Perplexity Decider v1.1 (27B) vs Celeris-1 Decision
Perplexity Decider v1.1 (27B) is cheaper per 1,000 decisions. Choose on whichever of accuracy, calibration and cost matters most for your decisions.
| Spec | Perplexity Decider v1.1 (27B) | Celeris-1 Decision |
|---|---|---|
| Provider | Perplexity | Celeris |
| Decision Index score | 62.8 | — |
| Calibration error (ECE) | 0.071 | — |
| Median latency (p50) | 104 ms | — |
| Cost per 1,000 decisions | $0.0040 | $0.0080 |
| Parameters | 28B | — |
| 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 Perplexity Decider v1.1 (27B) 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, Perplexity Decider v1.1 (27B) or Celeris-1 Decision?
No calibration difference between Perplexity Decider v1.1 (27B) and Celeris-1 Decision is recorded yet.
Is Perplexity Decider v1.1 (27B) or Celeris-1 Decision cheaper per 1,000 decisions?
Perplexity Decider v1.1 (27B) is cheaper: about $0.0040 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.