The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
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
decision
state-decider
Fine-tuned from
qwen/qwen3.5-9b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
77.4%
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 decision and state-decider-1?
decision is from vLLM Semantic Router and state-decider-1 from meraGPT. decision 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. decision reads up to 16K tokens of state, against 4K tokens for state-decider-1. decision is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, decision or state-decider-1?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), 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, decision or state-decider-1?
decision: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run decision or state-decider-1 locally?
decision yes — systemone pull vllm-semantic-router/decision downloads its weights. The other is only served as a hosted API.
