Kimi
Kimi K3
moonshotai/kimi-k3
Kimi K3 is a 2.8T-parameter open-weight multimodal reasoning model from Moonshot AI, built for complex coding and agentic workflows over long contexts.
Pricing
| Input | $3.00per 1M tokens |
|---|---|
| Output | $15.00per 1M tokens |
| Cached input | $0.3per 1M tokens read from cache |
Specifications
| Context window | 1Mtokens |
|---|---|
| Max output | 66Ktokens |
| Provider | Kimi |
| Capabilities | Vision · Reasoning · Function calling |
| Input types | text, image |
Use Kimi K3
Point your existing OpenAI SDK at xKiro and pass moonshotai/kimi-k3 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",
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 · reasoning · include_reasoning
Related models
Call Kimi K3 through the same endpoints you already use.
Get an API key