

Fuzzy search by model name. Example: qwen

model · String · Optional

Exact match by model ID. Example: qwen3-max

language · String · Optional

Language of the response. Valid values: zh-CN (Chinese), en-US (English).

page_no · Integer · Optional

Page number, starting from 1. Default value: 1.

page_size · Integer · Optional

Number of models per page. Default value: 20.

providers · Array[String] · Optional

Filter by model provider. Valid values:

providers values

qwen: Qwen
deepseek: DeepSeek
zhipu-ai: Zhipu AI
wan: Wan
moonshot-ai: Moonshot AI
mini-max: MiniMax
kling: Kling AI
vidu: Vidu
pixverse: PixVerse
xiaomi: Xiaomi
tripo: Tripo
happyhorse: HappyHorse
qwen-domain-model: Qwen Domain Model

Example: providers=qwen&providers=deepseek

inference_providers · Array[String] · Optional

Filter by inference provider. Valid values:

inference_providers values

aliyun-bailian: Alibaba Cloud Model Studio
alibaba-cloud-modelstudio: Alibaba Cloud Model Studio
siliconflow: SiliconFlow
moonshot: Kimi
mini-max: MiniMax
kling: Kling AI
vidu: Vidu
pixverse: PixVerse
vanchin: Kuaishou Wanqing
xiaomi: Xiaomi MiMo
zhipu-ai: Zhipu AI
tripo: Tripo

capabilities · Array[String] · Optional

Filter by modality type. Valid values:

capabilities values

TG: Text Generation
Reasoning: Advanced Reasoning
VU: Visual Understanding
IG: Image Generation
VG: Video Generation
ASR: Speech Recognition
TTS: Text-to-Speech
TR: Text Embedding
ME: Multimodal Embedding
Multimodal-Omni: Omni
Realtime-Omni: Realtime Omni
Realtime-Text-to-Speech: Realtime Text-to-Speech
Realtime-ASR: Realtime Speech Recognition
Realtime-Audio-Translate: Realtime Audio Translation
3D-generation: 3D Generation
Realtime-Chatting: Realtime Voice Chat

Example: capabilities=TG&capabilities=Reasoning

To specify multiple values, repeat the parameter name, for example, capabilities=TG&capabilities=Reasoning. This matches models that support either text generation or reasoning.

features · Array[String] · Optional

Filter by model capability. Valid values:

features values

function-calling: Function Calling
structured-outputs: Structured Outputs
web-search: Web Search
prefix-completion: Prefix Completion
cache: Context Caching
batch: Batch Inference
fine-tuning: Fine-tuning
model-experience: Model Playground

context_window · Integer · Optional

Filter by context length. Returns models with a context length strictly less than the specified value. Example: 20000.

service_site · String · Optional

Filter by deployment mode. If not specified, models of all deployment modes are returned. Valid values:

service_site values

global: Global
international: International (excluding Chinese mainland)
asia-pacific-china: Chinese mainland
cn-hongkong: China (Hong Kong)
european-union: European Union
united-states: United States
japan: Japan

supports · Array[String] · Optional

Filter by supported use case. Default value: inference. Valid values:

supports values

inference: Models that support inference
deploy: Models that support deployment

deployment_methods · Array[String] · Optional

Filter by deployment method. Valid values:

deployment_methods values

ptu: Provisioned Throughput Unit

deployment_ptu_service_tiers · Array[String] · Optional

Filter by PTU type. You must also set deployment_methods to include ptu.

Sample requests

List all models

Query without filters. The example retrieves the first page. To retrieve all models, increment page_no until all models counted by output.total have been retrieved.

curl

curl --get "https://dashscope-intl.aliyuncs.com/api/v1/models" \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header "Content-Type: application/json" \
    --data-urlencode "page_no=1" \
    --data-urlencode "page_size=20"

Python

import os
import dashscope
from dashscope import Models

dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"

resp = Models.list(
    page=1,
    page_size=20,
    api_key=os.getenv('DASHSCOPE_API_KEY'),
)
print(resp.output)

NoteThe Models.list() method in the DashScope Python SDK only supports the page and page_size pagination parameters for querying models. It does not support filters such as capabilities, providers, or features. Use the HTTP API to filter models. The Python example retrieves the first page; increment page to retrieve subsequent pages.

Query a model by ID

Set model=qwen3-max to query the exact model ID.

curl --get "https://dashscope-intl.aliyuncs.com/api/v1/models" \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header "Content-Type: application/json" \
    --data-urlencode "model=qwen3-max" \
    --data-urlencode "page_no=1" \
    --data-urlencode "page_size=20"

List all text generation models

Set capabilities=TG to query text generation models. The example retrieves the first page; increment page_no to retrieve subsequent pages.

curl --get "https://dashscope-intl.aliyuncs.com/api/v1/models" \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header "Content-Type: application/json" \
    --data-urlencode "capabilities=TG" \
    --data-urlencode "page_no=1" \
    --data-urlencode "page_size=20"

List Qwen reasoning models

Set providers=qwen and capabilities=Reasoning to query Qwen reasoning models. The example retrieves the first page; increment page_no to retrieve subsequent pages.

curl --get "https://dashscope-intl.aliyuncs.com/api/v1/models" \
    --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
    --header "Content-Type: application/json" \
    --data-urlencode "providers=qwen" \
    --data-urlencode "capabilities=Reasoning" \
    --data-urlencode "page_no=1" \
    --data-urlencode "page_size=100"

Response parameters

request_id · String

Request ID for troubleshooting.

output.total · Number

Total number of matching models.

output.page_no · Number

Current page number.

output.page_size · Number

Number of items per page.

output.models[]

model · String

Model ID, used to specify the model in API calls.

name · String

Display name of the model.

description · String

Description of the model.

provider · String

Model provider, such as qwen.

inference_provider · String

Inference provider, such as aliyun-bailian.

capabilities · Array[String]

Modality types supported by the model. Values are the same as the capabilities request parameter.

features · Array[String]

Capabilities supported by the model. Values are the same as the features request parameter.

published_time · String

Model release time in yyyy-MM-dd HH:mm:ss format. Can be null.

inference_metadata · Object

Input and output modality information of the model. Contains the following fields:

request_modality (Array[String]): Input modalities. Valid values: Text, Image, Audio, Video.
response_modality (Array[String]): Output modalities. Same valid values as above.

model_info · Object

Context length information of the model. A value of null indicates no limit or not applicable. Contains the following fields:

context_window (Integer): Total context window length
max_input_tokens (Integer): Maximum input tokens
max_output_tokens (Integer): Maximum output tokens
max_reasoning_tokens (Integer): Maximum reasoning tokens
reasoning_max_input_tokens (Integer): Maximum input tokens for reasoning
reasoning_max_output_tokens (Integer): Maximum output tokens for reasoning

prices · Array[Object]

Pricing information. Each element contains:

range_name (String): Tier name. Default if no tiered pricing, or a specific range (such as 32k<Input<=128k).
prices (Array[Object]): Price list. Each item contains type (billing item), price (unit price), price_unit (unit, such as "per million tokens"), and price_name (price description, such as "Input").

equivalent_snapshot · String

The corresponding snapshot model.

inference_offline_info · Object

Inference offline information.

inference_offline_info.$.offline_time · Date

Estimated offline time.

Sample response

The following example illustrates the response structure. Model information and prices are subject to the actual response.

{
    "code": null,
    "message": null,
    "success": true,
    "output": {
        "total": 168,
        "page_no": 1,
        "page_size": 10,
        "models": [
            {
                "model": "qwen3-max",
                "name": "Qwen3-Max",
                "description": "The Max model in the Qwen3 series, designed for complex agent scenarios.",
                "features": [
                    "function-calling",
                    "structured-outputs",
                    "web-search"
                ],
                "prices": [
                    {
                        "prices": [
                            {
                                "type": "input_token",
                                "price": "2",
                                "price_unit": "per million tokens",
                                "price_name": "Input"
                            },
                            {
                                "type": "output_token",
                                "price": "8",
                                "price_unit": "per million tokens",
                                "price_name": "Output"
                            }
                        ],
                        "range_name": "Default"
                    }
                ],
                "published_time": "2025-11-11 12:00:00",
                "inference_metadata": {
                    "response_modality": ["Text"],
                    "request_modality": ["Text"]
                },
                "model_info": {
                    "context_window": 131072,
                    "max_input_tokens": 130048,
                    "max_output_tokens": 16384,
                    "max_reasoning_tokens": null,
                    "reasoning_max_input_tokens": null,
                    "reasoning_max_output_tokens": null
                }
            },
            {
                "model": "qwen-image-max",
                "name": "Qwen-Image-Max",
                "description": "The Max model in the Qwen image generation series.",
                "features": ["model-experience"],
                "prices": [
                    {
                        "prices": [
                            {
                                "type": "image_number",
                                "price": "0.075",
                                "price_unit": "per image",
                                "price_name": "Image Generation"
                            }
                        ],
                        "range_name": "Default"
                    }
                ],
                "published_time": null,
                "inference_metadata": {
                    "response_modality": ["Image"],
                    "request_modality": ["Text"]
                },
                "model_info": {
                    "context_window": null,
                    "max_input_tokens": null,
                    "max_output_tokens": null,
                    "max_reasoning_tokens": null,
                    "reasoning_max_input_tokens": null,
                    "reasoning_max_output_tokens": null
                }
            }
        ]
    },
    "request_id": "d5f5201f-ee7a-9e3d-8569-bc0eedec21f9"
}

Error codes

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

List model quotas
Model list