Kimi K2 Thinking

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

by MoonshotAI

Overview

Quick stats across all benchmark runs.

Score

31%

58 benchmarks

Avg Latency

47.3s

378 requests

Pricing

$0.60 in / $2.50 out

per 1M tokens

Context

262K

tokens

Alternatives

Models with similar or better quality but different tradeoffs

Same Quality, Cheaper

Models with similar or better performance at a lower cost per token.

Model	Cost
Gemini 2.0 Flash	-91%
DeepSeek V3.2	-89%
DeepSeek V3 0324	-85%
Mistral Large 3 2512	-75%
Gemini 3 Flash Preview	-68%

Same Quality, Faster

Models with similar or better performance but lower latency.

Model	Latency
Gemini 3 Flash Preview	-86%
Gemini 2.0 Flash	-85%
Gemini 2.5 Flash	-83%
Claude Haiku 4.5	-81%
Claude Sonnet 4.5	-69%

Same Cost, Better

Models at a similar price point with higher benchmark scores.

Model	Score
Gemini 3 Flash Preview	+9%
GPT-5 Mini	+1%
DeepSeek V3.2 Speciale	+0%
GLM 4.7	+0%

Benchmark Performance

How this model performs across different benchmarks

Benchmark	Score	Rank
Character Frequency Bench	100%	2 / 29
Spatial Reasoning: Germany	95%	6 / 29
Explain Like I'm 5	94%	10 / 47
Niederstetten Benchmark	44%	20 / 35
Money Boy Cultural Literacy Test	37%	72 / 107
Categorization Bench	36%	39 / 54
German Memelord Bench	31%	15 / 29

Price vs Performance

Compare cost efficiency across all models

Current model (baseline)

Other models (relative score)

Y-axis shows score difference from shared benchmarks. X-axis uses log scale.

Score Over Time

Performance trends across all benchmark runs

Benchmark Activity

Number of benchmark runs over time

Quickstart

View on OpenRouter

Get started with this model using OpenRouter

import { OpenRouter } from "@openrouter/sdk";

const openrouter = new OpenRouter({
  apiKey: "<OPENROUTER_API_KEY>"
});

const completion = await openrouter.chat.completions.create({
  model: "moonshotai/kimi-k2-thinking",
  messages: [
    {
      role: "user",
      content: "Hello!"
    }
  ]
});

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

Get your API key at openrouter.ai/keys

Other Models from MoonshotAI

Compare performance with other models from the same creator

Model	Latency	Cost/1M	Score
Kimi K2.6	33.2s	$2.11	60%
Kimi K2 0905	34.5s	$1.55	—
Kimi K2 0711	15.0s	$1.44	—
Kimi Dev 72B	173.1s	$0.72	—
Kimi K2.5	9.6s	$1.15	—