Is Google: Gemma 3n 4B or OpenAI: gpt-oss-120b cheaper?

Google: Gemma 3n 4B is cheaper on output tokens ($0.04 vs $0.19 per 1M).

Which has the larger context window, Google: Gemma 3n 4B or OpenAI: gpt-oss-120b?

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

Google: Gemma 3n 4B vs OpenAI: gpt-oss-120b

Google: Gemma 3n 4B is cheaper on output tokens, while OpenAI: gpt-oss-120b offers a larger context window. Choose Google: Gemma 3n 4B or OpenAI: gpt-oss-120b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Google: Gemma 3n 4B	OpenAI: gpt-oss-120b
Provider	Kilo Gateway	Kilo Gateway
Input / 1M tokens	$0.02	$0.04
Output / 1M tokens	$0.04	$0.19
Context window	33K	131K
Parameters	—	117B
Open weights	Yes	Yes
Released	May 2025	Aug 2025

Google: Gemma 3n 4B 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.