AI model · Moonshot AI

kimi-k2

MoonshotAI: Kimi K2 0711

Input costs $0.57 per million tokens and output costs $2.30. It takes up to 131,072 tokens of context at once. At 10 million tokens a month that works out to about $10.02. Its intelligence index is 12.7, ranking 112 of 175 scored models. Listed in the catalogue on 7/12/2025.

Input$0.57
Output$2.30
Context131,072
Listed7/12/2025
ProducesText
AcceptsText

The maker does not sell this model directly. The figure shown is a reseller rate on OpenRouter, and its moves are not reported as news.

You will only get news about this version (kimi-k2).

What it costs a month

Token prices translated into real usage.

  • Light1M tokens a month: a personal tool or trial
    ₩1,327$1.00
  • Steady10M tokens a month: one small service
    ₩13,272$10.02
  • Heavy100M tokens a month: a service with real users
    ₩132,721$100.25

Sending 10,000 Korean characters and getting 2,000 back, 1,000 times a month, costs about ₩9,859.

The same content in English costs about ₩7,583. Korean runs 1.3x.

Mixed 75% input, 25% output: a common ratio for chat usage, though real cost depends on how you use it. Exchange rate is from the last collection.

Report card

What this model is good at, by subject.

Overall12.7#112 of 175 tracked
An index the source builds by weighting ten evaluations. Not a percentage, and not an average of the subjects below. It includes very hard tests we do not list, which keeps the numbers low (today's leader is in the low 50s). Use it to compare models.
  • KoreanKMMLU-HARDwe measured—not taken
  • ScienceGPQA76.6#88/159
  • MathAA Math Indexsaturated57#41/94
  • CodingAA Coding Index—not taken
  • ReadingAA-LCRin-house test53#101/155
  • KnowledgeMMLU-Pro82.4#30/92
  • Instruction followingIFBench41.5#82/129
  • Hard reasoningHLE7.4#114/171

Measured and published by Artificial Analysis. Each subject is a different test, so compare within a subject rather than across them.

Community

Share what using it is actually like: the part the metrics do not show.

Would you recommend this model?
No links, 500 characters max. Reported notes are hidden automatically.Sign in
  • No notes yet. Be the first to share.

Buzz trend

How much this model was talked about over the past week.

Rank#105
Buzz13.7
6d agoNow

News about this model

No news about this model yet.

Other models from this vendor

Jump straight to where the conversation is.

ModelPerformanceInputOutputContext
kimi-k3.1-pro55.1$2.00$10.001.049M
kimi-k343.6$3.00$15.001.049M
kimi-k2.7-code25.8$0.95$4.00262K
kimi-k2.627$0.95$4.00262K
kimi-k2.523.5$0.50$2.50262K
kimi-k2-thinking22$0.60$2.50262K
kimi-k2-090515.3$0.60$2.50262K

Compare with others

Pricing and scores side by side. Blank cells mean the price is undisclosed or the model did not take that test.