Is Llama-3.1-8B-Instruct or Llama-3.3-70B-Instruct cheaper?

Llama-3.1-8B-Instruct is cheaper on output tokens ($0.06 vs $0.79 per 1M).

Which has the larger context window, Llama-3.1-8B-Instruct or Llama-3.3-70B-Instruct?

Both models offer a similar context window.

Llama-3.1-8B-Instruct vs Llama-3.3-70B-Instruct

Llama-3.1-8B-Instruct is cheaper on output tokens. Choose Llama-3.1-8B-Instruct or Llama-3.3-70B-Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Llama-3.1-8B-Instruct	Llama-3.3-70B-Instruct
Provider	Hugging Face	Hugging Face
Input / 1M tokens	$0.06	$0.59
Output / 1M tokens	$0.06	$0.79
Context window	131K	131K
Parameters	—	—
Open weights	Yes	Yes
Released	Jul 2024	Dec 2024

Llama-3.1-8B-Instruct details →Llama-3.3-70B-Instruct details →

FAQ

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