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.
Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
Decides
choice, score, noul, classify, extract, route
noul, classify
Architecture
gliner2
span
Fine-tuned from
fastino/gliner2-large-v1
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Fastino
Respan
Input price
—
$0.020/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 span-01?
gliner2-5-decide is from Fastino Labs and span-01 from Respan. gliner2-5-decide has open weights and a hosted API; span-01 is only available as a hosted API. Both answer noul and classify questions. Only gliner2-5-decide answers choice, score, extract and route. gliner2-5-decide is licensed apache-2.0; span-01, proprietary.
Which is more accurate, gliner2-5-decide or span-01?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, gliner2-5-decide or span-01?
gliner2-5-decide: Hosted, price not published, or free to self-host. span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or span-01 locally?
gliner2-5-decide yes — systemone pull fastino-labs/gliner2-5-decide downloads its weights. The other is only served as a hosted API.
