Is MiniMax M2 or gpt-oss-20b cheaper?

gpt-oss-20b is cheaper on output tokens ($0.30 vs $1.20 per 1M).

Which has the larger context window, MiniMax M2 or gpt-oss-20b?

MiniMax M2 has the larger context window (205K tokens).

MiniMax M2 vs gpt-oss-20b

gpt-oss-20b is cheaper on output tokens, while MiniMax M2 offers a larger context window. Choose MiniMax M2 or gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	MiniMax M2	gpt-oss-20b
Provider	Amazon Bedrock	Amazon Bedrock
Input / 1M tokens	$0.30	$0.07
Output / 1M tokens	$1.20	$0.30
Context window	205K	128K
Parameters	229B	21B
Open weights	Yes	No
Released	Oct 2025	Aug 2025

MiniMax M2 details →gpt-oss-20b details →

FAQ

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