Is Devstral 2 123B 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 or gpt-oss-120b?

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

Devstral 2 123B vs gpt-oss-120b

gpt-oss-120b is cheaper on output tokens, while Devstral 2 123B offers a larger context window. Choose Devstral 2 123B 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	gpt-oss-120b
Provider	Amazon Bedrock	Amazon Bedrock
Input / 1M tokens	$0.40	$0.15
Output / 1M tokens	$2.00	$0.60
Context window	256K	128K
Parameters	—	117B
Open weights	Yes	No
Released	Feb 2026	Aug 2025

Devstral 2 123B 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.