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 Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, extract, route
choice, route, classify
Architecture
gliner2
trio-spark
Fine-tuned from
fastino/gliner2-large-v1
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Fastino
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
60.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
38.3 ms
—
p95 latency
—
—
Evaluation suite
Fastino fast-decisions suite (17 datasets)
—
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 trio-spark-v1?
gliner2-5-decide is from Fastino Labs and trio-spark-v1 from MachineFi. gliner2-5-decide has open weights and a hosted API; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only gliner2-5-decide answers score, noul and extract. gliner2-5-decide is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, gliner2-5-decide or trio-spark-v1?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, gliner2-5-decide or trio-spark-v1?
gliner2-5-decide: Hosted, price not published, or free to self-host. trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or trio-spark-v1 locally?
gliner2-5-decide yes — systemone pull fastino-labs/gliner2-5-decide downloads its weights. The other is only served as a hosted API.
