Is Devstral 2 123B Instruct (2512) or Qwen3.5 397B A17B cheaper?

Devstral 2 123B Instruct (2512) is cheaper on output tokens ($2.00 vs $3.60 per 1M).

Which has the larger context window, Devstral 2 123B Instruct (2512) or Qwen3.5 397B A17B?

Both models offer a similar context window.

Devstral 2 123B Instruct (2512) vs Qwen3.5 397B A17B

Devstral 2 123B Instruct (2512) is cheaper on output tokens. Choose Devstral 2 123B Instruct (2512) or Qwen3.5 397B A17B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Devstral 2 123B Instruct (2512)	Qwen3.5 397B A17B
Provider	Scaleway	Scaleway
Input / 1M tokens	$0.40	$0.60
Output / 1M tokens	$2.00	$3.60
Context window	256K	256K
Parameters	—	397B
Open weights	Yes	Yes
Released	Jan 2026	Mar 2026

Devstral 2 123B Instruct (2512) details →Qwen3.5 397B A17B details →

FAQ

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