Is MiniMax M2.5 or GPT OSS 20B cheaper?

GPT OSS 20B is cheaper on output tokens ($0.14 vs $1.15 per 1M).

Which has the larger context window, MiniMax M2.5 or GPT OSS 20B?

MiniMax M2.5 has the larger context window (197K tokens).

MiniMax M2.5 vs GPT OSS 20B

GPT OSS 20B is cheaper on output tokens, while MiniMax M2.5 offers a larger context window. Choose MiniMax M2.5 or GPT OSS 20B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	MiniMax M2.5	GPT OSS 20B
Provider	Deep Infra	Deep Infra
Input / 1M tokens	$0.15	$0.03
Output / 1M tokens	$1.15	$0.14
Context window	197K	131K
Parameters	—	21B
Open weights	Yes	Yes
Released	Feb 2026	Aug 2025

MiniMax M2.5 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.