| DeepSeek V4 Flash 0731 | gpt-oss-20b | |
|---|---|---|
| Input, per 1M tokens | $0.021 | $0.018 |
| Output, per 1M tokens | $0.32 | $0.09 |
| Context window | 1.31M | 131K |
| Classification or routing (600 tokens in, 10 out), per 1,000 | $0.0158 | $0.0117 |
| Chat reply (2,000 in, 400 out), per 1,000 | $0.17 | $0.072 |
| Retrieval-augmented answer (8,000 in, 500 out), per 1,000 | $0.328 | $0.189 |
| Confidence signal | yes | yes |
| Tool calling | yes | yes |
| BANKING77, correct of 400 | 298 | 313 |
Which one should carry your traffic?
If gpt-oss-20b answers your requests as well as DeepSeek V4 Flash 0731, moving that traffic saves 58% 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 DeepSeek V4 Flash 0731.
DeepSeek V4 Flash 0731 profile · gpt-oss-20b profile · Measure it on your traffic