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. 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.

Guide updated 2026-10-15. Check each provider's current terms below.
Get your API key$0.25 trial for eligible new accounts, no card. Plans from $19/mo.
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 5-hour, weekly and monthly request caps fit your week.
Daily use, cost-optimized
Standard Compute fits when you want each step on the cheapest model that can do it, with Qwen next to Claude, GPT or GLM on one key: use standardcompute to let routing pick per request, or pin qwen/qwen3.8-max-0902. For every model we vet providers for price, uptime and speed, with automatic fallback. Opt-in Europe or US Compliance rules apply per key, team or company, and we don't train on your prompts or store them. It is one monthly bill, and requests stop at the budget instead of billing overage.

API and subscription options for Qwen Code

OptionPriceWhat 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/moSmart 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.
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 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.

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 $19 compute budget.
Is Alibaba's Coding Plan or Standard Compute cheaper for Qwen Code?
For Qwen, GLM, Kimi and MiniMax only, the Coding Plan: Pro is $50 a month (¥200 in China) for up to 6,000 requests per 5 hours, 45,000 a week and 90,000 a month, and the Lite tier is closed. Standard Compute fits when you also want Claude or GPT for the hard steps: the router sends each step to the cheapest capable model, providers are vetted for price, uptime and speed with automatic fallback, and plans start at $19 a month with no request windows, only a monthly 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 →