Liquid AI · Decision
d1
Newer version: d1.2. Our catalogue has no release date for d1.2. We compared the version names in our catalogue.
d1 is a decision model from Liquid AI: instead of generating text it reads text and images and returns typed answers (yes/no, choice, score) with calibrated probabilities, in one forward pass with no output tokens — for classification, routing, scoring, moderation, visual inspection and LLM-as-judge checks.
Evidence and sources
All rankings:
#136 on OpenRouter this month
#192 on OpenRouter this weekSources: LiteLLM data, AI/ML API data, Hugging FacePrimary data from LiteLLM
from AI/ML API: description
from Hugging Face: release date
Advantages and trade-offs
Compared with 10 representative decision models
Trade-offs
Input & output
Inputs as stated by providers; output from the model’s typeText
Choices and scores
Also known as: liquid/d1, openrouter/liquid/d1
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works