Which API should you use with Qwen Code?

Since Qwen Code's free Qwen OAuth tier ended on April 15, 2026, every session needs a provider key. For one monthly price across Qwen and other models, add Standard Compute as an OpenAI-compatible provider in ~/.qwen/settings.json (baseUrl https://api.stdcmpt.com/v1), from $19 a month with a $20 compute budget. Alibaba's Coding Plan is the native fixed-price option for Qwen, GLM, Kimi and MiniMax models with a weekly quota, and OpenRouter suits light, bursty use.

Guide updated 2026-10-14. Check each provider's current terms below.
Light or occasional use
For occasional use, a pay-as-you-go key on an efficient Qwen model will likely cost the least. Alibaba's Coding Plan is worth a look if you only use the models it includes and its weekly quota fits your week.
One fixed monthly bill
Standard Compute fits when you want Qwen models next to Claude, GPT or GLM on one key and one bill. Pin qwen/qwen3.8-max-0902, or use standardcompute to let routing pick per request; requests stop at the monthly budget instead of billing overage.

API and subscription options for Qwen Code

OptionPriceWhat you get
Alibaba Cloud Coding PlanSee current plansThe fixed monthly plan built into Qwen Code's /auth menu: Qwen, GLM, Kimi and MiniMax models with a weekly quota, on a dedicated endpoint with sk-sp- keys. Check the included models and quota for your region. Source: github.com
Standard Compute (us)From $19/moStandard Compute starts at $19/month with a $20 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. Pin any model by its exact ID, or let smart routing pick per request. It is a fixed bill with a finite allowance.
OpenRouterPay-as-you-goChoose 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 + electricityNo 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, the Coding Plan details and the settings format come from Qwen Code's authentication docs, read on October 14, 2026. Qwen Code: authentication · Qwen Code: model providers. Spot an error? Tell us.

Add Standard Compute to Qwen Code

~/.qwen/settings.json
{
  "modelProviders": {
    "openai": [
      {
        "id": "standardcompute",
        "name": "Standard Compute",
        "baseUrl": "https://api.stdcmpt.com/v1",
        "envKey": "STANDARDCOMPUTE_API_KEY"
      }
    ]
  },
  "security": { "auth": { "selectedType": "openai" } },
  "model": { "name": "standardcompute" }
}

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.

Qwen Code questions

Is Qwen Code still free?
The tool is: Qwen Code is open source and costs nothing to install. The free Qwen OAuth model tier ended on April 15, 2026, and new requests through it are rejected, so you now bring a provider. The /auth menu offers Alibaba's Coding Plan, Token Plan or a Model Studio key, built-in third-party providers, or a Custom Provider. Standard Compute is a Custom Provider at https://api.stdcmpt.com/v1, from $19 a month with a $20 compute budget.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Qwen Code version.
  2. Run a small task on a clean branch and review the result, elapsed time and compute used.
  3. Estimate your actual monthly workload before selecting a larger allowance.
Get your API keyQwen Code setup guide →Compare compute budgets →

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.

All flat-rate plans compared →The cheapest-tokens math →Plan compute for your team →