An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
Telnyx's hosted decision models, in beta on Telnyx Inference. One request carries shared state and up to 64 typed questions (choice, yes/no noul, ordered score) and returns a probability per option, with no generated text, on a TypeSafe-compatible /v1/systemone route.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
ajev
telnyx-decision
Fine-tuned from
google/gemma-4-26b-a4b-it
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Telnyx
Input price
—
$0.035/MTok
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
49 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 ajev and decision-flash?
ajev is from Andy Zhang and decision-flash from Telnyx. ajev has open weights you can download and run; decision-flash is only available as a hosted API. Both answer choice, score and noul questions. Only decision-flash answers classify and route. ajev is licensed apache-2.0; decision-flash, proprietary.
Which is more accurate, ajev or decision-flash?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, ajev or decision-flash?
ajev: Free (open weights). decision-flash: $0.035 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run ajev or decision-flash locally?
ajev yes — systemone pull andy-zhang/ajev downloads its weights. The other is only served as a hosted API.
