Pricing

Models & pricing

Seven models from four Chinese vendors, all served through one OpenAI-compatible endpoint. Frontier quality at China's prices, billed per token against a prepaid balance with no monthly minimum.

ModelInputOutput Cached inputProfile
ByteDance Doubao
doubao-seed-2.0-lite
ByteDance Doubao
0.171.030.0343budgetfast
Zhipu AI
glm-5.3-flash
Zhipu AI
0.230.800.0657budgetfast
DeepSeek
deepseek-v4.1-flash Not for U.S. federal use
DeepSeek
0.572.290.0114balancedcheap cache
ByteDance Doubao
doubao-seed-2.1-pro
ByteDance Doubao
1.718.570.34flagship
Zhipu AI
glm-5.3
Zhipu AI
2.298.000.57flagship
DeepSeek
deepseek-v4-pro Not for U.S. federal use
DeepSeek
2.577.710.0857flagship
Moonshot AI
kimi-k3
Moonshot AI
5.7128.570.57premiumlong context
USD per 1 million tokens. Cached input applies when a prompt prefix is served from the provider's cache; it is billed separately and is far cheaper than fresh input. Prices exclude tax where applicable.

Compliance notes

!DeepSeek models are restricted for U.S. federal use

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.

iWhere your data is processed

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@adzukiai.com before sending production traffic.

How billing works

01

Prepaid balance

You add credit up front. Each request deducts the cost of its input tokens, cached tokens and output tokens. When the balance reaches zero, requests stop.

02

Output costs more

Output tokens are priced several times higher than input, as with every provider. Cost is dominated by how much you generate, not how much you send.

03

Failed calls

A request that fails through our error is not charged. Credits are restored automatically; there is no ticket to open.