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.
FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.
Decides
choice, classify, route
choice, score, noul
Architecture
gpt-6-luna
this-that
Fine-tuned from
—
mapika/decider
License
proprietary
mit
Availability
Hosted API
Open weights
Hosted by
OpenAI
—
Input price
—
—
Decision accuracy
—
87.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
31.4 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 decisions-api and this-that-model?
decisions-api is from OpenAI and this-that-model from FLock.io. decisions-api is only available as a hosted API; this-that-model has open weights you can download and run. Both answer choice questions. Only decisions-api answers classify and route. Only this-that-model answers score and noul. decisions-api is licensed proprietary; this-that-model, mit.
Which is more accurate, decisions-api or this-that-model?
Only this-that-model publishes an accuracy figure (87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark)); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decisions-api or this-that-model?
decisions-api: Hosted, price not published. this-that-model: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decisions-api or this-that-model locally?
this-that-model yes — systemone pull flock-io/this-that-model downloads its weights. The other is only served as a hosted API.
