Is Microsoft: Phi 4 or OpenAI: gpt-oss-120b cheaper?

Microsoft: Phi 4 is cheaper on output tokens ($0.14 vs $0.19 per 1M).

Which has the larger context window, Microsoft: Phi 4 or OpenAI: gpt-oss-120b?

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

Microsoft: Phi 4 vs OpenAI: gpt-oss-120b

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

Spec	Microsoft: Phi 4	OpenAI: gpt-oss-120b
Provider	Kilo Gateway	Kilo Gateway
Input / 1M tokens	$0.06	$0.04
Output / 1M tokens	$0.14	$0.19
Context window	16K	131K
Parameters	—	117B
Open weights	Yes	Yes
Released	Dec 2024	Aug 2025

Microsoft: Phi 4 details →OpenAI: gpt-oss-120b details →

FAQ

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