Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
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, score, noul, classify, route
choice, score, noul, classify, route
Architecture
mira
state-decider
Fine-tuned from
jhu-clsp/mmbert-small
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
74.5%
76.8%
Calibration error
0.025
—
Valid action rate
100.0%
—
Median latency
30 ms
—
p95 latency
43 ms
—
Evaluation suite
s1-decision-bench
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
Latest version
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 mira and state-decider-1?
mira is from SAGEA and state-decider-1 from meraGPT. mira has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. mira is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, mira or state-decider-1?
They report on different suites — mira 74.5% on s1-decision-bench, state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, mira or state-decider-1?
mira: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run mira or state-decider-1 locally?
mira yes — systemone pull sagea/mira downloads its weights. The other is only served as a hosted API.
