Home / Compare / Gemini 3.1 Pro Preview vs gpt-oss-20b

Gemini 3.1 Pro Preview vs gpt-oss-20b

For a typical chat reply (2,000 tokens in, 400 out), Gemini 3.1 Pro Preview costs 122× as much as gpt-oss-20b: $8.80 against $0.072 per 1,000 requests at list price on 2026-09-28.

Gemini 3.1 Pro Previewgpt-oss-20b
Input, per 1M tokens$2.00$0.018
Output, per 1M tokens$12.00$0.09
Context window1.05M131K
Classification or routing (600 tokens in, 10 out), per 1,000$1.32$0.0117
Chat reply (2,000 in, 400 out), per 1,000$8.80$0.072
Retrieval-augmented answer (8,000 in, 500 out), per 1,000$22.00$0.189
Confidence signalnoyes
Tool callingyesyes
BANKING77, correct of 400not measured313

Which one should carry your traffic?

If gpt-oss-20b answers your requests as well as Gemini 3.1 Pro Preview, moving that traffic saves 99% on chat-shaped requests. Averages cannot tell you whether it does for your requests. gpt-oss-20b exposes a confidence signal, so Gimbix can let it answer first and hand unsure cases to Gemini 3.1 Pro Preview.

Gemini 3.1 Pro Preview profile · gpt-oss-20b profile · Measure it on your traffic