Kimi K3.1 Pro API pricing and integration guide

Current prices and model reference

Model ID

kimi-k3.1-pro

Documented context

1M

Documented image input

Supported

Live model multiplier

15×

Input price

¥6 / 1M tokens

Output price

¥30 / 1M tokens

Prices are in CNY. A 1× multiplier equals CNY 0.4 per million input tokens. Output and cache charges follow the billing configuration; your usage record is authoritative.

When to consider this model

Evaluate multi-file code changes, complex tool tasks, 3D creation and financial document analysis. Compare result quality, latency and total cost on tasks with clear acceptance criteria.

How to evaluate it

Use kimi-k3.1-pro. Validate a short text request before images and multi-turn tool tasks. Thinking is always enabled; preserve complete assistant messages, including reasoning and tool calls, across turns.

What to check before integration

The new Feishu reference and live catalog both list 15x, equivalent to CNY 6 per million input tokens. Output and cache rates are billed separately using live pricing. K3 and K3.1 Pro are separate IDs; this entry neither establishes a Highspeed route nor reports a completed API test.

Client configuration

In a client supporting a custom API endpoint, enter this base URL and model ID with your own API key. Select the protocol described in the client tutorial and validate a short request first.

Base URL: https://api.llm-token.cn/v1
Model ID: kimi-k3.1-pro