Home / Compare / GPT-5.4 Mini vs gpt-oss-120b

GPT-5.4 Mini vs gpt-oss-120b

For a typical chat reply (2,000 tokens in, 400 out), GPT-5.4 Mini costs 6.1× as much as gpt-oss-120b: $3.30 against $0.54 per 1,000 requests at list price on 2026-09-28.

GPT-5.4 Minigpt-oss-120b
Input, per 1M tokens$0.75$0.15
Output, per 1M tokens$4.50$0.60
Context window400K131K
Classification or routing (600 tokens in, 10 out), per 1,000$0.495$0.096
Chat reply (2,000 in, 400 out), per 1,000$3.30$0.54
Retrieval-augmented answer (8,000 in, 500 out), per 1,000$8.25$1.50
Confidence signalnoyes
Tool callingyesyes
BANKING77, correct of 400not measured329

Which one should carry your traffic?

If gpt-oss-120b answers your requests as well as GPT-5.4 Mini, moving that traffic saves 84% on chat-shaped requests. Averages cannot tell you whether it does for your requests. gpt-oss-120b exposes a confidence signal, so Gimbix can let it answer first and hand unsure cases to GPT-5.4 Mini.

GPT-5.4 Mini profile · gpt-oss-120b profile · Measure it on your traffic