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.
The first System One model. Reads a state, answers typed Choice, Score and Noul questions in one call with calibrated probabilities, and generates no text. Closed weights, served by TypeSafe AI.
Decides
choice, score, noul, classify, extract, route
choice, score, noul, classify, route
Architecture
gliner2
jev
Fine-tuned from
fastino/gliner2-large-v1
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Fastino
TypeSafe AI
Input price
—
$0.042/MTok
Decision accuracy
60.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
38.3 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 gliner2-5-decide and jev?
gliner2-5-decide is from Fastino Labs and jev from TypeSafe AI. gliner2-5-decide has open weights and a hosted API; jev is only available as a hosted API. Both answer choice, score, noul, classify and route questions. Only gliner2-5-decide answers extract. gliner2-5-decide is licensed apache-2.0; jev, proprietary.
Which is more accurate, gliner2-5-decide or jev?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); jev does not, so there is no comparison to make without your own test.
Which is cheaper, gliner2-5-decide or jev?
gliner2-5-decide: Hosted, price not published, or free to self-host. jev: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or jev locally?
gliner2-5-decide yes — systemone pull fastino-labs/gliner2-5-decide downloads its weights. The other is only served as a hosted API.
