LLM360

K2 Think

Open Weightsapache-2.0Released May 2026

A 32 billion parameter open-weights reasoning model by LLM360/MBZUAI, built on Qwen2.5-32B. Trained with reinforcement learning and verifiable rewards for long chain-of-thought reasoning, agentic planning, and complex problem solving in math, science, and code.

Capabilities

chatcompletioncode-generationreasoning

Modalities

textcode

Context Window

131K tokens

Providers

available

Available from 1 provider

Cheapest

Cerebras

$1.20/1M tokens

Cerebras

Providers (1)

Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.

Provider	Pricing (per 1M)	Rate Limits	Regions	Health	Latency
Cerebras	In: $0.60Out: $0.60	30 RPM / 60K TPM	us-east-1	Healthy	0ms

Quick Start

Use this model via Cerebras with an OpenAI-compatible SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.cerebras.ai/v1",
  apiKey: process.env.CEREBRAS_API_KEY,
});

const response = await client.chat.completions.create({
  model: "k2-think",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

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

Using Cerebras API • OpenAI-compatible SDK