Is Phi-4-mini-instruct or gpt-oss-120b cheaper?

Phi-4-mini-instruct is cheaper on output tokens ($0.35 vs $0.60 per 1M).

Which has the larger context window, Phi-4-mini-instruct or gpt-oss-120b?

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

Phi-4-mini-instruct vs gpt-oss-120b

Phi-4-mini-instruct is cheaper on output tokens, while gpt-oss-120b offers a larger context window. Choose Phi-4-mini-instruct or gpt-oss-120b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Phi-4-mini-instruct	gpt-oss-120b
Provider	Weights & Biases	Weights & Biases
Input / 1M tokens	$0.08	$0.15
Output / 1M tokens	$0.35	$0.60
Context window	128K	131K
Parameters	—	117B
Open weights	Yes	No
Released	Dec 2024	Aug 2025

Phi-4-mini-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.