Kimi
Kimi K2.8 Preview
moonshotai/kimi-k2.8-preview
Kimi K2.8 Preview is Moonshot AI's newest mid-tier coding model, positioned between Kimi K2.7 Code and Kimi K3, with a 1M-token context window and adjustable reasoning effort.
Pricing
| Input | $0.5per 1M tokens |
|---|---|
| Output | $2.00per 1M tokens |
| Cached input | $0.08per 1M tokens read from cache |
Specifications
| Context window | 1.05Mtokens |
|---|---|
| Max output | 66Ktokens |
| Provider | Kimi |
| Capabilities | Vision · Reasoning · Function calling |
| Input types | text, image |
Use Kimi K2.8 Preview
Point your existing OpenAI SDK at xKiro and pass moonshotai/kimi-k2.8-preview 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-k2.8-preview",
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 K3$1.50
- Kimi K3 256K$1.50
- DeepSeek V4 FlashFree
- DeepSeek V4 Flash 0731$0.105
- DeepSeek V4 Flash Vision$0.198
Call Kimi K2.8 Preview through the same endpoints you already use.
Get an API key