modelbenchmark.io

Kimi K2 Thinking

Kimi · kimi-k2-thinking-maas

Compare

Kimi reasoning model for long-horizon research, planning, and tool use

Specification

most-agreed values

Context
262K
Max output
262K
Released
2025-11-13
Knowledge cutoff
2024-08
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.60
Output
$2.50
Cache read
$0.06

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
google-vertex · moonshotai$0.60$2.50$0.06262K262K
vertex_ai-moonshot_models$0.60$2.50256K256K

Other listings of this model

this page is one of them

The corpus files Kimi K2 Thinking under several keys. This page is the kimi-k2-thinking-maas listing. The full record — every host, every price and every benchmark score — is on the main Kimi K2 Thinking page.

More from Kimi

most-hosted first