OpenAI-Compatible Qwen & Multimodal Model Access - Model Studio

Alibaba Cloud Model Studio is a one-stop model service platform. It integrates the full series of Qwen and mainstream third-party LLMs, provides official Qwen APIs and OpenAI-compatible APIs, and supports multimodal capabilities such as text, image, and audio/video. It enables scenarios including code generation, translation, data mining, and intention recognition. Developers can call models on demand without managing infrastructure.

api Call APIs

Generate content and summaries with a few lines of code.

Model Studio is OpenAI-compatible. Update the API key, base URL, and model name to migrate existing OpenAI code.

import os
from openai import OpenAI

# Note: The base_url varies by region. The following example uses the base_url for the Singapore region.
# - Singapore: https://dashscope-intl.aliyuncs.com/compatible-mode/v1
# - US (Virginia): https://dashscope-us.aliyuncs.com/compatible-mode/v1
# - China (Beijing): https://dashscope.aliyuncs.com/compatible-mode/v1
# - China (Hong Kong): https://cn-hongkong.dashscope.aliyuncs.com/compatible-mode/v1
# - Germany (Frankfurt): https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/compatible-mode/v1. Replace {WorkspaceId} with your workspace ID.
client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"), 
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
)
completion = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[{"role": "user", "content": "Who are you?"}]
)
print(completion.choices[0].message.content)

Model service

Model Studio provides model services. Call Qwen models and third-party models such as DeepSeek, Kimi without deployment or operational management. See Model list.

Qwen flagship models:
- Qwen-Max: Top Qwen3 model for complex, multi-step tasks.
- Qwen-Plus: Balances performance, speed, and cost — recommended for most scenarios.
  Qwen3.5-Plus excels at language understanding, logical reasoning, code generation, agent tasks, and multimodal understanding.
- Qwen-Flash: Cost-effective and low-latency — ideal for simple tasks with fast responses.
- Qwen-Coder: Specialized for code generation and tool calling.
Multimodal coverage: Includes capabilities such as text generation, visual understanding, image generation, video generation, speech recognition and synthesis, and embedding.
Domain-specific models: For specific industries and tasks, provides domain models for long-text processing, translation, data mining, intent recognition, role-playing, and deep research.

Billing

Activating Model Studio is free. You incur costs only when you invoke models. See Billable items and the Model List.

Free quota for new users

New users receive a free quota in the Singapore region to experience model invocation. After depletion, billing switches to pay-as-you-go. To avoid unexpected charges, enable the Free quota only feature, and the service stops when the quota runs out. See Free quota for new users.

Payment methods

Model calls are billed per minute. For supported payment methods, see Payment methods.

View bills and usage

Billing details: Go to the Billing Details and Cost Analysis pages.
Call statistics: About one hour after making a model call, go to the Model Studio console, select your region from the top-right corner of the page, go to the Model Monitoring page, set your query conditions, click Monitor in the Actions column for the target model, and view call volume, token consumption, success rate, and other statistics. See Model monitoring.
Coding Plan usage: If you are subscribed to Coding Plan, view quota consumption on the Coding Plan page. Coding Plan uses a fixed monthly fee with a monthly request quota for AI coding tools. See Coding Plan overview.

Getting started

Try models online:
- Access the Model Studio console, and select your region from the top-right corner of the page.
- Go to the Playground and select a model.
Make your first API request: Make the first call to a Qwen API

FAQ

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

A: Alibaba Cloud protects data privacy and will never use your data for model training. All data you transmit when building applications or training models is encrypted. See Security certifications and privacy.

Q: How many regions is Model Studio available in? What are the differences between the regions?

A: Alibaba Cloud Model Studio provides model services in the following regions:

Singapore, US (Virginia), China (Beijing), China (Hong Kong), Germany (Frankfurt)

Calling a nearby region can reduce network latency. Regions differ in their Endpoints/Base URLs, API keys (not interchangeable), supported models, platform features, and pricing. For more information, see the Model list.

Q: How can I avoid automatic charges?

A: Model Studio uses pay-as-you-go billing with no automatic deduction. To avoid charges:

Delete API Key: Go to the Model Studio console, select your region in the upper-right corner of the page, go to the API-KEY page, and delete all API keys to prevent further charges.
Stop all model calls in applications, agents, and workflows. Check scheduled tasks or background processes.
Turn on Free quota only (new users only): On the model details page, enable this switch. Service stops when quota depletes, preventing paid mode. Applies only to Singapore models within validity period.
Set up cost monitoring and alerts: View Billing Details and Monitoring, and set up high-spending alerts to catch abnormal spending.
Coding Plan: This plan offers a fixed monthly fee and monthly request quota, eliminating pay-as-you-go charges. Use the dedicated base URL and API key for the Coding Plan to make calls. Otherwise, model calls are charged on pay-as-you-go. See Coding Plan overview.

Q: How to use Qwen3 or DeepSeek?

Try it online: Visit the Model Studio console, select your region in the top-right corner of the page, go to the Models page, and click a model (DeepSeek is available only in the Beijing region).
Call models via API: For the calling process, see Make the first call to a Qwen API. For supported models, see Model list.
Use developer tools (such as Claude Code): See Connect to clients or developer tools.