moonshotai

kimi-k2-thinking-turbo

K2 Long-term thinking model high-speed version, supports 256k context, excels at deep reasoning, output speed increased to 60-100 tokens per second.

moonshotai

kimi-k2-thinking-turbo

K2 Long-term thinking model high-speed version, supports 256k context, excels at deep reasoning, output speed increased to 60-100 tokens per second.

Learn more

Provider:

moonshotai

Model type:

chat

Location:

singapore

Context Window

262144

Intelligence Rating

Speed Rating

Cost Efficiency Rating

Pricing

$

1.15

Input tokens per million

$

8

Output tokens per million

Features

Tool Calling

Supported

JSON Mode

Supported

Create an account and start building today.

Book a demo

Explore docs

Create an account and start building today.

Book a demo

Explore docs