There are three key considerations when configuring the DashScope API:
- Endpoint Configuration: must be set
OPENAI_BASE_URL=https://dashscope-intl.aliyuncs.com/compatible-mode/v1, which is an AliCloud-specific compatibility endpoint that differs from the standard OpenAI API path. - model identification: need to be clearly designated
OPENAI_MODEL=qwen3-coder-plus, regular identifiers such as gpt-3.5 are not available. Enterprise users can also apply for an exclusiveqwen3-coder-proVersion. - billing strategy: The free quota includes 1 million tokens/month, after exceeding the quota, it will be billed at $0.02/thousand tokens. Long context requests can significantly increase token consumption, it is recommended to pass the
num_ctxParameters are rationally controlled.
Best practice recommendations: 1) Manage API keys in .env file 2) Enable for batch jobsstream=FalseImproved stability 3) Monitoringx-dashscope-ratelimit-remainingResponse headers prevent overages. Commercial programs are advised to purchase resource packs for step discounts.
This answer comes from the articleQwen3-Coder: open source code generation and intelligent programming assistantThe
May not be reproduced without permission:AI productivity tools " What configuration items do I need to pay special attention to when using the DashScope API?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil