Is Qwen3.5 397B A17B FP8 or Kimi K2.5 cheaper?

Kimi K2.5 is cheaper on output tokens ($2.59 vs $4.14 per 1M).

Which has the larger context window, Qwen3.5 397B A17B FP8 or Kimi K2.5?

Both models offer a similar context window.

Qwen3.5 397B A17B FP8 vs Kimi K2.5

Kimi K2.5 is cheaper on output tokens. Choose Qwen3.5 397B A17B FP8 or Kimi K2.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Qwen3.5 397B A17B FP8	Kimi K2.5
Provider	Neuralwatt	Neuralwatt
Input / 1M tokens	$0.69	$0.52
Output / 1M tokens	$4.14	$2.59
Context window	262K	262K
Parameters	—	1T
Open weights	Yes	Yes
Released	Feb 2026	Jan 2026

Qwen3.5 397B A17B FP8 details →Kimi K2.5 details →

FAQ

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