Is Llama 4 Scout 17B Instruct (US) or gpt-oss-120b cheaper?

gpt-oss-120b is cheaper on output tokens ($0.60 vs $0.66 per 1M).

Which has the larger context window, Llama 4 Scout 17B Instruct (US) or gpt-oss-120b?

Llama 4 Scout 17B Instruct (US) has the larger context window (3.5M tokens).

Llama 4 Scout 17B Instruct (US) vs gpt-oss-120b

gpt-oss-120b is cheaper on output tokens, while Llama 4 Scout 17B Instruct (US) offers a larger context window. Choose Llama 4 Scout 17B Instruct (US) or gpt-oss-120b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama 4 Scout 17B Instruct (US)	gpt-oss-120b
Provider	Amazon Bedrock	Amazon Bedrock
Input / 1M tokens	$0.17	$0.15
Output / 1M tokens	$0.66	$0.60
Context window	3.5M	128K
Parameters	—	117B
Open weights	Yes	No
Released	Apr 2025	Aug 2025

Llama 4 Scout 17B Instruct (US) 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.