Loading comparison…
HEAD TO HEAD
SAGEA: mira and Uprelic: strom, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | sagea/mira | uprelic/strom |
|---|---|---|
| Summary | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. | Uprelic's hosted decision API, run on GPUs in Paris. Answers noul, choice and score questions about text, JSON and up to 8 images, with a probability for every option and no generated text, on the same request shape as Jev. No weights; base model and size not disclosed. |
| Decides | choice, score, noul, classify, route | choice, score, noul, classify, route |
| Architecture | mira | strom |
| Fine-tuned from | jhu-clsp/mmbert-small | — |
| License | apache-2.0 | proprietary |
| Availability | Open weights | Hosted API |
| Hosted by | — | Uprelic |
| Input price | — | $0.042/MTok |
| Decision accuracy | 61.3% | 87.0% |
| Calibration error | 0.083 | 0.033 |
| Valid action rate | 100.0% | — |
| Median latency | 30 ms | 136 ms |
| p95 latency | 43 ms | — |
| Evaluation suite | s1-decision-bench | JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format) |
| Latest version | 0.1.5 |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
mira is from SAGEA and strom from Uprelic. mira has open weights you can download and run; strom is only available as a hosted API. Both answer choice, score, noul, classify and route questions. mira is licensed apache-2.0; strom, proprietary.
They report on different suites — mira 61.3% on s1-decision-bench, strom 87.0% on JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format) — so the numbers do not rank them. Test both on your own labelled examples.
mira: Free (open weights). strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, mira answers in about 30 ms at the median and strom in about 136 ms — measured on different hardware, so treat it as a rough guide.
mira yes — systemone pull sagea/mira downloads its weights. The other is only served as a hosted API.
| 2026.09 |
| Variants | — | — |
|---|
| Size of latest version | 568.8 MB | — |
|---|
| Files | 12 | 0 |
|---|
| Downloads | 112 | 0 |
|---|
| Stars | 1 | 0 |
|---|
| Tags | routing, nepali, nepal, calibration, cpu | system-one, hosted, vision, eu |
|---|
| Updated | Oct 6, 2026 | Oct 7, 2026 |
|---|