Is Devstral 2 123B Instruct (2512) or GPT-OSS 120B cheaper?

GPT-OSS 120B is cheaper on output tokens ($0.60 vs $2.00 per 1M).

Which has the larger context window, Devstral 2 123B Instruct (2512) or GPT-OSS 120B?

Devstral 2 123B Instruct (2512) has the larger context window (256K tokens).

Devstral 2 123B Instruct (2512) vs GPT-OSS 120B

GPT-OSS 120B is cheaper on output tokens, while Devstral 2 123B Instruct (2512) offers a larger context window. Choose Devstral 2 123B Instruct (2512) or GPT-OSS 120B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Devstral 2 123B Instruct (2512)	GPT-OSS 120B
Provider	Scaleway	Scaleway
Input / 1M tokens	$0.40	$0.15
Output / 1M tokens	$2.00	$0.60
Context window	256K	128K
Parameters	—	117B
Open weights	Yes	Yes
Released	Jan 2026	Jan 2024

Devstral 2 123B Instruct (2512) details →GPT-OSS 120B details →

FAQ

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