Home / Compare / DeepSeek V4 Flash 0731 vs gpt-oss-120b

DeepSeek V4 Flash 0731 vs gpt-oss-120b

For a typical chat reply (2,000 tokens in, 400 out), gpt-oss-120b costs 3.2× as much as DeepSeek V4 Flash 0731: $0.54 against $0.17 per 1,000 requests at list price on 2026-09-28.

DeepSeek V4 Flash 0731gpt-oss-120b
Input, per 1M tokens$0.021$0.15
Output, per 1M tokens$0.32$0.60
Context window1.31M131K
Classification or routing (600 tokens in, 10 out), per 1,000$0.0158$0.096
Chat reply (2,000 in, 400 out), per 1,000$0.17$0.54
Retrieval-augmented answer (8,000 in, 500 out), per 1,000$0.328$1.50
Confidence signalyesyes
Tool callingyesyes
BANKING77, correct of 400298329

Which one should carry your traffic?

If DeepSeek V4 Flash 0731 answers your requests as well as gpt-oss-120b, moving that traffic saves 69% on chat-shaped requests. Averages cannot tell you whether it does for your requests. DeepSeek V4 Flash 0731 exposes a confidence signal, so Gimbix can let it answer first and hand unsure cases to gpt-oss-120b.

DeepSeek V4 Flash 0731 profile · gpt-oss-120b profile · Measure it on your traffic