Is GPT-OSS 20B or Kimi K2 Thinking cheaper?

GPT-OSS 20B is cheaper on output tokens ($0.14 vs $2.25 per 1M).

Which has the larger context window, GPT-OSS 20B or Kimi K2 Thinking?

GPT-OSS 20B has the larger context window (64K tokens).

GPT-OSS 20B vs Kimi K2 Thinking

GPT-OSS 20B is cheaper on output tokens, while GPT-OSS 20B offers a larger context window. Choose GPT-OSS 20B or Kimi K2 Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-OSS 20B	Kimi K2 Thinking
Provider	IO.NET	IO.NET
Input / 1M tokens	$0.03	$0.55
Output / 1M tokens	$0.14	$2.25
Context window	64K	33K
Parameters	21B	1T
Open weights	Yes	No
Released	Dec 2024	Nov 2024

GPT-OSS 20B 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.