Is openai/gpt-oss-20b or openai/gpt-oss-120b cheaper?

openai/gpt-oss-20b is cheaper on output tokens ($0.18 vs $0.45 per 1M).

Which has the larger context window, openai/gpt-oss-20b or openai/gpt-oss-120b?

Both models offer a similar context window.

openai/gpt-oss-20b vs openai/gpt-oss-120b

openai/gpt-oss-20b is cheaper on output tokens. Choose openai/gpt-oss-20b or openai/gpt-oss-120b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	openai/gpt-oss-20b	openai/gpt-oss-120b
Provider	SiliconFlow	SiliconFlow
Input / 1M tokens	$0.04	$0.05
Output / 1M tokens	$0.18	$0.45
Context window	131K	131K
Parameters	21B	117B
Open weights	No	No
Released	Aug 2025	Aug 2025

openai/gpt-oss-20b details →openai/gpt-oss-120b details →

FAQ

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