Kimi-K2-Turbo · 10M tokens

The K2 generation served at higher throughput, for interfaces where perceived latency matters more than the last point of accuracy.

What you get

• 10M tokens for every unit you buy. Order several units to stack quota.
• A personal access key for kimi-k2-turbo, issued automatically once your order is completed.
• No shipping: delivery is digital, under My Account > Order History and by email.

Capabilities

• Fastest
• 200 tok/s
• Multimodal
• 256K context

Best for

Latency-sensitive agents and interactive multimodal tools.

Quick start

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_ACCESS_KEY",
    base_url="https://api.moonshot.ai/v1",
)

response = client.chat.completions.create(
    model="kimi-k2-turbo",
    messages=[{"role": "user", "content": "Hello"}],
)

print(response.choices[0].message.content)