Celeris-1 Decision vs Kev 4B r10
Celeris-1 Decision is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Celeris-1 Decision | Kev 4B r10 |
|---|---|---|
| Provider | Celeris | Jared Palmer |
| Decision Index score | — | 39.5 |
| Calibration error (ECE) | — | 0.032 |
| Median latency (p50) | — | 59 ms |
| Cost per 1,000 decisions | $0.0080 | $0.0084 |
| Parameters | — | 5B |
| Open weights | No | Yes |
| Question types | Choice (one of N options), Score (ordered rubric), Yes / no | Choice (one of N options), Score (ordered rubric), Yes / no |
| Mechanism | Diffusion LM | Decoder LM with a decision readout |
| License | proprietary | apache-2.0 |
FAQ
Is Celeris-1 Decision or Kev 4B r10 more accurate?
At least one of the two has no Jev Decision Index score yet, so their accuracy cannot be compared here.
Which is better calibrated, Celeris-1 Decision or Kev 4B r10?
No calibration difference between Celeris-1 Decision and Kev 4B r10 is recorded yet.
Is Celeris-1 Decision or Kev 4B r10 cheaper per 1,000 decisions?
Celeris-1 Decision is cheaper: about $0.0080 vs $0.0084 per 1,000 decisions at 200 input tokens each.
Cost per 1,000 decisions assumes 200 input tokens per decision. Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.