LAYA vs Celeris-1 Decision
LAYA is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | LAYA | Celeris-1 Decision |
|---|---|---|
| Provider | Convai Innovations | Celeris |
| Decision Index score | 4.4 | — |
| Calibration error (ECE) | 0.140 | — |
| Median latency (p50) | 6 ms | — |
| Cost per 1,000 decisions | Free | $0.0080 |
| Parameters | 421M | — |
| 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 | Encoder classifier | Diffusion LM |
| License | Apache 2.0 | proprietary |
FAQ
Is LAYA 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, LAYA or Celeris-1 Decision?
No calibration difference between LAYA and Celeris-1 Decision is recorded yet.
Is LAYA or Celeris-1 Decision cheaper per 1,000 decisions?
LAYA is cheaper: about Free vs $0.0080 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.