| Nova Micro 1.0 | Nemotron 3.5 Lightning | |
|---|---|---|
| Input, per 1M tokens | $0.035 | $0.08 |
| Output, per 1M tokens | $0.14 | $0.20 |
| Context window | 128K | 1M |
| Classification or routing (600 tokens in, 10 out), per 1,000 | $0.0224 | $0.05 |
| Chat reply (2,000 in, 400 out), per 1,000 | $0.126 | $0.24 |
| Retrieval-augmented answer (8,000 in, 500 out), per 1,000 | $0.35 | $0.74 |
| Confidence signal | no | yes |
| Tool calling | yes | yes |
| BANKING77, correct of 400 | not measured | 255 |
Which one should carry your traffic?
If Nova Micro 1.0 answers your requests as well as Nemotron 3.5 Lightning, moving that traffic saves 48% on chat-shaped requests. Averages cannot tell you whether it does for your requests. Nova Micro 1.0 does not expose a confidence signal through OpenRouter, so Gimbix would test it as a full replacement rather than a first answer.
Nova Micro 1.0 profile · Nemotron 3.5 Lightning profile · Measure it on your traffic