Is GPT OSS 20B or GPT OSS 120B cheaper?

GPT OSS 20B is cheaper on output tokens ($0.14 vs $0.19 per 1M).

Which has the larger context window, GPT OSS 20B or GPT OSS 120B?

Both models offer a similar context window.

GPT OSS 20B vs GPT OSS 120B

GPT OSS 20B is cheaper on output tokens. Choose GPT OSS 20B or GPT OSS 120B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT OSS 20B	GPT OSS 120B
Provider	Deep Infra	Deep Infra
Input / 1M tokens	$0.03	$0.04
Output / 1M tokens	$0.14	$0.19
Context window	131K	131K
Parameters	21B	117B
Open weights	Yes	Yes
Released	Aug 2025	Aug 2025

GPT OSS 20B 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.