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.
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
noul, classify
choice, score, noul, classify, route
Architecture
span
state-decider
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
Respan
meraGPT
Input price
$0.020/MTok
$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 span-01 and state-decider-1?
span-01 is from Respan and state-decider-1 from meraGPT. Both are only available as a hosted API. Both answer noul and classify questions. Only state-decider-1 answers choice, score and route.
Which is more accurate, span-01 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); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, span-01 or state-decider-1?
span-01: $0.02 / $0 per 1M. state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run span-01 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
