DeepSeek, GLM, Kimi and Doubao behind a single OpenAI-compatible endpoint. Frontier quality at a fraction of Western API prices — no Chinese phone number, no real-name verification, no CNY wallet. Just a card and an API key.
curl https://adzukiai.com/v1/chat/completions \ -H "Authorization: Bearer $CHINESE_MODEL_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Explain B-tree splits"}] }'
Each Chinese provider wants its own account, its own console and a domestic payment method. We collapse them into one key and one invoice.
Switch between DeepSeek, GLM, Kimi and Doubao by changing a single string in your request. No new account, no new SDK, no new invoice per provider.
Top up with Visa, Mastercard or Amex. No Chinese bank account, no CNY wallet, no third-party reseller of unknown provenance.
Any OpenAI SDK works. Point base_url at us, keep your code, and pick a model from the catalogue.
Per-million-token pricing with no monthly minimum. Prompt caching is billed separately and is dramatically cheaper than fresh input.
If a provider changes terms or deprecates a model, you switch models, not vendors. Your integration stays where it is.
Jurisdiction restrictions and data-routing facts are stated on this page, not buried in a subprocessor list. See the compliance section below.
USD per 1 million tokens, billed against your prepaid balance. Sorted by input price.
| Model | Input | Output | Cached input | Profile |
|---|---|---|---|---|
doubao-seed-2.0-lite | 0.17 | 1.03 | 0.0343 | budgetfast |
glm-5.3-flash | 0.23 | 0.80 | 0.0657 | budgetfast |
deepseek-v4.1-flash Not for U.S. federal use | 0.57 | 2.29 | 0.0114 | balancedcheap cache |
doubao-seed-2.1-pro | 1.71 | 8.57 | 0.34 | flagship |
glm-5.3 | 2.29 | 8.00 | 0.57 | flagship |
deepseek-v4-pro Not for U.S. federal use | 2.57 | 7.71 | 0.0857 | flagship |
kimi-k3 | 5.71 | 28.57 | 0.57 | premiumlong context |
Two facts you need before you build on this: who may not use which model, and where the data goes.
Under the FY2026 National Defense Authorization Act (§1532 and §6604) and the U.S. Department of Homeland Security directive issued in October 2026, U.S. federal civilian agencies, the Department of Defense, the Intelligence Community and their contractors may not procure or use DeepSeek technology — including through third-party services such as this one, and regardless of whether the model is self-hosted. Several states, including New York, Virginia, Tennessee and Texas, have imposed comparable restrictions on government devices and networks.
If you are a U.S. federal agency, a federal contractor, or a state or local government entity, do not use the DeepSeek models offered here. Other models in the catalogue are not covered by this restriction. This notice is provided for compliance convenience and is not legal advice; you remain responsible for your own regulatory position.
Every model in this catalogue is operated by a provider whose inference infrastructure is located in mainland China. When you call a model, the content of your request is transmitted to that provider and processed there, and the response is returned to you. Account and billing data are stored in the United States and the European Union.
We do not use your prompts or outputs to train models. If your workload cannot leave a particular jurisdiction, contact support@jinxiaodouai.cn before sending production traffic.
Three steps, no sales call.
Email and password. No phone number, no government ID.
Pay by card in USD. Minimum top-up is shown in the dashboard at checkout.
base_url = "https://adzukiai.com/v1"