Kimi K3 256K

moonshotai/kimi-k3-256k

Kimi K3 256K is Moonshot AI's Kimi K3 multimodal reasoning model served with a fixed 256K-token context window, for coding and agentic work that does not need the full 1M context.

Pricing

Specifications

Use Kimi K3 256K

Point your existing OpenAI SDK at xKiro and pass moonshotai/kimi-k3-256k as the model. Nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xkiro.com/v1",
    api_key="YOUR_XKIRO_KEY",
)

response = client.chat.completions.create(
    model="moonshotai/kimi-k3-256k",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

max_tokens · temperature · top_p · stop · frequency_penalty · presence_penalty · seed · stream · tools · tool_choice · response_format · structured_outputs · reasoning · include_reasoning

Related models

• Kimi K2.7 Code HighSpeed$0.95
• Kimi K2.8 Preview$0.5
• Kimi K3$1.50
• Qwen3 Max (Free)Free
• Qwen3 Omni Flash (Free)Free
• Qwen3 VL Plus (Free)Free