Is gpt-oss-120b or Llama-3.3-70B-Instruct cheaper?

gpt-oss-120b is cheaper on output tokens ($0.60 vs $0.71 per 1M).

Which has the larger context window, gpt-oss-120b or Llama-3.3-70B-Instruct?

gpt-oss-120b has the larger context window (131K tokens).

gpt-oss-120b vs Llama-3.3-70B-Instruct

gpt-oss-120b is cheaper on output tokens, while gpt-oss-120b offers a larger context window. Choose gpt-oss-120b or Llama-3.3-70B-Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	gpt-oss-120b	Llama-3.3-70B-Instruct
Provider	Weights & Biases	Weights & Biases
Input / 1M tokens	$0.15	$0.71
Output / 1M tokens	$0.60	$0.71
Context window	131K	128K
Parameters	117B	—
Open weights	No	Yes
Released	Aug 2025	Dec 2024

gpt-oss-120b 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.