Does Qwen Code work with Standard Compute?

Yes. Qwen Code supports a custom OpenAI-compatible base URL, so it works with Standard Compute. Set the base URL to https://api.stdcmpt.com/v1, paste your API key, and set the model to "standardcompute".

What base URL do I use for Qwen Code?

Use https://api.stdcmpt.com/v1 as the OpenAI-compatible base URL in Qwen Code, with your Standard Compute API key and the model "standardcompute".

Do I need to change my code or model names?

No code changes. The model "standardcompute" routes each request to a frontier or an efficient model, so you don't pick or update model names; an exact model ID from the Models page pins one model instead.

← All integrations

OpenAI-compatible · Custom base URL · Terminal coding agent

Use Standard Compute with Qwen Code

The Qwen team's open-source terminal coding agent, originally based on Gemini CLI and now developed on its own, tuned for Qwen models and open to any OpenAI- or Anthropic-compatible provider. Paste three settings into Qwen Code: the base URL, your Standard Compute API key and the model.

Qwen Code's free Qwen OAuth tier ended on April 15, 2026, so it now runs on a key: Alibaba's Coding Plan or Token Plan, a built-in third-party provider, or a Custom Provider such as Standard Compute.

Connect Qwen Code

Eligible new accounts can try $0.25 of compute, with no card. See trial terms →

Your connection settings

Copy these values, then put them where Qwen Code expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in Qwen Code

Open ~/.qwen/settings.json (create it if it doesn't exist).
Under modelProviders.openai, add an entry with id standardcompute, baseUrl set to https://api.stdcmpt.com/v1 and envKey STANDARDCOMPUTE_API_KEY.
Set security.auth.selectedType to openai and model.name to standardcompute, export STANDARDCOMPUTE_API_KEY, then run qwen. Inside the app, /auth → Custom Provider does the same step by step.

Qwen Code docs ↗

What changes in Qwen Code

Billing: Qwen Code requests draw on one monthly compute budget, with plans from $19 a month. There is no per-token bill. When the budget is used, requests stop until renewal or an upgrade, unless you turn on pay as you go.
Models: The model standardcompute picks a frontier or an efficient model for each request. An exact model ID from the Models page pins one model instead.
Good to know: Qwen Code itself is free. Its built-in web_search tool comes ready only with Alibaba's Token Plan or a Model Studio API key. Older guides use security.auth.apiKey and security.auth.baseUrl, which are deprecated, and the qwen auth command was removed. Pin qwen/qwen3.8-max-0902 or another exact ID to keep one model.