Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
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.
Decides
choice, score, noul, classify, extract, route
choice, score, noul, rank, extract
Architecture
gliner2
solvi
Fine-tuned from
fastino/gliner2-large-v1
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Fastino
—
Input price
—
—
Decision accuracy
60.2%
59.4%
Calibration error
—
0.210
Valid action rate
—
—
Median latency
38.3 ms
—
p95 latency
—
—
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 gliner2-5-decide and solvi?
gliner2-5-decide is from Fastino Labs and solvi from solvi. gliner2-5-decide has open weights and a hosted API; solvi has open weights you can download and run. Both answer choice, score, noul and extract questions. Only gliner2-5-decide answers classify and route. Only solvi answers rank. gliner2-5-decide is the smaller model, at 340M parameters to 396M.
Which is more accurate, gliner2-5-decide or solvi?
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gliner2-5-decide or solvi?
gliner2-5-decide: Hosted, price not published, or free to self-host. solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or solvi locally?
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull solvi-ai/solvi download the weights.
Evaluation suite
Fastino fast-decisions suite (17 datasets)
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
