Home / Compare / Gemma 4 31B vs gpt-oss-120b

Gemma 4 31B vs gpt-oss-120b

For a typical chat reply (2,000 tokens in, 400 out), gpt-oss-120b costs 1.7× as much as Gemma 4 31B: $0.54 against $0.316 per 1,000 requests at list price on 2026-09-28.

Gemma 4 31Bgpt-oss-120b
Input, per 1M tokens$0.09$0.15
Output, per 1M tokens$0.34$0.60
Context window262K131K
Classification or routing (600 tokens in, 10 out), per 1,000$0.0574$0.096
Chat reply (2,000 in, 400 out), per 1,000$0.316$0.54
Retrieval-augmented answer (8,000 in, 500 out), per 1,000$0.89$1.50
Confidence signalyesyes
Tool callingyesyes
BANKING77, correct of 400304329

Which one should carry your traffic?

If Gemma 4 31B answers your requests as well as gpt-oss-120b, moving that traffic saves 41% on chat-shaped requests. Averages cannot tell you whether it does for your requests. Gemma 4 31B exposes a confidence signal, so Gimbix can let it answer first and hand unsure cases to gpt-oss-120b.

Gemma 4 31B profile · gpt-oss-120b profile · Measure it on your traffic