Decider 1

Decider 1 is meraGPT’s System One model, announced on 22 September 2026. You send a state, which can be any JSON, and a set of typed questions. It answers every question in one call and generates no text. meraGPT, run by Singapore-registered Okyasoft Pte Ltd, serves it only through its own API, and the weights are proprietary. Decider 1 is not related to Mapika’s decider, an open model with a similar name.

The request schema is the same as Jev’s. A Noul returns the probability of yes. A Choice takes 2 to 10 labels and returns a probability per label plus the most likely one. A Score takes 2 to 10 levels and returns a probability per level and the expected level. One request holds up to 64 questions, and the state and questions together must fit in 4,096 tokens.

meraGPT names three jobs: routing and triage, guardrails and checks inside agents, and scoring against a rubric such as severity or urgency. The first two match support inbox triage, intent and model routing and LLM guardrails. Every quality figure comes from meraGPT’s own runs on typed-decisions, a synthetic benchmark published under the Hugging Face organisation LocalLLaMA. meraGPT’s submission to systemonemodels.org on 29 September 2026 says its team built the benchmark. The dataset card calls the benchmark independent and does not say who built it. On the card’s 400 test cases and 2,000 decisions, from a single run, Decider 1 scores 0.768 accuracy, 0.096 KL, 0.052 Brier and 0.180 ECE, with a p50 of 526 ms end to end. Jev 1.13.0 scores 0.727, 1.442, 0.148 and 0.144 on the same cases. The card also lists Liquid AI’s d1 at 0.742 accuracy, measured on 30 September. The card builds its gold answers from three samples of one teacher model, whose self-agreement is 0.735, and says “scores well above 0.735 mean a model is learning the teacher’s quirks.” Decider 1’s 0.768 is above that line. meraGPT’s own pages call the reference an ensemble of teacher models. The card puts Jev’s KL gap down to Jev placing nearly all its probability on one answer, against a soft three-sample gold. No third-party measurement had been published by 30 September 2026, and Decider 1 does not appear on Benchmark Heaven’s JevBench v1.5.4.

meraGPT rules out open-ended answers, facts the model would need to look up, and questions with more than ten options. State is text only, and 4,096 tokens rules out whole documents. The docs warn that unrelated items batched into one state sway each other’s answers.

Decider 1 is available now at POST https://meragpt.com/v1/systemone, as state-decider-1 or sd-1. Signing in adds $1 of free credit, then you buy prepaid credit from $10. The playground needs no account. TypeSafe’s Python and TypeScript SDKs work once TYPESAFE_BASE_URL is set to https://meragpt.com with a meraGPT key. It was not on OpenRouter on 30 September 2026.

Question types Choice Score Noul Max Choice options10 Score levelsUp to 10 Questions per call64 Total context4,096 tokens State budgetNot documented Rate limitNo numeric rate limit is published. The docs say per-key concurrency limits apply and ask high-volume users to email first. A full fleet returns 429 capacity_saturated with a Retry-After of 5 seconds, or 30 seconds while extra capacity starts. The signed-out playground allows 10 runs a day per IP. EndpointPOST https://meragpt.com/v1/systemone SDKsPython: typesafe-sdkTypeScript: @typesafe-ai/sdk The state and all questions share one 4,096-token context. There is no separate state limit. A request over it returns 400 input_too_long, which is not retryable. A Choice takes 2 to 10 labels and a Score 2 to 10 levels, and one request holds up to 64 questions. State is text only, with no images, audio or video.

state-decider-1, 22 Sep 2026, The only version, with the alias sd-1. meraGPT says model ids are never renamed and a change in behaviour ships as a new id. It reserves meragpt/state-decider-1 for a future OpenRouter listing, but OpenRouter did not list it on 30 September 2026. Release notes

What people use Decider 1 for, one page per pattern. Workflow controlStarter

Send a support ticket to Jev once with every question attached. Category comes back as a selected label, severity and frustration as numbers on scales you wrote, refund intent as a probability. Your code reads those values and decides what happens to the ticket. Choice Score Noul Workflow controlIntermediate

One Jev call reads an incoming request and returns its intent as a label plus a difficulty rating on a scale you wrote. Your router reads both numbers and picks the handler: deterministic code, a cheap model, an expensive one, or a human queue. Choice Score Safety and qualityIntermediate

Put one Jev request in front of an LLM and one behind it. Yes/no questions return the probability that each hazard holds, a Score rates how much harm complying would do, and your thresholds turn those numbers into pass, review, block, or a crisis path. Noul Score

The most-starred and most-viewed entries in the directory. Browse all examples.