Kimi K2 Thinking

by Moonshot

Moonshot Kimi K2 Thinking on Evroc (EU)

ReasoningToolsStructured output

Context window

262K

Max output

262K

Input price

$1.35 /1M

Output price

$5.40 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#70 of 505 LLMs

TierStrong

Output speed128 tok/s

First token0.92s

Intelligence Index40.9

Coding Index34.8

Math Index94.7

MMLU-Pro

85%

GPQA Diamond

84%

Humanity's Last Exam

22%

LiveCodeBench

85%

SciCode

42%

AIME 2025

95%

IFBench

68%

Long-context reasoning

66%

Terminal-Bench Hard

31%

τ²-Bench Telecom

93%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Available routes

The same Kimi K2 Thinking runs on 2 different routes through the Opper gateway. Each route has its own data-handling posture.

Provider	Region	Zero data retention	Training	Logging	Contract	Input	Output
Evroc	EU	None	No	Not enumerated publicly	PAYG	$1.35	$5.40
Novita	US	None	—	Not published; appendix available upon request.	PAYG	$0.60	$2.50

Human review: Abuse-flagged only

Other models from Moonshot