Kev 4B r10 vs Celeris-1 Decision
Celeris-1 Decision is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Kev 4B r10 | Celeris-1 Decision |
|---|---|---|
| Provider | Jared Palmer | Celeris |
| Decision Index score | 39.5 | — |
| Calibration error (ECE) | 0.032 | — |
| Median latency (p50) | 59 ms | — |
| Cost per 1,000 decisions | $0.0084 | $0.0080 |
| Parameters | 5B | — |
| Open weights | Yes | No |
| Question types | Choice (one of N options), Score (ordered rubric), Yes / no | Choice (one of N options), Score (ordered rubric), Yes / no |
| Mechanism | Decoder LM with a decision readout | Diffusion LM |
| License | apache-2.0 | proprietary |
FAQ
Is Kev 4B r10 or Celeris-1 Decision 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, Kev 4B r10 or Celeris-1 Decision?
No calibration difference between Kev 4B r10 and Celeris-1 Decision is recorded yet.
Is Kev 4B r10 or Celeris-1 Decision 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.