Is Llama 3 8B Instruct or GPT OSS 120B cheaper?

Llama 3 8B Instruct is cheaper on output tokens ($0.14 vs $0.15 per 1M).

Which has the larger context window, Llama 3 8B Instruct or GPT OSS 120B?

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

Llama 3 8B Instruct vs GPT OSS 120B

Llama 3 8B Instruct is cheaper on output tokens, while GPT OSS 120B offers a larger context window. Choose Llama 3 8B Instruct or GPT OSS 120B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama 3 8B Instruct	GPT OSS 120B
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$0.14	$0.03
Output / 1M tokens	$0.14	$0.15
Context window	8K	131K
Parameters	—	117B
Open weights	Yes	Yes
Released	Apr 2024	Aug 2025

Llama 3 8B Instruct 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.