d1
Liquid AI's first decision model for text and images, served at a /v1/systemone endpoint callable with TypeSafe SDKs.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
d1 is Liquid AI's first decision model. According to the list summary, it handles text and images and is served at a /v1/systemone endpoint, the same API shape as Jev, so the TypeSafe SDKs can call it. It is also available on OpenRouter, text-only for now.
For developers already using Jev, d1 is an alternative backend with the same request shape. The model size is not disclosed. Details come from Liquid AI's documentation and launch blog post, which were not reviewed here.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Typed decision questions (choice, noul, score) over text or images(inferred) | — |
How it works
- Send state and typed questions to Liquid's /v1/systemone endpoint
- Receive probabilities per option
- Act on the answer in code
Strengths
- Jev-compatible API shape
- Supports images as well as text
- Available through OpenRouter
Caveats
- List-only entry
- Model size not disclosed
- OpenRouter version is text-only
Getting started
See https://docs.liquid.ai/lfm/models/decision-models.At a glance
- Type
- Library
- Status
- production
- Runtime
- hosted API
Use cases and integrations
How curated lists describe it
Liquid AI's first decision model, for text and images, served at a `/v1/systemone` endpoint that the TypeSafe SDKs can call, and on [OpenRouter](https://openrouter.ai/liquid/d1) (text only for now). Launch post: [blog](https://www.liquid.ai/blog/d1-decision-model). Model size not disclosed.
AnotiaWang/awesome-decision-models
Frequently asked questions
Can I use the TypeSafe SDK with d1?
The list summary says the TypeSafe SDKs can call its /v1/systemone endpoint.
Does it support images?
Yes on Liquid's endpoint; the OpenRouter version is text-only for now.
Who makes it?
Liquid AI.
Related projects
Free hosted Jev-style multimodal decision model API (about 20B active) that picks actions from images and options, aimed at robot control.
ServicebetaComfyUI nodes for Jev-style noul, choice and score decisions over images and text using a local imajev adapter on Qwen3.5.
ProjectbetaPythonResearch code for an image-and-text System One model that reads option-letter logits from a multimodal LLM, with training and calibration.
ProjectresearchPythonIndependent open model on Molmo2-ER that answers spatial questions by choosing from fixed options with one shared classifier head.
ProjectresearchPythonOpen project training a vision-enabled Jev-like model (0.8B, 9B) that judges dynamic candidate sets over images with Choice, Noul and Score.
ProjectresearchPythonIndependent Jev-style server on DiffusionGemma and SGLang that classifies doodles, flowers and messages with Choice, Score and Noul.
ServiceresearchPython