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.
Standard Thinking's decision model. Ministral 3 8B with a merged LoRA, served through stock SGLang and an open jev-adapter that exposes /v1/systemone and scores the supplied options in one forward pass with per-type temperatures.
Decides
choice, classify, route
choice, score, noul, classify, route
Architecture
gpt-6-luna
standard-one
Fine-tuned from
—
mistralai/ministral-3-8b-instruct-2512-bf16
License
proprietary
apache-2.0
Availability
Hosted API
Open weights + hosted API
Hosted by
OpenAI
Standard Thinking
Input price
—
—
Decision accuracy
—
71.1%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
25.8 ms
p95 latency
—
41.9 ms
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 standard-one?
decisions-api is from OpenAI and standard-one from Standard Thinking. decisions-api is only available as a hosted API; standard-one has open weights and a hosted API. Both answer choice, classify and route questions. Only standard-one answers score and noul. decisions-api is licensed proprietary; standard-one, apache-2.0.
Which is more accurate, decisions-api or standard-one?
Only standard-one publishes an accuracy figure (71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2)); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decisions-api or standard-one?
decisions-api: Hosted, price not published. standard-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run decisions-api or standard-one locally?
standard-one yes — systemone pull standard-thinking/standard-one downloads its weights. The other is only served as a hosted API.
