All models

COMPARE

Put models side by side.

What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.

Propertyfastino-labs/gliner2-5-decide
SummaryFastino'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.
Decideschoice, score, noul, classify, extract, route
Architecturegliner2
Fine-tuned fromfastino/gliner2-large-v1
Licenseapache-2.0
AvailabilityOpen weights + hosted API
Hosted byFastino
Input price—
Decision accuracy60.2%
Calibration error—
Valid action rate—
Median latency38.3 ms
p95 latency—
Evaluation suiteFastino fast-decisions suite (17 datasets)
Latest version2026.09.25
Variantsencoder_config
Size of latest version1.8 GB
Files6
Downloads0
Stars0
Tagssystem-one, encoder, deberta, extraction, gliner, 340m
UpdatedSep 25, 2026