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.
Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
Decides
choice, classify, route
noul, classify
Architecture
gpt-6-luna
span
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
OpenAI
Respan
Input price
—
$0.020/MTok
Decision accuracy
—
—
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 span-01?
decisions-api is from OpenAI and span-01 from Respan. Both are only available as a hosted API. Both answer classify questions. Only decisions-api answers choice and route. Only span-01 answers noul.
Which is more accurate, decisions-api or span-01?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, decisions-api or span-01?
decisions-api: Hosted, price not published. span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
