What is Alibaba Cloud Model Studio - Alibaba Cloud Model Studio

Alibaba Cloud Model Studio integrates the Qwen series and other mainstream third-party models. It covers multiple modalities, including text, image, audio, and video, and supports domains such as coding, translation, data mining, and intention recognition. You can choose from official Tongyi API and OpenAI-compatible API, without having to manage the underlying infrastructure.

api Call APIs

Chat with models to perform tasks, such as content creation and summary generation, with just a few lines of code.

Model Studio is compatible with OpenAI API standards. To migrate your existing OpenAI code, simply change the API key, base_url, and model name: Make your first API call to Qwen.

import os
from openai import OpenAI
client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"), 
    # The following base_url is for the Singapore region. To use models in the Beijing region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
)
completion = client.chat.completions.create(
    model="qwen-plus",
    messages=[{"role": "user", "content": "Who are you?"}]
)
print(completion.choices[0].message.content)

Model service

Model Studio provides out-of-the-box model services. You can directly call the Qwen models or third-party models such as DeepSeek and Kimi, without deploying or maintaining them. For more information, see Models.

Qwen flagship models:
- Qwen-Max: The best-performing model in the Qwen series, suitable for handling complex, multi-step tasks.
- Qwen-Plus: A balanced choice for performance, speed, and cost, suitable for general-purpose scenarios.
- Qwen-Flash: Cost-effective and low-latency, suitable for simple job scenarios that require fast responses.
- Qwen-Coder: Excels at tool calling and environment interaction, specialized for code generation and understanding.
Multimodal coverage: Includes various capabilities, such as text generation, visual understanding, image generation, video generation, speech recognition and synthesis, and embedding.
Domain-specific models: Includes various domain-specific models for specific industries and tasks, such as long text processing, translation, data mining, intention recognition, role-playing, and deep research.

Billing

Activating Model Studio is free of charge. You are charged only when you call the models. For more information, see Billable items and Models.

Free quota for new users

Model Studio provides new users with a free quota in the Singapore region to try out the models. After the quota runs out, billing automatically switches to pay-as-you-go. To avoid unexpected charges, turn on the Free quota only feature. The service automatically stops when the quota is depleted. For more information, see Free quota for new users.

How to pay

Calling a model incurs hourly charges. For information about supported payment methods, see Introduction to payment methods.

View bills and usage

Billing details: Visit the Bill Details and Cost Analysis pages.
Call statistics: Approximately one hour after a model call is completed, go to the Model Observation (Singapore or Beijing) page, set the query conditions, and click Monitor in the Actions column. Then, view statistics for that model, such as call count, token consumption, and success rate. For more information, see Usage and performance observation.

Get started with Model Studio

Try models online: Playground (Singapore) or Playground (Beijing)
Make your first API request: Make your first API call to Qwen

FAQ

Q: Is my data secure? Will Model Studio use my data for training?

A: Alibaba Cloud strictly protects data privacy and will never use your data for model training. In addition, the data that you transmit when building applications or training models is encrypted to ensure data security. For more information, see Privacy policy.

Q: What is the difference between the International (Singapore) and Chinese Mainland (Beijing) regions?

A: Model Studio provides model services in the International (Singapore) region and the Chinese Mainland (Beijing) region. Calling a model from a nearby region reduces network latency. Different regions have different model service endpoints (base_url), and their API keys are not interchangeable. The supported models, platform features, and prices also vary between regions, see Models.

Q: How to use Qwen3 or DeepSeek models?

Online experience: Visit the Models (Singapore or Beijing) page and click a model to try it out. Note that DeepSeek is only supported in the Beijing region.
Use APIs: For the calling procedure, see Make your first API call to Qwen. For supported models, see Model list.
Use developer tools (such as Claude Code): See Clients and developer tools.