Typed decisions from Google's frozen Gemma-4-12B-it, with no fine-tuning. A small shim over unmodified vLLM letters the options, reads the model's own probability for each letter at one answer position and applies one calibration temperature; one output token per decision.
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
choice, classify, route
Architecture
cygnet
gpt-6-luna
Fine-tuned from
google/gemma-4-12b-it
—
License
mit
proprietary
Availability
Open weights
Hosted API
Hosted by
—
OpenAI
Input price
—
—
Decision accuracy
87.9%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
—
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 cygnet and decisions-api?
cygnet is from Blockbrain Labs and decisions-api from OpenAI. cygnet has open weights you can download and run; decisions-api is only available as a hosted API. Both answer choice questions. Only cygnet answers score and noul. Only decisions-api answers classify and route. cygnet is licensed mit; decisions-api, proprietary.
Which is more accurate, cygnet or decisions-api?
Only cygnet publishes an accuracy figure (87.9% on JevBench public set (231 items), JevBench CLI); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, cygnet or decisions-api?
cygnet: Free (open weights). decisions-api: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run cygnet or decisions-api locally?
cygnet yes — systemone pull blockbrain-labs/cygnet downloads its weights. The other is only served as a hosted API.
