Is Devstral Small 2505 or Kimi K2 Thinking cheaper?

Devstral Small 2505 is cheaper on output tokens ($0.22 vs $2.25 per 1M).

Which has the larger context window, Devstral Small 2505 or Kimi K2 Thinking?

Devstral Small 2505 has the larger context window (128K tokens).

Devstral Small 2505 vs Kimi K2 Thinking

Devstral Small 2505 is cheaper on output tokens, while Devstral Small 2505 offers a larger context window. Choose Devstral Small 2505 or Kimi K2 Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Devstral Small 2505	Kimi K2 Thinking
Provider	IO.NET	IO.NET
Input / 1M tokens	$0.05	$0.55
Output / 1M tokens	$0.22	$2.25
Context window	128K	33K
Parameters	—	1T
Open weights	No	No
Released	May 2025	Nov 2024

Devstral Small 2505 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.