Moonshot AI

Kimi K2

Moonshot's Kimi — the long-context reading specialist.

Long context

Kimi K2 is not currently offered on Token Harbor.

Looking for something comparable? Kimi K3 is live on our catalog — same family, currently served and priced.

Browse live models →

Ratings & benchmarks

Snapshot 2026-04-28

Overall

4.0 / 5

Composite of intelligence + reliability.

Output speed

40 t/s

Output tokens per second under typical load.

Time to first token

1.5 s

Lower is better. Reasoning models naturally stretch this.

Value

4.2 / 5

Intelligence per dollar at typical mix.

Context window

262,144 tokens