Liquid AI's first decision model, served only through the Liquid API. Returns Choice, Score and Noul answers with probability distributions and zero output tokens, on the /v1/systemone request shape used by TypeSafe's SDK.
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.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
d1
djev
Fine-tuned from
—
google/diffusiongemma-26b-a4b-it
License
proprietary
apache-2.0
Availability
Hosted API
Open weights + hosted API
Hosted by
Liquid AI
Maisa
Input price
—
$0.035/MTok
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 d1 and djev?
d1 is from Liquid AI and djev from Maisa. d1 is only available as a hosted API; djev has open weights and a hosted API. Both answer choice, score and noul questions. Only d1 answers classify and route. d1 is licensed proprietary; djev, apache-2.0.
Which is more accurate, d1 or djev?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, d1 or djev?
d1: Hosted, price not published. djev: $0.035 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run d1 or djev locally?
djev yes — systemone pull maisa/djev downloads its weights. The other is only served as a hosted API.
