Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.
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
bekko
telnyx-decision
Fine-tuned from
cross-encoder/ettin-reranker-400m-v1
—
License
Unassigned: the weights licence is not finalised (treated as non-commercial); training code MIT
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Telnyx
Input price
—
$0.035/MTok
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
5 ms
—
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 bekko-system-one and decision-flash?
bekko-system-one is from Yuichi Tateno (hotchpotch) and decision-flash from Telnyx. bekko-system-one 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. bekko-system-one is licensed other; decision-flash, proprietary.
Which is more accurate, bekko-system-one or decision-flash?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, bekko-system-one or decision-flash?
bekko-system-one: Free (open weights). decision-flash: $0.035 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run bekko-system-one or decision-flash locally?
bekko-system-one yes — systemone pull hotchpotch/bekko-system-one downloads its weights. The other is only served as a hosted API.
p95 latency
5.4 ms
—
Evaluation suite
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)