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.
OpenAI's decision endpoint, announced at DevDay 2026. It focuses GPT-6 Luna on developer-defined questions that have a finite set of predefined answers, with text or image context, for classification, routing and an agent's next action.
Decides
choice, score, noul, classify, route
choice, classify, route
Architecture
bosun
gpt-6-luna
Fine-tuned from
qwen/qwen3-1.7b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
OpenAI
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 decisions-api?
bosun is from Hanno Labs and decisions-api from OpenAI. bosun has open weights you can download and run; decisions-api is only available as a hosted API. Both answer choice, classify and route questions. Only bosun answers score and noul. bosun is licensed apache-2.0; decisions-api, proprietary.
Which is more accurate, bosun or decisions-api?
Only bosun publishes an accuracy figure (84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, bosun or decisions-api?
bosun: Free (open weights). decisions-api: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run bosun or decisions-api 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)
