Is Kimi K2 Instruct or Kimi K2 Thinking cheaper?

Kimi K2 Instruct is cheaper on output tokens ($1.90 vs $2.25 per 1M).

Which has the larger context window, Kimi K2 Instruct or Kimi K2 Thinking?

Both models offer a similar context window.

Kimi K2 Instruct vs Kimi K2 Thinking

Kimi K2 Instruct is cheaper on output tokens. Choose Kimi K2 Instruct or Kimi K2 Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Kimi K2 Instruct	Kimi K2 Thinking
Provider	IO.NET	IO.NET
Input / 1M tokens	$0.39	$0.55
Output / 1M tokens	$1.90	$2.25
Context window	33K	33K
Parameters	—	1T
Open weights	No	No
Released	Sep 2024	Nov 2024

Kimi K2 Instruct details →Kimi K2 Thinking details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.