Is Llama 3.1 8B or GPT-OSS 120B cheaper?

Llama 3.1 8B is cheaper on output tokens ($0.27 vs $0.71 per 1M).

Which has the larger context window, Llama 3.1 8B or GPT-OSS 120B?

GPT-OSS 120B has the larger context window (131K tokens).

Llama 3.1 8B vs GPT-OSS 120B

Llama 3.1 8B is cheaper on output tokens, while GPT-OSS 120B offers a larger context window. Choose Llama 3.1 8B or GPT-OSS 120B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama 3.1 8B	GPT-OSS 120B
Provider	STACKIT	STACKIT
Input / 1M tokens	$0.16	$0.49
Output / 1M tokens	$0.27	$0.71
Context window	128K	131K
Parameters	—	117B
Open weights	Yes	Yes
Released	Jul 2024	Aug 2025

Llama 3.1 8B 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.