Mercury Decide
Inception's decision model on OpenRouter, with a free route, cited by Inception at up to 14 decisions per second.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
Mercury Decide is a decision model from Inception, available on OpenRouter including a free route. According to the listing, Inception cites throughput of up to 14 decisions per second. It is one of several decision models offered through OpenRouter's decisions endpoint alongside Jev.
No model card or documentation was available here, so its question types, accuracy and calibration are not confirmed. Presumably it supports the same typed decision format used by OpenRouter for Jev.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Typed decision questions via OpenRouter (details not documented here)(inferred) | — |
How it works
- Call OpenRouter's decisions endpoint with model inception/mercury-decide
- Send state and typed questions
- Receive typed answers
Strengths
- Free route available
- High cited throughput
Caveats
- No documentation available here
- Accuracy and calibration unknown
Getting started
See https://openrouter.ai/inception/mercury-decide.At a glance
- Type
- Model
- Runtime
- hosted API via OpenRouter
Use cases and integrations
How curated lists describe it
Inception's decision model, with a free route on OpenRouter; Inception cites up to 14 decisions per second.
AnotiaWang/awesome-decision-models
Frequently asked questions
Who makes Mercury Decide?
Inception.
Is it free?
A free route is listed on OpenRouter.
How fast is it?
Inception cites up to 14 decisions per second.
Related projects
Gateway that distils System One or LLM answers into small fine-tuned classifiers and serves them when confident, falling back otherwise.
ServiceprototypeRustRouter that uses Jev's cloud decisions today, logs every decision with probabilities, and distils a local routing model from your traffic.
ProjectbetaPythonResearch code showing confidence cascades let a 0.8B prefill-only decision model approach a 4B model's accuracy at a fraction of the cost.
ProjectresearchPython0.8B open System One model with task adapters that makes millisecond decisions in front of a larger local model like Qwen3.8-27B.
ModelbetaPythonDependency-free Python wrapper that turns any LLM API into a Jev-style choose-one-option decision call for old machines.
ModelprototypePythonClojure System One engine on Jolt that routes typed questions to Laya encoders, a llama.cpp 'thinker', Clef or TinyDecide.
ModelresearchClojure