Is gpt-oss-120b or Meta-Llama-3_3-70B-Instruct cheaper?

gpt-oss-120b is cheaper on output tokens ($0.47 vs $0.74 per 1M).

Which has the larger context window, gpt-oss-120b or Meta-Llama-3_3-70B-Instruct?

Both models offer a similar context window.

gpt-oss-120b vs Meta-Llama-3_3-70B-Instruct

gpt-oss-120b is cheaper on output tokens. Choose gpt-oss-120b or Meta-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	Meta-Llama-3_3-70B-Instruct
Provider	OVHcloud AI Endpoints	OVHcloud AI Endpoints
Input / 1M tokens	$0.09	$0.74
Output / 1M tokens	$0.47	$0.74
Context window	131K	131K
Parameters	117B	—
Open weights	Yes	Yes
Released	Aug 2025	Apr 2025

gpt-oss-120b details →Meta-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.