Is Llama Guard 4 12B or gpt-oss-20b cheaper?

gpt-oss-20b is cheaper on output tokens ($0.14 vs $0.18 per 1M).

Which has the larger context window, Llama Guard 4 12B or gpt-oss-20b?

Llama Guard 4 12B has the larger context window (164K tokens).

Llama Guard 4 12B vs gpt-oss-20b

gpt-oss-20b is cheaper on output tokens, while Llama Guard 4 12B offers a larger context window. Choose Llama Guard 4 12B or gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama Guard 4 12B	gpt-oss-20b
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$0.18	$0.03
Output / 1M tokens	$0.18	$0.14
Context window	164K	131K
Parameters	—	21B
Open weights	Yes	Yes
Released	Apr 2025	Aug 2025

Llama Guard 4 12B 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.