Kimi K2.8 Preview

Kimi K2.8 预览版 · 始终开启思考模式 (reasoning_content 计入 token 消耗) · 支持工具调用与隐式提示缓存

Model ID: kimi-k2.8-preview · Type: chat · Provider: Moonshot

Endpoints: /v1/chat/completions · /v1/messages · /v1/responses

Pricing

Input (per 1M tokens)$0.55 USD
Output (per 1M tokens)$2.2 USD
Cache read (per 1M tokens)$0.1375 USD

Capabilities

from openai import OpenAI

client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
    model="kimi-k2.8-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does Kimi K2.8 Preview cost on 聚合 AI 中转站?

Kimi K2.8 Preview (`kimi-k2.8-preview`) is billed per usage at $0.55/1M in · $2.2/1M out, in USD. Current pricing is always listed at https://yigekey.com/models/kimi-k2.8-preview.

How do I call Kimi K2.8 Preview through 聚合 AI 中转站?

Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "kimi-k2.8-preview"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

Which endpoints does Kimi K2.8 Preview support?

Kimi K2.8 Preview can be called on: /v1/chat/completions; /v1/messages; /v1/responses.

What is Kimi K2.8 Preview's context window?

Kimi K2.8 Preview accepts up to 1,048,576 input tokens and can return up to 131,072 output tokens. Requests exceeding the input limit are rejected before reaching the model.

What can Kimi K2.8 Preview do?

Kimi K2.8 Preview supports: function_calling, prompt_caching, reasoning, web_search.

Who makes Kimi K2.8 Preview?

Kimi K2.8 Preview is a chat model from Moonshot, available through the 聚合 AI 中转站 gateway with the same API key as every other model.

Call it through the 聚合 AI 中转站 OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can discover and call every model on this gateway through MCP (https://mcp.router.ai/mcp) with no manual integration.

Which should you pick

API reference · All models