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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, classify, route
choice, score, noul, classify, route
Architecture
gpt-6-luna
state-decider
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
OpenAI
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
—
76.8%
Calibration error
—
—
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 decisions-api and state-decider-1?
decisions-api is from OpenAI and state-decider-1 from meraGPT. Both are only available as a hosted API. Both answer choice, classify and route questions. Only state-decider-1 answers score and noul.
Which is more accurate, decisions-api or state-decider-1?
Only state-decider-1 publishes an accuracy figure (76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decisions-api or state-decider-1?
decisions-api: Hosted, price not published. state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run decisions-api or state-decider-1 locally?
Neither: both are only served as hosted APIs.
Evaluation suite
—
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
