Skip to main content
Launching the open-source gateway

Kimi K2 vs MiniMax M2

SpecKimi K2MiniMax M2
Respan Index17.3 (#136)17.5 (#135)
Blended price per 1M$1$0.446
Context window128K205K
Input / output per 1M$0.57 / $2.3$0.255 / $1.02
Max output-128K
Inputtexttext
Released2025-07-112025-10-27

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryKimi K2MiniMax M2
Coding5.3 Kimi K25.1 MiniMax M2
Agents12.3* Kimi K212.7 MiniMax M2
Reasoning18.5 Kimi K218.9 MiniMax M2
Knowledge & language11.6 Kimi K211.8* MiniMax M2
Human preference47.2 Kimi K247.5 MiniMax M2

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Kimi K2 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkKimi K2MiniMax M2
LMArena Elo14181344
SimpleBench (SimpleBench)26.3%25%

FAQ

Is Kimi K2 better than MiniMax M2?

MiniMax M2 scores 17.5 on the Respan Index (#135), ahead of Kimi K2 at 17.3 (#136). Kimi K2 leads on 2 of the 2 benchmarks both report.

Which is cheaper, Kimi K2 or MiniMax M2?

Kimi K2 lists at $0.57 input and $2.3 output per 1M tokens; MiniMax M2 at $0.255 and $1.02. MiniMax M2 is 2.2x cheaper per token at list price.

Which has the larger context window?

Kimi K2 accepts 128K tokens and MiniMax M2 205K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.