Caliber Flex 1B by OnePass. Decision-only model, exactly 1,000,000,000 parameters.
StartLux's decision family in six sizes, 0.8B to a 35B-A3B mixture of experts. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server. Text, JSON or images, up to 256K tokens.
Decides
choice, noul, score
choice, score, noul
Architecture
llm
startlux-decision
Fine-tuned from
qwen/qwen3.5-0.8b-base
—
License
caliber-flex-non-commercial-1.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
26 ms
p95 latency
—
—
Evaluation suite
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 caliber-flex-1b and startlux-decision?
caliber-flex-1b is from onepass and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice, noul and score questions. caliber-flex-1b is licensed other; startlux-decision, cc-by-nc-4.0.
Which is more accurate, caliber-flex-1b or startlux-decision?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); caliber-flex-1b does not, so there is no comparison to make without your own test.
Which is cheaper, caliber-flex-1b or startlux-decision?
caliber-flex-1b: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run caliber-flex-1b or startlux-decision locally?
Yes, both: systemone pull onepass/caliber-flex-1b and systemone pull startlux/startlux-decision download the weights.
—
JevBench public set (231 items; 204 correct), maker's run
