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.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
state-decider
trio-spark
Fine-tuned from
—
—
License
proprietary
proprietary
Availability
Hosted API
Hosted API
Hosted by
meraGPT
MachineFi
Input price
$0.030/MTok
$0.042/MTok
Decision accuracy
76.8%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
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 state-decider-1 and trio-spark-v1?
state-decider-1 is from meraGPT and trio-spark-v1 from MachineFi. Both are only available as a hosted API. Both answer choice, classify and route questions. Only state-decider-1 answers score and noul. state-decider-1 reads up to 4K tokens of state, against 1K tokens for trio-spark-v1.
Which is more accurate, state-decider-1 or trio-spark-v1?
Only state-decider-1 publishes an accuracy figure (76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, state-decider-1 or trio-spark-v1?
state-decider-1: $0.03 / $0 per 1M. trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run state-decider-1 or trio-spark-v1 locally?
