Celeris-1 Decision vs GPT-6 Luna Decisions (OpenAI Decisions API)
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 | GPT-6 Luna Decisions (OpenAI Decisions API) |
|---|---|---|
| Provider | Celeris | OpenAI |
| Decision Index score | — | — |
| Calibration error (ECE) | — | — |
| Median latency (p50) | — | — |
| Cost per 1,000 decisions | $0.0080 | $0.020 |
| Parameters | — | — |
| Open weights | No | No |
| 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 | Hosted API |
| License | proprietary | proprietary |
FAQ
Is Celeris-1 Decision or GPT-6 Luna Decisions (OpenAI Decisions API) 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 GPT-6 Luna Decisions (OpenAI Decisions API)?
No calibration difference between Celeris-1 Decision and GPT-6 Luna Decisions (OpenAI Decisions API) is recorded yet.
Is Celeris-1 Decision or GPT-6 Luna Decisions (OpenAI Decisions API) cheaper per 1,000 decisions?
Celeris-1 Decision is cheaper: about $0.0080 vs $0.020 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.