Is Google Gemma 3 27B Instruct or gpt-oss-120b cheaper?

Google Gemma 3 27B Instruct is cheaper on output tokens ($0.20 vs $0.60 per 1M).

Which has the larger context window, Google Gemma 3 27B Instruct or gpt-oss-120b?

Google Gemma 3 27B Instruct has the larger context window (203K tokens).

Google Gemma 3 27B Instruct vs gpt-oss-120b

Google Gemma 3 27B Instruct is cheaper on output tokens, while Google Gemma 3 27B Instruct offers a larger context window. Choose Google Gemma 3 27B Instruct or gpt-oss-120b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Google Gemma 3 27B Instruct	gpt-oss-120b
Provider	Amazon Bedrock	Amazon Bedrock
Input / 1M tokens	$0.12	$0.15
Output / 1M tokens	$0.20	$0.60
Context window	203K	128K
Parameters	—	117B
Open weights	Yes	No
Released	Jul 2025	Aug 2025

Google Gemma 3 27B 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.