MoonshotPaidOperational

Kimi K2 Thinking Turbo

API model name: kimi-k2-thinking-turbo

Kimi K2 Thinking Turbo is Moonshot's chat model, served on the Api.Airforce unified API. Capabilities include Reasoning. It is priced at $1.51 per million input tokens and $10.93 per million output tokens. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.

Get an API key View pricing

Pricing

Input / 1M tokens

$1.51

Output / 1M tokens

$10.93

Cache read / 1M tokens

$0.20

Specifications

Provider: Moonshot
Type: chat model

Capabilities

Reasoning

What is Kimi K2 Thinking Turbo used for?

Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
Complex reasoning — math, coding and step-by-step problem solving.

Kimi K2 Thinking Turbo vs. similar models

Model	Intelligence	Context	Input / 1M	Output / 1M
Kimi K2 Thinking Turbo	—	—	$1.51	$10.93
Kimi K2	23.5	131K	$1.76	$7.32
Kimi K2	23.5	—	$1.04	$4.15
Kimi K2 Preview	—	—	$0.23	$0.92

Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.

Related models

Kimi K2Moonshot · $1.76 / 1M Kimi K2Moonshot · $1.04 / 1M Kimi K2 PreviewMoonshot · $0.23 / 1M Kimi K2 PreviewMoonshot · $101.11 / 1M Kimi K2 InstructMoonshot · $1.14 / 1M Kimi K2 TurboMoonshot · $2.09 / 1M Kimi K2.5Moonshot · $0.86 / 1M Kimi K2.6Moonshot · $0.85 / 1M Kimi K2.6 ThinkingMoonshot · $0.55 / 1M Kimi K2.7Moonshot · $0.85 / 1M Kimi K2.7 CodeMoonshot · Free Kimi K3Moonshot · $2.85 / 1M

Kimi K2 Thinking Turbo — frequently asked questions

How much does Kimi K2 Thinking Turbo cost?: Kimi K2 Thinking Turbo is billed pay-as-you-go at $1.51 per 1M input tokens and $10.93 per 1M output tokens. There is no subscription — you only pay for what you use.
What can Kimi K2 Thinking Turbo do?: Kimi K2 Thinking Turbo supports Reasoning.
Is Kimi K2 Thinking Turbo free to use?: Kimi K2 Thinking Turbo is a paid, pay-as-you-go model — no subscription, you are only charged for usage.
How do I use Kimi K2 Thinking Turbo via the API?: Kimi K2 Thinking Turbo is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID kimi-k2-thinking-turbo with your Api.Airforce API key.
Who makes Kimi K2 Thinking Turbo?: Kimi K2 Thinking Turbo is Moonshot's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.

All models·Quickstart·Chat API reference

Use Kimi K2 Thinking Turbo via the API

OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass kimi-k2-thinking-turbo as the model.

cURL

curl https://api.airforce/v1/chat/completions \
  -H "Authorization: Bearer $AIRFORCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2-thinking-turbo",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Python

from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
    model="kimi-k2-thinking-turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
  model: "kimi-k2-thinking-turbo",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);