Billing note Non-commercial use only: this model is currently provided solely for performance evaluation, and commercial use is not permitted. The charges are an API infrastructure usage fee, not a for-profit price. Reasoning is always on (default reasoning_effort max) and counts toward max_tokens: in testing max_tokens 20 ended with empty content (finish_reason length). Use max_tokens >= 2048, or set reasoning_effort to low for short answers. Reasoning tokens are billed at the output rate.

LG AI ResearchMediumHigh

K-EXAONE 2.5

LG AI Research's K-EXAONE 2.5 over the direct EXAONE API - a Korean/English reasoning model (750B total, 31B active parameters) with a 512K-token context window, tool calling and structured outputs. Currently available for non-commercial use only, for performance evaluation. It always reasons before answering, so keep max_tokens at 2,048 or more.

186/929credits

input / output · per 1M tokens

512K-token context window

Korean and English reasoning model

Tool calling and structured outputs

reasoning_effort low / high / max

OpenAI-compatible API (chat completions) via /llm/exaone/v1

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Model Specifications

Context Window

524K

tokens

Max Output

524K

tokens

Training Cutoff

2026-01

Compatible SDK

OpenAI

Capabilities

Vision

Function Calling

Streaming

JSON Mode

System Prompt

Token Pricing (per 1M tokens)

Token Type	Credits	USD Equivalent
Input Tokens	186	$0.12
Output Tokens	929	$0.62

* 1,500 credits ≈ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/exaone/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "k-exaone_v2.5",
  "messages": [
    {
      "role": "user",
      "content": "다음 보고서를 다섯 줄로 요약해 줘."
    }
  ],
  "max_tokens": 4096
}'

Parameters

Parameter	Type	Required	Default	Description
`messages`	array	Yes	-	Chat messages in OpenAI format (system/user/assistant roles).
`max_tokens`	integer	No	2048	Maximum completion tokens including reasoning. Keep >= 2048 or the answer may be cut off before any content is produced.
`reasoning_effort`	string	No	max	Reasoning depth: low, high or max.
`temperature`	number	No	1.0	Sampling temperature. LG recommends 1.0 with top_p 0.95.
`stream`	boolean	No	false	Stream the response as server-sent events.

Examples

Chat completion

OpenAI-compatible chat completion over the direct EXAONE route

curl -X POST "https://api.core.today/llm/exaone/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "k-exaone_v2.5",
  "messages": [
    {
      "role": "user",
      "content": "다음 보고서를 다섯 줄로 요약해 줘."
    }
  ],
  "max_tokens": 4096
}'