A 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
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, rank, extract
choice, score, noul, classify, route
Architecture
solvi
strom
Fine-tuned from
answerdotai/modernbert-large
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Uprelic
Input price
—
$0.042/MTok
Decision accuracy
59.4%
87.0%
Calibration error
0.210
0.033
Valid action rate
—
—
Median latency
—
136 ms
p95 latency
—
—
Evaluation suite
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.
Questions
What is the difference between solvi and strom?
solvi is from solvi and strom from Uprelic. solvi has open weights you can download and run; strom is only available as a hosted API. Both answer choice, score and noul questions. Only solvi answers rank and extract. Only strom answers classify and route. strom reads up to 32K tokens of state, against 512 tokens for solvi. solvi is licensed apache-2.0; strom, proprietary.
Which is more accurate, solvi or strom?
They report on different suites — solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot, 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.
Which is cheaper, solvi or strom?
solvi: Free (open weights). strom: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run solvi or strom locally?
solvi yes — systemone pull solvi-ai/solvi downloads its weights. The other is only served as a hosted API.
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
JevBench public set (231 items), the maker's production run of Strom 1.0.7 on 1 Oct 2026 (Open-Jev harness format)
