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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul, classify, extract, route
choice, score, noul, classify, route
Architecture
gliner2
state-decider
Fine-tuned from
fastino/gliner2-large-v1
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Fastino
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
60.2%
76.8%
Calibration error
—
—
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 state-decider-1?
gliner2-5-decide is from Fastino Labs and state-decider-1 from meraGPT. gliner2-5-decide has open weights and a hosted API; state-decider-1 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; state-decider-1, proprietary.
Which is more accurate, gliner2-5-decide or state-decider-1?
They report on different suites — gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets), state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, gliner2-5-decide or state-decider-1?
gliner2-5-decide: Hosted, price not published, or free to self-host. state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or state-decider-1 locally?
gliner2-5-decide yes — systemone pull fastino-labs/gliner2-5-decide downloads its weights. The other is only served as a hosted API.
Evaluation suite
Fastino fast-decisions suite (17 datasets)
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
