Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.
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, noul, score
choice, score, noul, classify, route
Architecture
canopy-jev
telnyx-decision
Fine-tuned from
qwen/qwen3.8-27b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Telnyx
Input price
—
$0.035/MTok
Decision accuracy
87.4%
—
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 canopy-jev and decision-flash?
canopy-jev is from Ruoxi Qiu and decision-flash from Telnyx. canopy-jev has open weights you can download and run; decision-flash is only available as a hosted API. Both answer choice, noul and score questions. Only decision-flash answers classify and route. canopy-jev is licensed apache-2.0; decision-flash, proprietary.
Which is more accurate, canopy-jev or decision-flash?
Only canopy-jev publishes an accuracy figure (87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer); decision-flash does not, so there is no comparison to make without your own test.
Which is cheaper, canopy-jev or decision-flash?
canopy-jev: Free (open weights). decision-flash: $0.035 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run canopy-jev or decision-flash locally?
canopy-jev yes — systemone pull camellia86/canopy-jev downloads its weights. The other is only served as a hosted API.
—
Evaluation suite
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
