A typed-decision layer for Google's DiffusionGemma, from David Villalón at Maisa AI. It compiles a request into a small answer canvas, runs one denoising read on patched vLLM and reads the probabilities of the allowed labels, for text, images and images offered as options.
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.
Decides
choice, score, noul
choice, score, noul, classify, extract, route
Architecture
djev
gliner2
Fine-tuned from
google/diffusiongemma-26b-a4b-it
fastino/gliner2-large-v1
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights + hosted API
Hosted by
Maisa
Fastino
Input price
$0.035/MTok
—
Decision accuracy
—
60.2%
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 djev and gliner2-5-decide?
djev is from Maisa and gliner2-5-decide from Fastino Labs. Both have open weights and a hosted API. Both answer choice, score and noul questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 26B.
Which is more accurate, djev or gliner2-5-decide?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); djev does not, so there is no comparison to make without your own test.
Which is cheaper, djev or gliner2-5-decide?
djev: $0.035 / $0 per 1M, or free to self-host. gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run djev or gliner2-5-decide locally?
Yes, both: systemone pull maisa/djev and systemone pull fastino-labs/gliner2-5-decide download the weights.
