Hanno Labs' small calibrated decision model. A LoRA on Qwen3-1.7B plus trained decision-token embeddings with stable slots, returning the full distribution over up to 255 caller-defined choices and a null slot for Choice, Score and Noul questions.
Liquid AI's first decision model, served only through the Liquid API. Returns Choice, Score and Noul answers with probability distributions and zero output tokens, on the /v1/systemone request shape used by TypeSafe's SDK.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
d1
Fine-tuned from
qwen/qwen3-1.7b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Liquid AI
Input price
—
—
Decision accuracy
84.9%
—
Calibration error
0.050
—
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 bosun and d1?
bosun is from Hanno Labs and d1 from Liquid AI. bosun has open weights you can download and run; d1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. bosun is licensed apache-2.0; d1, proprietary.
Which is more accurate, bosun or d1?
Only bosun publishes an accuracy figure (84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)); d1 does not, so there is no comparison to make without your own test.
Which is cheaper, bosun or d1?
bosun: Free (open weights). d1: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run bosun or d1 locally?
bosun yes — systemone pull hanno-labs/bosun downloads its weights. The other is only served as a hosted API.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
