Kimi-K3.1-Pro API pricing: $1.86 in / $9.71 out per 1M

Kimi-K3.1-Pro at a glance

Every figure below is the price applied at request time.

Model ID	kimi-k3.1-pro
Vendor	Moonshot AI
Input	$1.86 per 1M tokens
Cached input	$0.19 per 1M tokens
Output	$9.71 per 1M tokens
Output vs input	5.23× — output is the expensive side of every request
Wire format	OpenAI Chat Completions — POST /chat/completions
Base URL	https://adzukiai.com/v1
Billing	Per token, prepaid USD balance. No subscription, no monthly minimum.
Restrictions	Not for U.S. federal use. See the compliance note below.

What a request actually costs

A worked example: a 10,000-token prompt where 8,000 tokens hit the cache, which produces 2,000 output tokens.

Component	Tokens	Rate per 1M	Cost
Fresh input	2,000	$1.8571	$0.0037142
Cached input	8,000	$0.1857	$0.0014856
Output	2,000	$9.7143	$0.0194286
Total	12,000	—	$0.0246284

Rates shown to six decimals so the arithmetic adds up; the catalogue page rounds them for display. Cached tokens are only billed at the cache rate when the provider serves a prompt prefix from its cache.

The same request without cache hits would cost $0.0379996 — caching is what makes long, repeated system prompts affordable.

How Kimi-K3.1-Pro compares

All seven models in the catalogue, sorted by input price, shown as a multiple of Kimi-K3.1-Pro. USD per million tokens.

Model	Vendor	Input	Output	Input vs Kimi-K3.1-Pro
doubao-seed-2.0-lite	ByteDance Doubao	0.0519	0.31	0.03×
glm-5.3-flash	Zhipu AI	0.0553	0.19	0.03×
doubao-seed-2.1-lite	ByteDance Doubao	0.0691	0.23	0.04×
mimo-v2.5	Xiaomi MiMo	0.0927	0.19	0.05×
deepseek-v4.1-flash	DeepSeek	0.14	0.55	0.07×
mimo-v2.5-pro	Xiaomi MiMo	0.28	0.56	0.15×
minimax-m3	MiniMax	0.36	1.43	0.19×
doubao-seed-2.1-pro	ByteDance Doubao	0.52	2.59	0.28×
glm-5.3	Zhipu AI	0.55	1.94	0.30×
deepseek-v4-pro	DeepSeek	0.91	2.72	0.49×
qwen3.8-max	Alibaba Qwen	1.51	4.53	0.81×
kimi-k3.1-pro	Moonshot AI	1.86	9.71	1.00×
kimi-k3	Moonshot AI	2.20	11.00	1.18×

Full profiles, tags and the machine-readable catalogue are on the pricing page.

Use it in three steps

No sales call required, no approval queue. You can start on your own.

Create an account

Email and password. No phone number, no government ID.

Add credit

Pay by card in USD. The balance is drawn down per token as you use it.

Send the model string

kimi-k3.1-pro in any OpenAI SDK.

curl

curl https://adzukiai.com/v1/chat/completions \
  -H "Authorization: Bearer $ADZUKI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3.1-pro",
    "messages": [{"role": "user", "content": "Explain B-tree splits"}]
  }'

Compliance

Two facts to check before you send production traffic.

!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.

Kimi-K3.1-Pro questions

Cost, caching and jurisdiction — the three things people ask first.

How much does Kimi-K3.1-Pro cost?

Kimi-K3.1-Pro costs $1.86 per million input tokens and $9.71 per million output tokens, with cached input at $0.19 per million. Billing is per token against a prepaid USD balance; there is no subscription and no monthly minimum.

Does prompt caching reduce the cost of Kimi-K3.1-Pro?

Yes. Cached input is $0.19 per million tokens against $1.86 for fresh input, roughly 10× cheaper. Caching only applies when the provider serves a prompt prefix from its cache; the first request that populates the cache still pays the full input rate.