Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Solar Decide

Upstage's beta decision model on Solar Mini 4 with a 512K context and Jev's request format, offered on OpenRouter.

Modelbeta
Open source ↗Live demo ↗

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

Solar Decide is Upstage's decision model built on Solar Mini 4, listed on OpenRouter. According to the directory summary, it is in beta, has a 512K context window and uses the same request format as Jev, so clients written for Jev's typed questions can target it. A lower-latency variant, Solar Decide Flash, is also available.

No model card was fetched, so accuracy, calibration and pricing are not available here. The large context window is its main stated difference from Jev, whose request limit is around 32K tokens according to other projects in this directory.

What the decision model decides

TypeQuestionAnswers
OtherChoice/Score/Noul questions in Jev's request format(inferred)—

How it works

  1. Call Solar Decide through OpenRouter
  2. Send state and typed questions in Jev's format
  3. Read typed answers

Strengths

  • 512K context per the list summary
  • Jev-compatible request format

Caveats

  • Beta
  • Grounded only in a list summary

At a glance

Type
Model
Status
beta
Runtime
Hosted model (OpenRouter)

Use cases and integrations

How curated lists describe it

  • Upstage's decision model on Solar Mini 4, in beta, with a 512K context and the same request format as Jev. [Solar Decide Flash](https://openrouter.ai/upstage/solar-decide-flash) is the lower-latency variant.

    AnotiaWang/awesome-decision-models

Frequently asked questions

Who makes Solar Decide?

Upstage, built on Solar Mini 4.

How does it differ from Jev?

It offers a 512K context in the same request format, per the list summary.

Is there a faster version?

Yes, Solar Decide Flash.

Related projects

  • gojev

    Go harness for System One models: hosted Jev, open Kev in-process via llama.cpp, and Cloudflare Clef, with typed helpers and a CLI.

    ServicebetaGo
  • jev

    TypeScript library for one-line local decisions with open models (kev-0.6b, kev-4b, open-jev), no API keys or cloud.

    ProjectbetaTypeScript
  • jev-foundation-models

    Swift 6 bridge that runs System One decision models behind Apple's Foundation Models API, on device with Laya or via hosted endpoints.

    ProjectbetaSwift
  • laya-system-one

    Zero-dependency npm package that runs Laya natively or as WebAssembly in Node, Bun and browsers, drop-in for Jev's /v1/systemone.

    ProjectbetaJavaScript
  • OmniStudio

    Local-first desktop AI workbench for llama.cpp, vLLM and SGLang that includes a JEV typed-decision page and /v1/systemone gateway.

    Servicebeta
  • typesafe-sdk-rust (zchee)

    Vendor-neutral async Rust SDK for System One decision models with derive-based question sets and one multiplexed HTTP/2 connection.

    LibrarybetaRust