model · available

Decider 1

Give it a piece of state — a support conversation, an alert, an invoice, an agent trace — and a set of typed questions about it. Every question comes back as a probability distribution: yes or no, a choice between labels, or a score on a rubric. Twenty questions over one state are answered in a single pass, so asking more costs almost nothing. It speaks the System One schema, so the typesafe-sdk works against it by changing its base URL.

Try it in the browser

spec

model: decider-1
context: 4,096 tokens
max output: none — nothing is generated
input price: $0.04 / 1M tokens
output price: $0.00 / 1M tokens
repeatability: same input, same output
max request: 4,096 tokens, state and questions

built for

Routing and triage: which team, which queue, whether a human needs to see it.
Guardrails and checks inside agents: is this action safe, did this step succeed, should the run stop.
Scoring against a rubric — severity, urgency, risk — where you want the spread, not just a number.

not for

Open-ended answers. It picks between the options you give it and cannot write anything else.
Facts it would need to look up. It decides from the state you send and knows nothing beyond it.
Questions with more than ten options. Split a large label set into groups with a "none of these" option.

calling it

One state, every question.

curl https://meragpt.com/v1/systemone \
  -H "Authorization: Bearer $MERAGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "decider-1", "state": {...}, "questions": {"refund": {"type": "noul", "instructions": "..."}}}'

Send one state — any JSON — and as many typed questions as you need: noul for yes or no, choice for up to ten labels, score for an ordered rubric. Each comes back as a distribution: the probability of yes, a probability per label, or a probability per level with the expected score. All the questions are answered together, so adding one costs a few dozen tokens, and output is never billed. It speaks the System One schema: point the typesafe-sdk at https://meragpt.com with TYPESAFE_BASE_URL and your meraGPT key, and your existing code works. See the docs.

evaluation

How it measures up

Scored on the typed-decisions benchmark: four workflows — customer service, security incidents, invoice processing and agent traces — with twenty question schemas the model never saw in training, 400 cases and 2,000 decisions. Every answer is compared against a reference distribution, not only a single label.

accuracy	0.768	TypeSafe Jev 1.13.0 scores 0.727 on the same cases
KL from reference	0.096	lower is better; Jev is 1.442
Brier score	0.052	lower is better; Jev is 0.148
yes / no accuracy	0.840	Jev 0.775
choice accuracy	0.733	Jev 0.720
score accuracy	0.739	Jev 0.696; 98.4% within one rubric level

limits

What it does not do well.

The reference answers on this benchmark come from an ensemble of teacher models, so a score here measures agreement with that ensemble, not ground truth.
Every number comes from a single evaluation run.
Text state only — no images, audio or video — and at most ten options per choice question.

disclosure

Decider 1 is our own model, built and trained in house for this one task. The weights are proprietary and are not published. What is published is the measurement: every number on this page comes from a test run on data the model had never seen in training, not from a demo we liked. decider-1 always serves the current version of Decider 1: when an improved version ships, every request moves to it, and this page shows its numbers.

Calling it from your own code is in the API docs. Pricing and the credit model are on the homepage.