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.
An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
Decides
choice, classify, route
choice, score, noul, classify
Architecture
gpt-6-luna
open-jev
Fine-tuned from
—
microsoft/deberta-v3-large
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
OpenAI
—
Input price
—
—
Decision accuracy
—
85.4%
Calibration error
—
0.022
Valid action rate
—
—
Median latency
—
28 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 open-jev-deberta-v3-large?
decisions-api is from OpenAI and open-jev-deberta-v3-large from Kotoba Labs. decisions-api is only available as a hosted API; open-jev-deberta-v3-large has open weights you can download and run. Both answer choice and classify questions. Only decisions-api answers route. Only open-jev-deberta-v3-large answers score and noul. decisions-api is licensed proprietary; open-jev-deberta-v3-large, apache-2.0.
Which is more accurate, decisions-api or open-jev-deberta-v3-large?
Only open-jev-deberta-v3-large publishes an accuracy figure (85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decisions-api or open-jev-deberta-v3-large?
decisions-api: Hosted, price not published. open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decisions-api or open-jev-deberta-v3-large locally?
open-jev-deberta-v3-large yes — systemone pull kotoba-labs/open-jev-deberta-v3-large downloads its weights. The other is only served as a hosted API.
Evaluation suite
—
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
