Berget AI's System One model for gating agent commands: a LoRA adapter and a fine-tuned joint schema head on Cloudflare's Clef-Flash that answer noul, choice and score questions over a state in one forward pass. Trained on Swedish and English operations decisions.
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
noul, choice, score
choice, score, noul, classify, route
Architecture
clef
telnyx-decision
Fine-tuned from
cloudflare/clef-flash
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Telnyx
Input price
—
$0.035/MTok
Decision accuracy
97.0%
—
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 bev and decision-flash?
bev is from Berget AI and decision-flash from Telnyx. bev has open weights you can download and run; decision-flash is only available as a hosted API. Both answer noul, choice and score questions. Only decision-flash answers classify and route. bev is licensed apache-2.0; decision-flash, proprietary.
Which is more accurate, bev or decision-flash?
Only bev publishes an accuracy figure (97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)); decision-flash does not, so there is no comparison to make without your own test.
Which is cheaper, bev or decision-flash?
bev: Free (open weights). decision-flash: $0.035 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run bev or decision-flash locally?
bev yes — systemone pull berget-ai/bev downloads its weights. The other is only served as a hosted API.
—
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
