G

Groq: Kimi K2 Instruct

Groq
131K
Context
$0.0500
Input /1M
$0.1500
Output /1M
8K
Max Output
Run API Call Open in Chat

Groq: Kimi K2 Instruct

Model Overview

Property Value
Model ID groq/moonshotai/kimi-k2-instruct
Name Kimi K2 Instruct
Provider Groq / MoonshotAI

Description

MoonshotAI's Kimi K2 instruction-tuned model, hosted on Groq infrastructure for fast inference. Designed for general-purpose instruction following with strong multilingual capabilities.

Specifications

Spec Value
Context Window 131,072 tokens
Max Completion 8,192 tokens
Inference Speed ~200 tokens/sec

Pricing

Type Price
Input $0.05 per 1M tokens
Output $0.15 per 1M tokens

Capabilities

  • Instruction Following: Yes
  • Multilingual: Yes
  • Fast Inference: Yes

Use Cases

General-purpose chat, instruction following, multilingual applications.

Integration with LangMart

Gateway Support: Type 2 (Cloud), Type 3 (Self-hosted)

API Usage:

curl -X POST https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "groq/moonshotai/kimi-k2-instruct",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 4096
  }'
  • groq/moonshotai/kimi-k2-instruct-0905 - September 5 version

Last Updated: December 28, 2025