Since Qwen Code's free Qwen OAuth tier ended on April 15, 2026, every session needs a provider key. To run it cost-efficiently across Qwen and other models, add Standard Compute as an OpenAI-compatible provider in ~/.qwen/settings.json (baseUrl https://api.stdcmpt.com/v1): its router sends each step to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), on a plan from $19 a month with a $19 compute budget. Alibaba's Coding Plan ($50 a month for Pro) is the native fixed-price option for Qwen, GLM, Kimi and MiniMax models with 5-hour, weekly and monthly request caps, and OpenRouter suits light, bursty use.
| Option | Price | What you get |
|---|---|---|
| Alibaba Cloud Coding Plan | $50/mo Pro (¥200 in China) | The fixed monthly plan built into Qwen Code's /auth menu: qwen3.7-plus, qwen3.6-plus, Kimi K2.5, GLM-5 and MiniMax-M2.5 on a dedicated endpoint with sk-sp- keys. Pro is the only tier open (Lite closed in March 2026), capped at 6,000 requests per 5 hours, 45,000 a week and 90,000 a month, for coding tools only. Checked 2026-10-15. Source: alibabacloud.com |
| Standard Compute (us) | From $19/mo | Smart routing sends each request to the cheapest model that can do it, or pin any model by its exact ID. Standard Compute starts at $19/month with a $19 monthly compute budget. Requests stop when that budget is exhausted until renewal or a plan change; there are no automatic overage charges. Requests are not slowed as the budget is used. It is a fixed bill with a finite allowance. |
| OpenRouter | Pay-as-you-go | Choose models and providers through one API. Usage-based pricing can suit light or bursty work; estimate long agent sessions and review current fees and limits. Source: openrouter.ai |
| Local model (Ollama / vLLM) | Hardware + electricity | No hosted per-token bill, but hardware, context capacity, throughput and maintenance still limit what you can run. Test task quality on your own hardware. Source: docs.ollama.com |
Prices and allowances can change. The end of the free Qwen OAuth tier and the settings format come from Qwen Code's authentication and model-provider docs, read on October 14, 2026 and re-checked on October 15 (Qwen Code v0.25.2). Coding Plan price and limits are from Alibaba Cloud's Coding Plan page, read on October 15, 2026. Qwen Code: authentication · Alibaba Cloud: Coding Plan · Qwen Code: model providers. Spot an error? Tell us.
Then export STANDARDCOMPUTE_API_KEY with your key and run qwen. Add entries with exact IDs such as qwen/qwen3.8-max-0902 to switch between them with /model.
Record your own results with the workload CSV and report template. These are blank templates, not published benchmark results.
Disclosure: this guide is maintained by Standard Compute, one of the options above. Choose based on task quality, supported features and total cost for your workload. Light usage may cost less on a usage-based API; sustained workloads need enough allowance on any subscription.