K-EXAONE-236B-A23B

Overview

K-EXAONE is a state-of-the-art large language model developed by LG AI Research with 236 billion parameters. It features advanced reasoning capabilities, strong performance in both Korean and English, and excels at complex tasks including mathematics, coding, and creative writing. The model uses A23B quantization for efficient inference while maintaining high quality outputs. K-EXAONE is designed for enterprise applications with robust instruction following and knowledge integration.

K-EXAONE-236B-A23B was released on December 31, 2025. API access is available through FriendliAI.

Benchmarks

K-EXAONE-236B-A23B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

Share

llm-stats.com - Fri Jan 09 2026

Pricing

Pricing, performance, and capabilities for K-EXAONE-236B-A23B across different providers:

Provider	Input ($/M)	Output ($/M)	Max Input	Max Output	Latency (s)	Throughput	Quantization	Input	Output
FriendliAIA23B	$0.60	$1.00	32.8K	8.2K	0.4	50.0 c/s	A23B	Text Image Audio Video	Text Image Audio Video

API Access