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

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

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

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

GPT-OSS 120B vs Llama 3.1 8B

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

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

GPT-OSS 120B details →Llama 3.1 8B details →

FAQ

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