Kimi K2.8 Preview

Moonshot AIMCP Tool CallReasoning
moonshotai/kimi-k2.8-previewClosed API

Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code

Benchmark Pricing$0.00 / 1M in$0.00 / 1M out$0.00 cache read
Context: 1,048,576 tokens•Max Output: 4,096 tokens•Released: 2026-09-11

TECHNICAL SPECIFICATIONS

Context Window1,048,5761M tokens
Max Output4,0964.1K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVisionVideo
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Kimi K2.8 Preview natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,048,576 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

API CALL INVOCATION EXAMPLE

// Example: Calling Kimi K2.8 Preview via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MOONSHOTAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "moonshotai/kimi-k2.8-preview",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

1 providers
Kimi For Coding (kimi.com)kimi-for-coding
$0.00 / $0.00$0.00 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.00 / 1M tokens, saving up to 100% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES