Kimi K2 Instruct

by Moonshot

Kimi K2 Instruct is Moonshot's post-trained variant of the base Kimi K2 model, tuned for instruction following, conversational use, and agentic problem solving. It uses the 1 trillion total parameter Mixture-of-Experts architecture with 32 billion active parameters and a 128K token context window. Trained with the Muon optimizer, the model targets tool use, reasoning, and autonomous task execution. Moonshot reports strong results across coding (53.7 on LiveCodeBench v6, 85.7 on MultiPL-E), mathematics (69.6 on AIME 2024), and reasoning (89.5 on MMLU), making it well suited to general-purpose assistance with reasoning demands. The model is built for tool calling in agentic applications and is optimized for immediate, reflex-style responses rather than long deliberation. It supports structured output and runs on inference engines including vLLM, SGLang, and KTransformers.

Key info

Input
Output
Features
Context window
128K
Max output
33K
Input price
$1.00 /1M
Output price
$3.00 /1M
  • US residency available
  • Zero data retention via Enterprise
  • No training by default
  • GDPR DPA available

Available routes

Kimi K2 Instruct runs on 2 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
GroqUSEnterpriseNo$1.00$3.00
NovitaUSEnterpriseNo$0.57$2.30

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Kimi K2 Instruct has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Groq β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring (30-day retention)
Third-party access
Provider may share with subprocessors / partners
GDPR DPA
DPA available
Transfer mechanism
SCCs

Novita β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
SCCs

Get started

Call Kimi K2 Instruct through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β€” Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent β€” Claude Code, Cursor, Codex, and more β€” and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "groq/moonshotai/kimi-k2-instruct",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Kimi K2 Instruct with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Moonshot

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Kimi K2 Instruct by Moonshot β€” pricing, benchmarks | Opper AI