Qwen API tutorial

How to authenticate, which endpoint to call, and the mistakes that cost people an afternoon.

The Qwen API is OpenAI-compatible: the official documentation shows requests built with the standard OpenAI SDKs. In practice that means three values decide whether your first call works — the API key, the base URL and the model ID.

1. Create an account and an API key

• Sign in to the developer platform: www.aliyun.com/product/bailian.
• Create an API key in the console and store it in an environment variable rather than in source code.
• Full details: API documentation

2. Point your client at the right endpoint

https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1 (legacy: https://dashscope.aliyuncs.com)
Overseas endpoints documented: Singapore https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 (legacy dashscope-intl.aliyuncs.com), US https://dashscope-us.aliyuncs.com/compatible-mode/v1, Tokyo https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1

If you are migrating existing code, keep your current SDK and change only base_url and the model name. If you see 401 responses, the key is usually wrong; if you see 404 on the model, the model ID is wrong or deprecated.

3. A minimal working request

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DASHSCOPE_API_KEY"],
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",  # legacy domain; workspace domains are also documented
)

resp = client.chat.completions.create(
    model="qwen-plus",
    messages=[{"role": "user", "content": "Explain vector databases in three sentences."}],
)
print(resp.choices[0].message.content)

4. Watch out for these

• The base URL is migrating to workspace-specific domains; older documentation still shows dashscope.aliyuncs.com style URLs.
• Prices differ by region and by input-length tier, so the numbers above are examples, not a quote.
• Saving-plan and Token Plan prices are not published.
• Old model IDs get retired: check the model list before hard-coding a name in production.
• Context limits are documented per model — sending more input than the window allows is the most common cause of rejection in long-document workloads.

5. Controlling cost

• Cache-hit input tokens are cheaper than cache-miss input tokens, so keep prompts stable where possible.
• Batch or off-peak options are documented for some models and are billed below the standard rate.
• Current rates: official pricing page.

6. Next steps

• Qwen overview: what the product is, which models exist and what each is documented to do.
• Published Qwen pricing: free allowances, token rates and subscription tiers, with sources.
• Qwen vs Western AI models: how the interfaces, context limits and availability compare.
• Qwen in the AI-Mind directory: ratings, categories and alternatives.

Facts on this page were checked against the official pages linked above on 2026-09-19. Prices and model IDs change frequently: confirm them on the vendor’s own pricing page before you rely on them.