| Ministral 3 8B 2512 | Nemotron 3 Ultra | |
|---|---|---|
| Input, per 1M tokens | $0.15 | $0.60 |
| Output, per 1M tokens | $0.15 | $2.40 |
| Context window | 262K | 262K |
| Classification or routing (600 tokens in, 10 out), per 1,000 | $0.0915 | $0.384 |
| Chat reply (2,000 in, 400 out), per 1,000 | $0.36 | $2.16 |
| Retrieval-augmented answer (8,000 in, 500 out), per 1,000 | $1.27 | $6.00 |
| Confidence signal | no | no |
| Tool calling | yes | yes |
Which one should carry your traffic?
If Ministral 3 8B 2512 answers your requests as well as Nemotron 3 Ultra, moving that traffic saves 83% on chat-shaped requests. Averages cannot tell you whether it does for your requests. Ministral 3 8B 2512 does not expose a confidence signal through OpenRouter, so Gimbix would test it as a full replacement rather than a first answer.
Ministral 3 8B 2512 profile · Nemotron 3 Ultra profile · Measure it on your traffic