| DeepSeek V4.1 Flash | GPT-6 Luna | |
|---|---|---|
| Input, per 1M tokens | $0.0295 | $0.10 |
| Output, per 1M tokens | $0.60 | $0.50 |
| Context window | 1.05M | 1.05M |
| Classification or routing (600 tokens in, 10 out), per 1,000 | $0.0237 | $0.065 |
| Chat reply (2,000 in, 400 out), per 1,000 | $0.299 | $0.40 |
| Retrieval-augmented answer (8,000 in, 500 out), per 1,000 | $0.536 | $1.05 |
| Confidence signal | yes | no |
| Tool calling | yes | yes |
| BANKING77, correct of 400 | 316 | 320 |
Which one should carry your traffic?
If DeepSeek V4.1 Flash answers your requests as well as GPT-6 Luna, moving that traffic saves 25% on chat-shaped requests. Averages cannot tell you whether it does for your requests. DeepSeek V4.1 Flash exposes a confidence signal, so Gimbix can let it answer first and hand unsure cases to GPT-6 Luna.
DeepSeek V4.1 Flash profile · GPT-6 Luna profile · Measure it on your traffic